facebook
/
zstd
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

v1.4.2: Merge pull request #1700 from facebook/dev

dev
Felix Handte 2019-07-25 13:44:51 -04:00 committed by GitHub
parent 52181f877a d95ac34202
commit ff304e9e65
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
35 changed files with 985 additions and 658 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
CHANGELOG
View File

@ -1,3 +1,9 @@
v1.4.2
bug: Fix bug in zstd-0.5 decoder by @terrelln (#1696)
bug: Fix seekable decompression in-memory API by @iburinoc (#1695)
misc: Validate blocks are smaller than size limit by @vivekmg (#1685)
misc: Restructure source files by @ephiepark (#1679)
v1.4.1
bug: Fix data corruption in niche use cases by @terrelln (#1659)
bug: Fuzz legacy modes, fix uncovered bugs by @terrelln (#1593, #1594, #1595)

16
build/VS2008/fullbench/fullbench.vcproj
View File

@ -364,6 +364,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstdmt_compress.c"
>
@ -494,6 +502,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.h"
>

16
build/VS2008/fuzzer/fuzzer.vcproj
View File

@ -412,6 +412,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
>
</File>
<File
RelativePath="..\..\..\lib\decompress\zstd_decompress.c"
>
@ -530,6 +538,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.h"
>

16
build/VS2008/zstd/zstd.vcproj
View File

@ -424,6 +424,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
>
</File>
<File
RelativePath="..\..\..\lib\decompress\zstd_decompress.c"
>
@ -610,6 +618,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.h"
>

16
build/VS2008/zstdlib/zstdlib.vcproj
View File

@ -396,6 +396,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.c"
>
@ -542,6 +550,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.h"
>

4
build/VS2010/fullbench/fullbench.vcxproj
View File

@ -167,6 +167,8 @@
<ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
<ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
@ -193,6 +195,8 @@
<ClInclude Include="..\..\..\lib\common\threading.h" />
<ClInclude Include="..\..\..\lib\common\xxhash.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />

4
build/VS2010/fuzzer/fuzzer.vcxproj
View File

@ -167,6 +167,8 @@
<ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@ -196,6 +198,8 @@
<ClInclude Include="..\..\..\lib\common\zstd_errors.h" />
<ClInclude Include="..\..\..\lib\zstd.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />

4
build/VS2010/libzstd-dll/libzstd-dll.vcxproj
View File

@ -31,6 +31,8 @@
<ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@ -78,6 +80,8 @@
<ClInclude Include="..\..\..\lib\zstd.h" />
<ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />

4
build/VS2010/libzstd/libzstd.vcxproj
View File

@ -31,6 +31,8 @@
<ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@ -78,6 +80,8 @@
<ClInclude Include="..\..\..\lib\zstd.h" />
<ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />

4
build/VS2010/zstd/zstd.vcxproj
View File

@ -32,6 +32,8 @@
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@ -75,6 +77,8 @@
<ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
<ClInclude Include="..\..\..\lib\common\zstd_errors.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />

74
build/cmake/lib/CMakeLists.txt
View File

@ -20,62 +20,32 @@ endif()
# Define library directory, where sources and header files are located
include_directories(${LIBRARY_DIR} ${LIBRARY_DIR}/common)
file(GLOB CommonSources ${LIBRARY_DIR}/common/*.c)
file(GLOB CompressSources ${LIBRARY_DIR}/compress/*.c)
file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c)
file(GLOB DictBuilderSources ${LIBRARY_DIR}/dictBuilder/*.c)
file(GLOB DeprecatedSources ${LIBRARY_DIR}/deprecated/*.c)
set(Sources
${LIBRARY_DIR}/common/entropy_common.c
${LIBRARY_DIR}/common/fse_decompress.c
${LIBRARY_DIR}/common/threading.c
${LIBRARY_DIR}/common/pool.c
${LIBRARY_DIR}/common/zstd_common.c
${LIBRARY_DIR}/common/error_private.c
${LIBRARY_DIR}/common/xxhash.c
${LIBRARY_DIR}/compress/hist.c
${LIBRARY_DIR}/compress/fse_compress.c
${LIBRARY_DIR}/compress/huf_compress.c
${LIBRARY_DIR}/compress/zstd_compress.c
${LIBRARY_DIR}/compress/zstdmt_compress.c
${LIBRARY_DIR}/compress/zstd_fast.c
${LIBRARY_DIR}/compress/zstd_double_fast.c
${LIBRARY_DIR}/compress/zstd_lazy.c
${LIBRARY_DIR}/compress/zstd_opt.c
${LIBRARY_DIR}/compress/zstd_ldm.c
${LIBRARY_DIR}/decompress/huf_decompress.c
${LIBRARY_DIR}/decompress/zstd_decompress.c
${LIBRARY_DIR}/decompress/zstd_decompress_block.c
${LIBRARY_DIR}/decompress/zstd_ddict.c
${LIBRARY_DIR}/dictBuilder/cover.c
${LIBRARY_DIR}/dictBuilder/fastcover.c
${LIBRARY_DIR}/dictBuilder/divsufsort.c
${LIBRARY_DIR}/dictBuilder/zdict.c
${LIBRARY_DIR}/deprecated/zbuff_common.c
${LIBRARY_DIR}/deprecated/zbuff_compress.c
${LIBRARY_DIR}/deprecated/zbuff_decompress.c)
${CommonSources}
${CompressSources}
${DecompressSources}
${DictBuilderSources}
${DeprecatedSources})
file(GLOB CommonHeaders ${LIBRARY_DIR}/common/*.h)
file(GLOB CompressHeaders ${LIBRARY_DIR}/compress/*.h)
file(GLOB DecompressHeaders ${LIBRARY_DIR}/decompress/*.h)
file(GLOB DictBuilderHeaders ${LIBRARY_DIR}/dictBuilder/*.h)
file(GLOB DeprecatedHeaders ${LIBRARY_DIR}/deprecated/*.h)
set(Headers
${LIBRARY_DIR}/zstd.h
${LIBRARY_DIR}/common/debug.h
${LIBRARY_DIR}/common/pool.h
${LIBRARY_DIR}/common/threading.h
${LIBRARY_DIR}/common/bitstream.h
${LIBRARY_DIR}/common/error_private.h
${LIBRARY_DIR}/common/zstd_errors.h
${LIBRARY_DIR}/common/fse.h
${LIBRARY_DIR}/common/huf.h
${LIBRARY_DIR}/common/mem.h
${LIBRARY_DIR}/common/zstd_internal.h
${LIBRARY_DIR}/compress/hist.h
${LIBRARY_DIR}/compress/zstd_compress_internal.h
${LIBRARY_DIR}/compress/zstd_fast.h
${LIBRARY_DIR}/compress/zstd_double_fast.h
${LIBRARY_DIR}/compress/zstd_lazy.h
${LIBRARY_DIR}/compress/zstd_opt.h
${LIBRARY_DIR}/compress/zstd_ldm.h
${LIBRARY_DIR}/compress/zstdmt_compress.h
${LIBRARY_DIR}/decompress/zstd_decompress_internal.h
${LIBRARY_DIR}/decompress/zstd_decompress_block.h
${LIBRARY_DIR}/decompress/zstd_ddict.h
${LIBRARY_DIR}/dictBuilder/zdict.h
${LIBRARY_DIR}/dictBuilder/cover.h
${LIBRARY_DIR}/deprecated/zbuff.h)
${CommonHeaders}
${CompressHeaders}
${DecompressHeaders}
${DictBuilderHeaders}
${DeprecatedHeaders})
if (ZSTD_LEGACY_SUPPORT)
set(LIBRARY_LEGACY_DIR ${LIBRARY_DIR}/legacy)

2
build/meson/lib/meson.build
View File

@ -28,6 +28,8 @@ libzstd_sources = [join_paths(zstd_rootdir, 'lib/common/entropy_common.c'),
join_paths(zstd_rootdir, 'lib/compress/fse_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/huf_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_compress_literals.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_compress_sequences.c'),
join_paths(zstd_rootdir, 'lib/compress/zstdmt_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_fast.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_double_fast.c'),

2
contrib/largeNbDicts/largeNbDicts.c
View File

@ -559,7 +559,7 @@ static int benchMem(slice_collection_t dstBlocks,
CONTROL(BMK_isSuccessful_runOutcome(outcome));
BMK_runTime_t const result = BMK_extract_runTime(outcome);
U64 const dTime_ns = result.nanoSecPerRun;
double const dTime_ns = result.nanoSecPerRun;
double const dTime_sec = (double)dTime_ns / 1000000000;
size_t const srcSize = result.sumOfReturn;
double const dSpeed_MBps = (double)srcSize / dTime_sec / (1 MB);

1
contrib/seekable_format/examples/.gitignore vendored
View File

@ -1,4 +1,5 @@
seekable_compression
seekable_decompression
seekable_decompression_mem
parallel_processing
parallel_compression

7
contrib/seekable_format/examples/Makefile
View File

@ -24,7 +24,8 @@ SEEKABLE_OBJS = ../zstdseek_compress.c ../zstdseek_decompress.c $(ZSTDLIB)
default: all
all: seekable_compression seekable_decompression parallel_processing
all: seekable_compression seekable_decompression seekable_decompression_mem \
parallel_processing
$(ZSTDLIB):
make -C $(ZSTDLIB_PATH) $(ZSTDLIB_NAME)
@ -35,6 +36,9 @@ seekable_compression : seekable_compression.c $(SEEKABLE_OBJS)
seekable_decompression : seekable_decompression.c $(SEEKABLE_OBJS)
$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
seekable_decompression_mem : seekable_decompression_mem.c $(SEEKABLE_OBJS)
$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
parallel_processing : parallel_processing.c $(SEEKABLE_OBJS)
$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@ -pthread
@ -44,5 +48,6 @@ parallel_compression : parallel_compression.c $(SEEKABLE_OBJS)
clean:
@rm -f core *.o tmp* result* *.zst \
seekable_compression seekable_decompression \
seekable_decompression_mem \
parallel_processing parallel_compression
@echo Cleaning completed

144
contrib/seekable_format/examples/seekable_decompression_mem.c Normal file
View File

@ -0,0 +1,144 @@
/*
* Copyright (c) 2017-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).
*/
#include <stdlib.h> // malloc, exit
#include <stdio.h> // fprintf, perror, feof
#include <string.h> // strerror
#include <errno.h> // errno
#define ZSTD_STATIC_LINKING_ONLY
#include <zstd.h> // presumes zstd library is installed
#include <zstd_errors.h>
#include "zstd_seekable.h"
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define MAX_FILE_SIZE (8 * 1024 * 1024)
static void* malloc_orDie(size_t size)
{
void* const buff = malloc(size);
if (buff) return buff;
/* error */
perror("malloc");
exit(1);
}
static void* realloc_orDie(void* ptr, size_t size)
{
ptr = realloc(ptr, size);
if (ptr) return ptr;
/* error */
perror("realloc");
exit(1);
}
static FILE* fopen_orDie(const char *filename, const char *instruction)
{
FILE* const inFile = fopen(filename, instruction);
if (inFile) return inFile;
/* error */
perror(filename);
exit(3);
}
static size_t fread_orDie(void* buffer, size_t sizeToRead, FILE* file)
{
size_t const readSize = fread(buffer, 1, sizeToRead, file);
if (readSize == sizeToRead) return readSize; /* good */
if (feof(file)) return readSize; /* good, reached end of file */
/* error */
perror("fread");
exit(4);
}
static size_t fwrite_orDie(const void* buffer, size_t sizeToWrite, FILE* file)
{
size_t const writtenSize = fwrite(buffer, 1, sizeToWrite, file);
if (writtenSize == sizeToWrite) return sizeToWrite; /* good */
/* error */
perror("fwrite");
exit(5);
}
static size_t fclose_orDie(FILE* file)
{
if (!fclose(file)) return 0;
/* error */
perror("fclose");
exit(6);
}
static void fseek_orDie(FILE* file, long int offset, int origin) {
if (!fseek(file, offset, origin)) {
if (!fflush(file)) return;
}
/* error */
perror("fseek");
exit(7);
}
static void decompressFile_orDie(const char* fname, off_t startOffset, off_t endOffset)
{
FILE* const fin = fopen_orDie(fname, "rb");
FILE* const fout = stdout;
// Just for demo purposes, assume file is <= MAX_FILE_SIZE
void* const buffIn = malloc_orDie(MAX_FILE_SIZE);
size_t const inSize = fread_orDie(buffIn, MAX_FILE_SIZE, fin);
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_seekable* const seekable = ZSTD_seekable_create();
if (seekable==NULL) { fprintf(stderr, "ZSTD_seekable_create() error \n"); exit(10); }
size_t const initResult = ZSTD_seekable_initBuff(seekable, buffIn, inSize);
if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_seekable_init() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
while (startOffset < endOffset) {
size_t const result = ZSTD_seekable_decompress(seekable, buffOut, MIN(endOffset - startOffset, buffOutSize), startOffset);
if (ZSTD_isError(result)) {
fprintf(stderr, "ZSTD_seekable_decompress() error : %s \n",
ZSTD_getErrorName(result));
exit(12);
}
fwrite_orDie(buffOut, result, fout);
startOffset += result;
}
ZSTD_seekable_free(seekable);
fclose_orDie(fin);
fclose_orDie(fout);
free(buffIn);
free(buffOut);
}
int main(int argc, const char** argv)
{
const char* const exeName = argv[0];
if (argc!=4) {
fprintf(stderr, "wrong arguments\n");
fprintf(stderr, "usage:\n");
fprintf(stderr, "%s FILE START END\n", exeName);
return 1;
}
{
const char* const inFilename = argv[1];
off_t const startOffset = atoll(argv[2]);
off_t const endOffset = atoll(argv[3]);
decompressFile_orDie(inFilename, startOffset, endOffset);
}
return 0;
}

4
contrib/seekable_format/zstdseek_decompress.c
View File

@ -106,7 +106,7 @@ typedef struct {
static int ZSTD_seekable_read_buff(void* opaque, void* buffer, size_t n)
{
buffWrapper_t* buff = (buffWrapper_t*) opaque;
if (buff->size + n > buff->pos) return -1;
if (buff->pos + n > buff->size) return -1;
memcpy(buffer, (const BYTE*)buff->ptr + buff->pos, n);
buff->pos += n;
return 0;
@ -124,7 +124,7 @@ static int ZSTD_seekable_seek_buff(void* opaque, long long offset, int origin)
newOffset = (unsigned long long)buff->pos + offset;
break;
case SEEK_END:
newOffset = (unsigned long long)buff->size - offset;
newOffset = (unsigned long long)buff->size + offset;
break;
default:
assert(0); /* not possible */

4
doc/zstd_manual.html
View File

@ -1,10 +1,10 @@
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>zstd 1.4.1 Manual</title>
<title>zstd 1.4.2 Manual</title>
</head>
<body>
<h1>zstd 1.4.1 Manual</h1>
<h1>zstd 1.4.2 Manual</h1>
<hr>
<a name="Contents"></a><h2>Contents</h2>
<ol>

577
lib/compress/zstd_compress.c
View File

@ -21,6 +21,8 @@
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "zstd_compress_internal.h"
#include "zstd_compress_sequences.h"
#include "zstd_compress_literals.h"
#include "zstd_fast.h"
#include "zstd_double_fast.h"
#include "zstd_lazy.h"
@ -397,18 +399,6 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
}
}
/* ZSTD_cParam_withinBounds:
* @return 1 if value is within cParam bounds,
* 0 otherwise */
static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
{
ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
if (ZSTD_isError(bounds.error)) return 0;
if (value < bounds.lowerBound) return 0;
if (value > bounds.upperBound) return 0;
return 1;
}
/* ZSTD_cParam_clampBounds:
* Clamps the value into the bounded range.
*/
@ -1903,155 +1893,6 @@ static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* s
return ZSTD_blockHeaderSize + srcSize;
}
static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE* const)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
memcpy(ostart + flSize, src, srcSize);
return srcSize + flSize;
}
static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE* const)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
(void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
ostart[flSize] = *(const BYTE*)src;
return flSize+1;
}
/* ZSTD_minGain() :
* minimum compression required
* to generate a compress block or a compressed literals section.
* note : use same formula for both situations */
static size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
{
U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
return (srcSize >> minlog) + 2;
}
static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_hufCTables_t* nextHuf,
ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
void* workspace, size_t wkspSize,
const int bmi2)
{
size_t const minGain = ZSTD_minGain(srcSize, strategy);
size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
BYTE* const ostart = (BYTE*)dst;
U32 singleStream = srcSize < 256;
symbolEncodingType_e hType = set_compressed;
size_t cLitSize;
DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
disableLiteralCompression);
/* Prepare nextEntropy assuming reusing the existing table */
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
if (disableLiteralCompression)
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
/* small ? don't even attempt compression (speed opt) */
# define COMPRESS_LITERALS_SIZE_MIN 63
{ size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
{ HUF_repeat repeat = prevHuf->repeatMode;
int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
: HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
if (repeat != HUF_repeat_none) {
/* reused the existing table */
hType = set_repeat;
}
}
if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
if (cLitSize==1) {
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
}
if (hType == set_compressed) {
/* using a newly constructed table */
nextHuf->repeatMode = HUF_repeat_check;
}
/* Build header */
switch(lhSize)
{
case 3: /* 2 - 2 - 10 - 10 */
{ U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
MEM_writeLE24(ostart, lhc);
break;
}
case 4: /* 2 - 2 - 14 - 14 */
{ U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
MEM_writeLE32(ostart, lhc);
break;
}
case 5: /* 2 - 2 - 18 - 18 */
{ U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
MEM_writeLE32(ostart, lhc);
ostart[4] = (BYTE)(cLitSize >> 10);
break;
}
default: /* not possible : lhSize is {3,4,5} */
assert(0);
}
return lhSize+cLitSize;
}
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
{
const seqDef* const sequences = seqStorePtr->sequencesStart;
@ -2074,418 +1915,6 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
}
/**
* -log2(x / 256) lookup table for x in [0, 256).
* If x == 0: Return 0
* Else: Return floor(-log2(x / 256) * 256)
*/
static unsigned const kInverseProbabilityLog256[256] = {
0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889,
874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734,
724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626,
618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542,
535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473,
468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415,
411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366,
362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322,
318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282,
279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247,
244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215,
212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185,
182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157,
155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132,
130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108,
106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85,
83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64,
62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44,
42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25,
23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7,
5, 4, 2, 1,
};
/**
* Returns the cost in bits of encoding the distribution described by count
* using the entropy bound.
*/
static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
{
unsigned cost = 0;
unsigned s;
for (s = 0; s <= max; ++s) {
unsigned norm = (unsigned)((256 * count[s]) / total);
if (count[s] != 0 && norm == 0)
norm = 1;
assert(count[s] < total);
cost += count[s] * kInverseProbabilityLog256[norm];
}
return cost >> 8;
}
/**
* Returns the cost in bits of encoding the distribution in count using the
* table described by norm. The max symbol support by norm is assumed >= max.
* norm must be valid for every symbol with non-zero probability in count.
*/
static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
unsigned const* count, unsigned const max)
{
unsigned const shift = 8 - accuracyLog;
size_t cost = 0;
unsigned s;
assert(accuracyLog <= 8);
for (s = 0; s <= max; ++s) {
unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
unsigned const norm256 = normAcc << shift;
assert(norm256 > 0);
assert(norm256 < 256);
cost += count[s] * kInverseProbabilityLog256[norm256];
}
return cost >> 8;
}
static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
void const* ptr = ctable;
U16 const* u16ptr = (U16 const*)ptr;
U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
return maxSymbolValue;
}
/**
* Returns the cost in bits of encoding the distribution in count using ctable.
* Returns an error if ctable cannot represent all the symbols in count.
*/
static size_t ZSTD_fseBitCost(
FSE_CTable const* ctable,
unsigned const* count,
unsigned const max)
{
unsigned const kAccuracyLog = 8;
size_t cost = 0;
unsigned s;
FSE_CState_t cstate;
FSE_initCState(&cstate, ctable);
RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
"Repeat FSE_CTable has maxSymbolValue %u < %u",
ZSTD_getFSEMaxSymbolValue(ctable), max);
for (s = 0; s <= max; ++s) {
unsigned const tableLog = cstate.stateLog;
unsigned const badCost = (tableLog + 1) << kAccuracyLog;
unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
if (count[s] == 0)
continue;
RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
"Repeat FSE_CTable has Prob[%u] == 0", s);
cost += count[s] * bitCost;
}
return cost >> kAccuracyLog;
}
/**
* Returns the cost in bytes of encoding the normalized count header.
* Returns an error if any of the helper functions return an error.
*/
static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
size_t const nbSeq, unsigned const FSELog)
{
BYTE wksp[FSE_NCOUNTBOUND];
S16 norm[MaxSeq + 1];
const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
}
typedef enum {
ZSTD_defaultDisallowed = 0,
ZSTD_defaultAllowed = 1
} ZSTD_defaultPolicy_e;
MEM_STATIC symbolEncodingType_e
ZSTD_selectEncodingType(
FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
FSE_CTable const* prevCTable,
short const* defaultNorm, U32 defaultNormLog,
ZSTD_defaultPolicy_e const isDefaultAllowed,
ZSTD_strategy const strategy)
{
ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
if (mostFrequent == nbSeq) {
*repeatMode = FSE_repeat_none;
if (isDefaultAllowed && nbSeq <= 2) {
/* Prefer set_basic over set_rle when there are 2 or less symbols,
* since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
* If basic encoding isn't possible, always choose RLE.
*/
DEBUGLOG(5, "Selected set_basic");
return set_basic;
}
DEBUGLOG(5, "Selected set_rle");
return set_rle;
}
if (strategy < ZSTD_lazy) {
if (isDefaultAllowed) {
size_t const staticFse_nbSeq_max = 1000;
size_t const mult = 10 - strategy;
size_t const baseLog = 3;
size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */
assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */
assert(mult <= 9 && mult >= 7);
if ( (*repeatMode == FSE_repeat_valid)
&& (nbSeq < staticFse_nbSeq_max) ) {
DEBUGLOG(5, "Selected set_repeat");
return set_repeat;
}
if ( (nbSeq < dynamicFse_nbSeq_min)
|| (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
DEBUGLOG(5, "Selected set_basic");
/* The format allows default tables to be repeated, but it isn't useful.
* When using simple heuristics to select encoding type, we don't want
* to confuse these tables with dictionaries. When running more careful
* analysis, we don't need to waste time checking both repeating tables
* and default tables.
*/
*repeatMode = FSE_repeat_none;
return set_basic;
}
}
} else {
size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
if (isDefaultAllowed) {
assert(!ZSTD_isError(basicCost));
assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
}
assert(!ZSTD_isError(NCountCost));
assert(compressedCost < ERROR(maxCode));
DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
(unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
if (basicCost <= repeatCost && basicCost <= compressedCost) {
DEBUGLOG(5, "Selected set_basic");
assert(isDefaultAllowed);
*repeatMode = FSE_repeat_none;
return set_basic;
}
if (repeatCost <= compressedCost) {
DEBUGLOG(5, "Selected set_repeat");
assert(!ZSTD_isError(repeatCost));
return set_repeat;
}
assert(compressedCost < basicCost && compressedCost < repeatCost);
}
DEBUGLOG(5, "Selected set_compressed");
*repeatMode = FSE_repeat_check;
return set_compressed;
}
MEM_STATIC size_t
ZSTD_buildCTable(void* dst, size_t dstCapacity,
FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
unsigned* count, U32 max,
const BYTE* codeTable, size_t nbSeq,
const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
const FSE_CTable* prevCTable, size_t prevCTableSize,
void* workspace, size_t workspaceSize)
{
BYTE* op = (BYTE*)dst;
const BYTE* const oend = op + dstCapacity;
DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
switch (type) {
case set_rle:
FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
*op = codeTable[0];
return 1;
case set_repeat:
memcpy(nextCTable, prevCTable, prevCTableSize);
return 0;
case set_basic:
FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */
return 0;
case set_compressed: {
S16 norm[MaxSeq + 1];
size_t nbSeq_1 = nbSeq;
const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
if (count[codeTable[nbSeq-1]] > 1) {
count[codeTable[nbSeq-1]]--;
nbSeq_1--;
}
assert(nbSeq_1 > 1);
FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
{ size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
FORWARD_IF_ERROR(NCountSize);
FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
return NCountSize;
}
}
default: assert(0); RETURN_ERROR(GENERIC);
}
}
FORCE_INLINE_TEMPLATE size_t
ZSTD_encodeSequences_body(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
BIT_CStream_t blockStream;
FSE_CState_t stateMatchLength;
FSE_CState_t stateOffsetBits;
FSE_CState_t stateLitLength;
RETURN_ERROR_IF(
ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
dstSize_tooSmall, "not enough space remaining");
DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)",
(int)(blockStream.endPtr - blockStream.startPtr),
(unsigned)dstCapacity);
/* first symbols */
FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]);
FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]);
BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
if (MEM_32bits()) BIT_flushBits(&blockStream);
BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
if (MEM_32bits()) BIT_flushBits(&blockStream);
if (longOffsets) {
U32 const ofBits = ofCodeTable[nbSeq-1];
int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
if (extraBits) {
BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
BIT_flushBits(&blockStream);
}
BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
ofBits - extraBits);
} else {
BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
}
BIT_flushBits(&blockStream);
{ size_t n;
for (n=nbSeq-2 ; n<nbSeq ; n--) { /* intentional underflow */
BYTE const llCode = llCodeTable[n];
BYTE const ofCode = ofCodeTable[n];
BYTE const mlCode = mlCodeTable[n];
U32 const llBits = LL_bits[llCode];
U32 const ofBits = ofCode;
U32 const mlBits = ML_bits[mlCode];
DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
(unsigned)sequences[n].litLength,
(unsigned)sequences[n].matchLength + MINMATCH,
(unsigned)sequences[n].offset);
/* 32b*/ /* 64b*/
/* (7)*/ /* (7)*/
FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */ /* 15 */
FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */
if (MEM_32bits()) BIT_flushBits(&blockStream); /* (7)*/
FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */
if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
BIT_flushBits(&blockStream); /* (7)*/
BIT_addBits(&blockStream, sequences[n].litLength, llBits);
if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
if (longOffsets) {
int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
if (extraBits) {
BIT_addBits(&blockStream, sequences[n].offset, extraBits);
BIT_flushBits(&blockStream); /* (7)*/
}
BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
ofBits - extraBits); /* 31 */
} else {
BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
}
BIT_flushBits(&blockStream); /* (7)*/
DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
} }
DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
FSE_flushCState(&blockStream, &stateMatchLength);
DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
FSE_flushCState(&blockStream, &stateOffsetBits);
DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
FSE_flushCState(&blockStream, &stateLitLength);
{ size_t const streamSize = BIT_closeCStream(&blockStream);
RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
return streamSize;
}
}
static size_t
ZSTD_encodeSequences_default(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
return ZSTD_encodeSequences_body(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#if DYNAMIC_BMI2
static TARGET_ATTRIBUTE("bmi2") size_t
ZSTD_encodeSequences_bmi2(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
return ZSTD_encodeSequences_body(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#endif
static size_t ZSTD_encodeSequences(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
{
DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
#if DYNAMIC_BMI2
if (bmi2) {
return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#endif
(void)bmi2;
return ZSTD_encodeSequences_default(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
{
switch (cctxParams->literalCompressionMode) {
@ -2530,8 +1959,8 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
BYTE* seqHead;
BYTE* lastNCount = NULL;
DEBUGLOG(5, "ZSTD_compressSequences_internal (nbSeq=%zu)", nbSeq);
ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
DEBUGLOG(5, "ZSTD_compressSequences_internal");
/* Compress literals */
{ const BYTE* const literals = seqStorePtr->litStart;

24
lib/compress/zstd_compress_internal.h
View File

@ -307,6 +307,30 @@ MEM_STATIC U32 ZSTD_MLcode(U32 mlBase)
return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase];
}
/* ZSTD_cParam_withinBounds:
* @return 1 if value is within cParam bounds,
* 0 otherwise */
MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
{
ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
if (ZSTD_isError(bounds.error)) return 0;
if (value < bounds.lowerBound) return 0;
if (value > bounds.upperBound) return 0;
return 1;
}
/* ZSTD_minGain() :
* minimum compression required
* to generate a compress block or a compressed literals section.
* note : use same formula for both situations */
MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
{
U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
return (srcSize >> minlog) + 2;
}
/*! ZSTD_storeSeq() :
* Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
* `offsetCode` : distance to match + 3 (values 1-3 are repCodes).

149
lib/compress/zstd_compress_literals.c Normal file
View File

@ -0,0 +1,149 @@
/*
* Copyright (c) 2016-present, Yann Collet, 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).
* You may select, at your option, one of the above-listed licenses.
*/
/*-*************************************
* Dependencies
***************************************/
#include "zstd_compress_literals.h"
size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE* const)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
memcpy(ostart + flSize, src, srcSize);
return srcSize + flSize;
}
size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE* const)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
(void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
switch(flSize)
{
case 1: /* 2 - 1 - 5 */
ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
break;
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
break;
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
ostart[flSize] = *(const BYTE*)src;
return flSize+1;
}
size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_hufCTables_t* nextHuf,
ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
void* workspace, size_t wkspSize,
const int bmi2)
{
size_t const minGain = ZSTD_minGain(srcSize, strategy);
size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
BYTE* const ostart = (BYTE*)dst;
U32 singleStream = srcSize < 256;
symbolEncodingType_e hType = set_compressed;
size_t cLitSize;
DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
disableLiteralCompression);
/* Prepare nextEntropy assuming reusing the existing table */
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
if (disableLiteralCompression)
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
/* small ? don't even attempt compression (speed opt) */
# define COMPRESS_LITERALS_SIZE_MIN 63
{ size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
{ HUF_repeat repeat = prevHuf->repeatMode;
int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
: HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
if (repeat != HUF_repeat_none) {
/* reused the existing table */
hType = set_repeat;
}
}
if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
}
if (cLitSize==1) {
memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
}
if (hType == set_compressed) {
/* using a newly constructed table */
nextHuf->repeatMode = HUF_repeat_check;
}
/* Build header */
switch(lhSize)
{
case 3: /* 2 - 2 - 10 - 10 */
{ U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
MEM_writeLE24(ostart, lhc);
break;
}
case 4: /* 2 - 2 - 14 - 14 */
{ U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
MEM_writeLE32(ostart, lhc);
break;
}
case 5: /* 2 - 2 - 18 - 18 */
{ U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
MEM_writeLE32(ostart, lhc);
ostart[4] = (BYTE)(cLitSize >> 10);
break;
}
default: /* not possible : lhSize is {3,4,5} */
assert(0);
}
return lhSize+cLitSize;
}

29
lib/compress/zstd_compress_literals.h Normal file
View File

@ -0,0 +1,29 @@
/*
* Copyright (c) 2016-present, Yann Collet, 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).
* You may select, at your option, one of the above-listed licenses.
*/
#ifndef ZSTD_COMPRESS_LITERALS_H
#define ZSTD_COMPRESS_LITERALS_H
#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */
size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_hufCTables_t* nextHuf,
ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
void* workspace, size_t wkspSize,
const int bmi2);
#endif /* ZSTD_COMPRESS_LITERALS_H */

415
lib/compress/zstd_compress_sequences.c Normal file
View File

@ -0,0 +1,415 @@
/*
* Copyright (c) 2016-present, Yann Collet, 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).
* You may select, at your option, one of the above-listed licenses.
*/
/*-*************************************
* Dependencies
***************************************/
#include "zstd_compress_sequences.h"
/**
* -log2(x / 256) lookup table for x in [0, 256).
* If x == 0: Return 0
* Else: Return floor(-log2(x / 256) * 256)
*/
static unsigned const kInverseProbabilityLog256[256] = {
0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889,
874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734,
724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626,
618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542,
535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473,
468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415,
411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366,
362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322,
318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282,
279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247,
244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215,
212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185,
182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157,
155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132,
130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108,
106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85,
83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64,
62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44,
42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25,
23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7,
5, 4, 2, 1,
};
static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
void const* ptr = ctable;
U16 const* u16ptr = (U16 const*)ptr;
U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
return maxSymbolValue;
}
/**
* Returns the cost in bytes of encoding the normalized count header.
* Returns an error if any of the helper functions return an error.
*/
static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
size_t const nbSeq, unsigned const FSELog)
{
BYTE wksp[FSE_NCOUNTBOUND];
S16 norm[MaxSeq + 1];
const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
}
/**
* Returns the cost in bits of encoding the distribution described by count
* using the entropy bound.
*/
static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
{
unsigned cost = 0;
unsigned s;
for (s = 0; s <= max; ++s) {
unsigned norm = (unsigned)((256 * count[s]) / total);
if (count[s] != 0 && norm == 0)
norm = 1;
assert(count[s] < total);
cost += count[s] * kInverseProbabilityLog256[norm];
}
return cost >> 8;
}
/**
* Returns the cost in bits of encoding the distribution in count using ctable.
* Returns an error if ctable cannot represent all the symbols in count.
*/
static size_t ZSTD_fseBitCost(
FSE_CTable const* ctable,
unsigned const* count,
unsigned const max)
{
unsigned const kAccuracyLog = 8;
size_t cost = 0;
unsigned s;
FSE_CState_t cstate;
FSE_initCState(&cstate, ctable);
RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
"Repeat FSE_CTable has maxSymbolValue %u < %u",
ZSTD_getFSEMaxSymbolValue(ctable), max);
for (s = 0; s <= max; ++s) {
unsigned const tableLog = cstate.stateLog;
unsigned const badCost = (tableLog + 1) << kAccuracyLog;
unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
if (count[s] == 0)
continue;
RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
"Repeat FSE_CTable has Prob[%u] == 0", s);
cost += count[s] * bitCost;
}
return cost >> kAccuracyLog;
}
/**
* Returns the cost in bits of encoding the distribution in count using the
* table described by norm. The max symbol support by norm is assumed >= max.
* norm must be valid for every symbol with non-zero probability in count.
*/
static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
unsigned const* count, unsigned const max)
{
unsigned const shift = 8 - accuracyLog;
size_t cost = 0;
unsigned s;
assert(accuracyLog <= 8);
for (s = 0; s <= max; ++s) {
unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
unsigned const norm256 = normAcc << shift;
assert(norm256 > 0);
assert(norm256 < 256);
cost += count[s] * kInverseProbabilityLog256[norm256];
}
return cost >> 8;
}
symbolEncodingType_e
ZSTD_selectEncodingType(
FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
FSE_CTable const* prevCTable,
short const* defaultNorm, U32 defaultNormLog,
ZSTD_defaultPolicy_e const isDefaultAllowed,
ZSTD_strategy const strategy)
{
ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
if (mostFrequent == nbSeq) {
*repeatMode = FSE_repeat_none;
if (isDefaultAllowed && nbSeq <= 2) {
/* Prefer set_basic over set_rle when there are 2 or less symbols,
* since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
* If basic encoding isn't possible, always choose RLE.
*/
DEBUGLOG(5, "Selected set_basic");
return set_basic;
}
DEBUGLOG(5, "Selected set_rle");
return set_rle;
}
if (strategy < ZSTD_lazy) {
if (isDefaultAllowed) {
size_t const staticFse_nbSeq_max = 1000;
size_t const mult = 10 - strategy;
size_t const baseLog = 3;
size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */
assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */
assert(mult <= 9 && mult >= 7);
if ( (*repeatMode == FSE_repeat_valid)
&& (nbSeq < staticFse_nbSeq_max) ) {
DEBUGLOG(5, "Selected set_repeat");
return set_repeat;
}
if ( (nbSeq < dynamicFse_nbSeq_min)
|| (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
DEBUGLOG(5, "Selected set_basic");
/* The format allows default tables to be repeated, but it isn't useful.
* When using simple heuristics to select encoding type, we don't want
* to confuse these tables with dictionaries. When running more careful
* analysis, we don't need to waste time checking both repeating tables
* and default tables.
*/
*repeatMode = FSE_repeat_none;
return set_basic;
}
}
} else {
size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
if (isDefaultAllowed) {
assert(!ZSTD_isError(basicCost));
assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
}
assert(!ZSTD_isError(NCountCost));
assert(compressedCost < ERROR(maxCode));
DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
(unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
if (basicCost <= repeatCost && basicCost <= compressedCost) {
DEBUGLOG(5, "Selected set_basic");
assert(isDefaultAllowed);
*repeatMode = FSE_repeat_none;
return set_basic;
}
if (repeatCost <= compressedCost) {
DEBUGLOG(5, "Selected set_repeat");
assert(!ZSTD_isError(repeatCost));
return set_repeat;
}
assert(compressedCost < basicCost && compressedCost < repeatCost);
}
DEBUGLOG(5, "Selected set_compressed");
*repeatMode = FSE_repeat_check;
return set_compressed;
}
size_t
ZSTD_buildCTable(void* dst, size_t dstCapacity,
FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
unsigned* count, U32 max,
const BYTE* codeTable, size_t nbSeq,
const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
const FSE_CTable* prevCTable, size_t prevCTableSize,
void* workspace, size_t workspaceSize)
{
BYTE* op = (BYTE*)dst;
const BYTE* const oend = op + dstCapacity;
DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
switch (type) {
case set_rle:
FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
*op = codeTable[0];
return 1;
case set_repeat:
memcpy(nextCTable, prevCTable, prevCTableSize);
return 0;
case set_basic:
FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */
return 0;
case set_compressed: {
S16 norm[MaxSeq + 1];
size_t nbSeq_1 = nbSeq;
const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
if (count[codeTable[nbSeq-1]] > 1) {
count[codeTable[nbSeq-1]]--;
nbSeq_1--;
}
assert(nbSeq_1 > 1);
FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
{ size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
FORWARD_IF_ERROR(NCountSize);
FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
return NCountSize;
}
}
default: assert(0); RETURN_ERROR(GENERIC);
}
}
FORCE_INLINE_TEMPLATE size_t
ZSTD_encodeSequences_body(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
BIT_CStream_t blockStream;
FSE_CState_t stateMatchLength;
FSE_CState_t stateOffsetBits;
FSE_CState_t stateLitLength;
RETURN_ERROR_IF(
ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
dstSize_tooSmall, "not enough space remaining");
DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)",
(int)(blockStream.endPtr - blockStream.startPtr),
(unsigned)dstCapacity);
/* first symbols */
FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]);
FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]);
BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
if (MEM_32bits()) BIT_flushBits(&blockStream);
BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
if (MEM_32bits()) BIT_flushBits(&blockStream);
if (longOffsets) {
U32 const ofBits = ofCodeTable[nbSeq-1];
int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
if (extraBits) {
BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
BIT_flushBits(&blockStream);
}
BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
ofBits - extraBits);
} else {
BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
}
BIT_flushBits(&blockStream);
{ size_t n;
for (n=nbSeq-2 ; n<nbSeq ; n--) { /* intentional underflow */
BYTE const llCode = llCodeTable[n];
BYTE const ofCode = ofCodeTable[n];
BYTE const mlCode = mlCodeTable[n];
U32 const llBits = LL_bits[llCode];
U32 const ofBits = ofCode;
U32 const mlBits = ML_bits[mlCode];
DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
(unsigned)sequences[n].litLength,
(unsigned)sequences[n].matchLength + MINMATCH,
(unsigned)sequences[n].offset);
/* 32b*/ /* 64b*/
/* (7)*/ /* (7)*/
FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */ /* 15 */
FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */
if (MEM_32bits()) BIT_flushBits(&blockStream); /* (7)*/
FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */
if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
BIT_flushBits(&blockStream); /* (7)*/
BIT_addBits(&blockStream, sequences[n].litLength, llBits);
if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
if (longOffsets) {
int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
if (extraBits) {
BIT_addBits(&blockStream, sequences[n].offset, extraBits);
BIT_flushBits(&blockStream); /* (7)*/
}
BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
ofBits - extraBits); /* 31 */
} else {
BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
}
BIT_flushBits(&blockStream); /* (7)*/
DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
} }
DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
FSE_flushCState(&blockStream, &stateMatchLength);
DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
FSE_flushCState(&blockStream, &stateOffsetBits);
DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
FSE_flushCState(&blockStream, &stateLitLength);
{ size_t const streamSize = BIT_closeCStream(&blockStream);
RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
return streamSize;
}
}
static size_t
ZSTD_encodeSequences_default(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
return ZSTD_encodeSequences_body(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#if DYNAMIC_BMI2
static TARGET_ATTRIBUTE("bmi2") size_t
ZSTD_encodeSequences_bmi2(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets)
{
return ZSTD_encodeSequences_body(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#endif
size_t ZSTD_encodeSequences(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
{
DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
#if DYNAMIC_BMI2
if (bmi2) {
return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}
#endif
(void)bmi2;
return ZSTD_encodeSequences_default(dst, dstCapacity,
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq, longOffsets);
}

47
lib/compress/zstd_compress_sequences.h Normal file
View File

@ -0,0 +1,47 @@
/*
* Copyright (c) 2016-present, Yann Collet, 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).
* You may select, at your option, one of the above-listed licenses.
*/
#ifndef ZSTD_COMPRESS_SEQUENCES_H
#define ZSTD_COMPRESS_SEQUENCES_H
#include "fse.h" /* FSE_repeat, FSE_CTable */
#include "zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
typedef enum {
ZSTD_defaultDisallowed = 0,
ZSTD_defaultAllowed = 1
} ZSTD_defaultPolicy_e;
symbolEncodingType_e
ZSTD_selectEncodingType(
FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
FSE_CTable const* prevCTable,
short const* defaultNorm, U32 defaultNormLog,
ZSTD_defaultPolicy_e const isDefaultAllowed,
ZSTD_strategy const strategy);
size_t
ZSTD_buildCTable(void* dst, size_t dstCapacity,
FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
unsigned* count, U32 max,
const BYTE* codeTable, size_t nbSeq,
const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
const FSE_CTable* prevCTable, size_t prevCTableSize,
void* workspace, size_t workspaceSize);
size_t ZSTD_encodeSequences(
void* dst, size_t dstCapacity,
FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
#endif /* ZSTD_COMPRESS_SEQUENCES_H */

2
lib/decompress/zstd_decompress.c
View File

@ -909,6 +909,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
{ blockProperties_t bp;
size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
if (ZSTD_isError(cBlockSize)) return cBlockSize;
RETURN_ERROR_IF(cBlockSize > dctx->fParams.blockSizeMax, corruption_detected, "Block Size Exceeds Maximum");
dctx->expected = cBlockSize;
dctx->bType = bp.blockType;
dctx->rleSize = bp.origSize;
@ -953,6 +954,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
RETURN_ERROR(corruption_detected);
}
if (ZSTD_isError(rSize)) return rSize;
RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum");
DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
dctx->decodedSize += rSize;
if (dctx->fParams.checksumFlag) XXH64_update(&dctx->xxhState, dst, rSize);

29
lib/legacy/zstd_v05.c
View File

@ -218,11 +218,6 @@ MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
}
}
MEM_STATIC U32 MEM_readLE24(const void* memPtr)
{
return MEM_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
}
MEM_STATIC U32 MEM_readLE32(const void* memPtr)
{
if (MEM_isLittleEndian())
@ -3158,10 +3153,14 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
if (litLength == MaxLL) {
const U32 add = *dumps++;
if (add < 255) litLength += add;
else if (dumps + 3 <= de) {
litLength = MEM_readLE24(dumps);
if (litLength&1) litLength>>=1, dumps += 3;
else litLength = (U16)(litLength)>>1, dumps += 2;
else if (dumps + 2 <= de) {
litLength = MEM_readLE16(dumps);
dumps += 2;
if ((litLength & 1) && dumps < de) {
litLength += *dumps << 16;
dumps += 1;
}
litLength>>=1;
}
if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */
}
@ -3191,10 +3190,14 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
if (matchLength == MaxML) {
const U32 add = dumps<de ? *dumps++ : 0;
if (add < 255) matchLength += add;
else if (dumps + 3 <= de) {
matchLength = MEM_readLE24(dumps);
if (matchLength&1) matchLength>>=1, dumps += 3;
else matchLength = (U16)(matchLength)>>1, dumps += 2;
else if (dumps + 2 <= de) {
matchLength = MEM_readLE16(dumps);
dumps += 2;
if ((matchLength & 1) && dumps < de) {
matchLength += *dumps << 16;
dumps += 1;
}
matchLength >>= 1;
}
if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */
}

2
lib/zstd.h
View File

@ -71,7 +71,7 @@ extern "C" {
/*------ Version ------*/
#define ZSTD_VERSION_MAJOR 1
#define ZSTD_VERSION_MINOR 4
#define ZSTD_VERSION_RELEASE 1
#define ZSTD_VERSION_RELEASE 2
#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< to check runtime library version */

4
programs/README.md
View File

@ -157,8 +157,8 @@ Advanced arguments :
Dictionary builder :
--train ## : create a dictionary from a training set of files
--train-cover[=k=#,d=#,steps=#,split=#] : use the cover algorithm with optional args
--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,accel=#] : use the fastcover algorithm with optional args
--train-cover[=k=#,d=#,steps=#,split=#,shrink[=#]] : use the cover algorithm with optional args
--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,shrink[=#],accel=#] : use the fastcover algorithm with optional args
--train-legacy[=s=#] : use the legacy algorithm with selectivity (default: 9)
-o file : `file` is dictionary name (default: dictionary)
--maxdict=# : limit dictionary to specified size (default: 112640)

1
programs/util.c
View File

@ -245,6 +245,7 @@ int UTIL_prepareFileList(const char *dirName, char** bufStart, size_t* pos, char
if (!followLinks && UTIL_isLink(path)) {
UTIL_DISPLAYLEVEL(2, "Warning : %s is a symbolic link, ignoring\n", path);
free(path);
continue;
}

14
programs/zstd.1
View File

@ -1,5 +1,5 @@
.
.TH "ZSTD" "1" "July 2019" "zstd 1.4.1" "User Commands"
.TH "ZSTD" "1" "July 2019" "zstd 1.4.2" "User Commands"
.
.SH "NAME"
\fBzstd\fR \- zstd, zstdmt, unzstd, zstdcat \- Compress or decompress \.zst files
@ -229,11 +229,11 @@ Split input files in blocks of size # (default: no split)
A dictionary ID is a locally unique ID that a decoder can use to verify it is using the right dictionary\. By default, zstd will create a 4\-bytes random number ID\. It\'s possible to give a precise number instead\. Short numbers have an advantage : an ID < 256 will only need 1 byte in the compressed frame header, and an ID < 65536 will only need 2 bytes\. This compares favorably to 4 bytes default\. However, it\'s up to the dictionary manager to not assign twice the same ID to 2 different dictionaries\.
.
.TP
\fB\-\-train\-cover[=k#,d=#,steps=#,split=#]\fR
Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or split <= 0, then the default value of 100 is used\. Requires that \fId\fR <= \fIk\fR\.
\fB\-\-train\-cover[=k#,d=#,steps=#,split=#,shrink[=#]]\fR
Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or split <= 0, then the default value of 100 is used\. Requires that \fId\fR <= \fIk\fR\. If \fIshrink\fR flag is not used, then the default value for \fIshrinkDict\fR of 0 is used\. If \fIshrink\fR is not specified, then the default value for \fIshrinkDictMaxRegression\fR of 1 is used\.
.
.IP
Selects segments of size \fIk\fR with highest score to put in the dictionary\. The score of a segment is computed by the sum of the frequencies of all the subsegments of size \fId\fR\. Generally \fId\fR should be in the range [6, 8], occasionally up to 16, but the algorithm will run faster with d <= \fI8\fR\. Good values for \fIk\fR vary widely based on the input data, but a safe range is [2 * \fId\fR, 2000]\. If \fIsplit\fR is 100, all input samples are used for both training and testing to find optimal \fId\fR and \fIk\fR to build dictionary\. Supports multithreading if \fBzstd\fR is compiled with threading support\.
Selects segments of size \fIk\fR with highest score to put in the dictionary\. The score of a segment is computed by the sum of the frequencies of all the subsegments of size \fId\fR\. Generally \fId\fR should be in the range [6, 8], occasionally up to 16, but the algorithm will run faster with d <= \fI8\fR\. Good values for \fIk\fR vary widely based on the input data, but a safe range is [2 * \fId\fR, 2000]\. If \fIsplit\fR is 100, all input samples are used for both training and testing to find optimal \fId\fR and \fIk\fR to build dictionary\. Supports multithreading if \fBzstd\fR is compiled with threading support\. Having \fIshrink\fR enabled takes a truncated dictionary of minimum size and doubles in size until compression ratio of the truncated dictionary is at most \fIshrinkDictMaxRegression%\fR worse than the compression ratio of the largest dictionary\.
.
.IP
Examples:
@ -253,6 +253,12 @@ Examples:
.IP
\fBzstd \-\-train\-cover=k=50,split=60 FILEs\fR
.
.IP
\fBzstd \-\-train\-cover=shrink FILEs\fR
.
.IP
\fBzstd \-\-train\-cover=shrink=2 FILEs\fR
.
.TP
\fB\-\-train\-fastcover[=k#,d=#,f=#,steps=#,split=#,accel=#]\fR
Same as cover but with extra parameters \fIf\fR and \fIaccel\fR and different default value of split If \fIsplit\fR is not specified, then it tries \fIsplit\fR = 75\. If \fIf\fR is not specified, then it tries \fIf\fR = 20\. Requires that 0 < \fIf\fR < 32\. If \fIaccel\fR is not specified, then it tries \fIaccel\fR = 1\. Requires that 0 < \fIaccel\fR <= 10\. Requires that \fId\fR = 6 or \fId\fR = 8\.

11
programs/zstd.1.md
View File

@ -244,13 +244,15 @@ Compression of small files similar to the sample set will be greatly improved.
This compares favorably to 4 bytes default.
However, it's up to the dictionary manager to not assign twice the same ID to
2 different dictionaries.
* `--train-cover[=k#,d=#,steps=#,split=#]`:
* `--train-cover[=k#,d=#,steps=#,split=#,shrink[=#]]`:
Select parameters for the default dictionary builder algorithm named cover.
If _d_ is not specified, then it tries _d_ = 6 and _d_ = 8.
If _k_ is not specified, then it tries _steps_ values in the range [50, 2000].
If _steps_ is not specified, then the default value of 40 is used.
If _split_ is not specified or split <= 0, then the default value of 100 is used.
Requires that _d_ <= _k_.
If _shrink_ flag is not used, then the default value for _shrinkDict_ of 0 is used.
If _shrink_ is not specified, then the default value for _shrinkDictMaxRegression_ of 1 is used.
Selects segments of size _k_ with highest score to put in the dictionary.
The score of a segment is computed by the sum of the frequencies of all the
@ -262,6 +264,9 @@ Compression of small files similar to the sample set will be greatly improved.
If _split_ is 100, all input samples are used for both training and testing
to find optimal _d_ and _k_ to build dictionary.
Supports multithreading if `zstd` is compiled with threading support.
Having _shrink_ enabled takes a truncated dictionary of minimum size and doubles
in size until compression ratio of the truncated dictionary is at most
_shrinkDictMaxRegression%_ worse than the compression ratio of the largest dictionary.
Examples:
@ -275,6 +280,10 @@ Compression of small files similar to the sample set will be greatly improved.
`zstd --train-cover=k=50,split=60 FILEs`
`zstd --train-cover=shrink FILEs`
`zstd --train-cover=shrink=2 FILEs`
* `--train-fastcover[=k#,d=#,f=#,steps=#,split=#,accel=#]`:
Same as cover but with extra parameters _f_ and _accel_ and different default value of split
If _split_ is not specified, then it tries _split_ = 75.

3
programs/zstdcli.c
View File

@ -294,13 +294,14 @@ static unsigned longCommandWArg(const char** stringPtr, const char* longCommand)
#ifndef ZSTD_NODICT
static const unsigned kDefaultRegression = 1;
/**
* parseCoverParameters() :
* reads cover parameters from *stringPtr (e.g. "--train-cover=k=48,d=8,steps=32") into *params
* @return 1 means that cover parameters were correct
* @return 0 in case of malformed parameters
*/
static const unsigned kDefaultRegression = 1;
static unsigned parseCoverParameters(const char* stringPtr, ZDICT_cover_params_t* params)
{
memset(params, 0, sizeof(*params));

2
programs/zstdgrep.1
View File

@ -1,5 +1,5 @@
.
.TH "ZSTDGREP" "1" "July 2019" "zstd 1.4.1" "User Commands"
.TH "ZSTDGREP" "1" "July 2019" "zstd 1.4.2" "User Commands"
.
.SH "NAME"
\fBzstdgrep\fR \- print lines matching a pattern in zstandard\-compressed files

2
programs/zstdless.1
View File

@ -1,5 +1,5 @@
.
.TH "ZSTDLESS" "1" "July 2019" "zstd 1.4.1" "User Commands"
.TH "ZSTDLESS" "1" "July 2019" "zstd 1.4.2" "User Commands"
.
.SH "NAME"
\fBzstdless\fR \- view zstandard\-compressed files

4
tests/decodecorpus.c
View File

@ -1050,8 +1050,8 @@ static void writeBlock(U32* seed, frame_t* frame, size_t contentSize,
op += contentSize;
blockType = 0;
blockSize = contentSize;
} else if (blockTypeDesc == 1) {
/* RLE */
} else if (blockTypeDesc == 1 && frame->header.contentSize > 0) {
/* RLE (Don't create RLE block if frame content is 0 since block size of 1 may exceed max block size)*/
BYTE const symbol = RAND(seed) & 0xff;
op[0] = symbol;