AuroraMiddleware/zstd
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1586 from facebook/dev

Browse Source 
v1.4.0
This commit is contained in:
Nick Terrell 2019-04-16 15:37:24 -07:00 committed by GitHub
commit 83b51e9f88
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
150 changed files with 6256 additions and 3524 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
.cirrus.yml Normal file
View 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

14
.travis.yml
View File

@ -2,7 +2,6 @@
language: c
dist: trusty
sudo: required
git:
depth: 1
@ -179,14 +178,17 @@ matrix:
# meson dedicated test
- name: Xenial (Meson + clang)
# env: ALLOW_FAILURES=true
dist: xenial
language: cpp
compiler: clang
before_install:
install:
- sudo apt-get install -qq liblz4-dev valgrind tree
- curl -o ~/get-pip.py 'https://bootstrap.pypa.io/get-pip.py'
- python3 ~/get-pip.py --user
- pip3 install --user meson ninja
- travis_retry curl -o ~/ninja.zip -L 'https://github.com/ninja-build/ninja/releases/download/v1.8.2/ninja-linux.zip'
&& unzip ~/ninja.zip -d ~/.local/bin
- travis_retry curl -o ~/get-pip.py -L 'https://bootstrap.pypa.io/get-pip.py'
&& python3 ~/get-pip.py --user
&& pip3 install --user meson
script:
- meson --buildtype=debug
-Db_lundef=false
@ -198,4 +200,4 @@ matrix:
- DESTDIR=./staging ninja install
- tree ./staging
allow_failures:
- name: Xenial (Meson + clang)
- env: ALLOW_FAILURES=true

39
CHANGELOG
View File

@ -1,3 +1,40 @@
v1.4.0
perf: Improve level 1 compression speed in most scenarios by 6% by @gbtucker and @terrelln
api: Move the advanced API, including all functions in the staging section, to the stable section
api: Make ZSTD_e_flush and ZSTD_e_end block for maximum forward progress
api: Rename ZSTD_CCtxParam_getParameter to ZSTD_CCtxParams_getParameter
api: Rename ZSTD_CCtxParam_setParameter to ZSTD_CCtxParams_setParameter
api: Don't export ZSTDMT functions from the shared library by default
api: Require ZSTD_MULTITHREAD to be defined to use ZSTDMT
api: Add ZSTD_decompressBound() to provide an upper bound on decompressed size by @shakeelrao
api: Fix ZSTD_decompressDCtx() corner cases with a dictionary
api: Move ZSTD_getDictID_*() functions to the stable section
api: Add ZSTD_c_literalCompressionMode flag to enable or disable literal compression by @terrelln
api: Allow compression parameters to be set when a dictionary is used
api: Allow setting parameters before or after ZSTD_CCtx_loadDictionary() is called
api: Fix ZSTD_estimateCStreamSize_usingCCtxParams()
api: Setting ZSTD_d_maxWindowLog to 0 means use the default
cli: Ensure that a dictionary is not used to compress itself by @shakeelrao
cli: Add --[no-]compress-literals flag to enable or disable literal compression
doc: Update the examples to use the advanced API
doc: Explain how to transition from old streaming functions to the advanced API in the header
build: Improve the Windows release packages
build: Improve CMake build by @hjmjohnson
build: Build fixes for FreeBSD by @lwhsu
build: Remove redundant warnings by @thatsafunnyname
build: Fix tests on OpenBSD by @bket
build: Extend fuzzer build system to work with the new clang engine
build: CMake now creates the libzstd.so.1 symlink
build: Improve Menson build by @lzutao
misc: Fix symbolic link detection on FreeBSD
misc: Use physical core count for -T0 on FreeBSD by @cemeyer
misc: Fix zstd --list on truncated files by @kostmo
misc: Improve logging in debug mode by @felixhandte
misc: Add CirrusCI tests by @lwhsu
misc: Optimize dictionary memory usage in corner cases
misc: Improve the dictionary builder on small or homogeneous data
misc: Fix spelling across the repo by @jsoref
v1.3.8
perf: better decompression speed on large files (+7%) and cold dictionaries (+15%)
perf: slightly better compression ratio at high compression modes
@ -239,7 +276,7 @@ v1.0.0
Change Licensing, all project is now BSD, Copyright Facebook
Small decompression speed improvement
API : Streaming API supports legacy format
API : ZDICT_getDictID(), ZSTD_sizeof_{CCtx, DCtx, CStream, DStream}(), ZSTD_setDStreamParamter()
API : ZDICT_getDictID(), ZSTD_sizeof_{CCtx, DCtx, CStream, DStream}(), ZSTD_setDStreamParameter()
CLI supports legacy formats v0.4+
Fixed : compression fails on certain huge files, reported by Jesse McGrew
Enhanced documentation, by Przemyslaw Skibinski

8
Makefile
View File

@ -156,7 +156,7 @@ list:
done \
} | column -t -s $$'\t'
.PHONY: install clangtest armtest usan asan uasan
.PHONY: install armtest usan asan uasan
install:
@$(MAKE) -C $(ZSTDDIR) $@
@$(MAKE) -C $(PRGDIR) $@
@ -188,7 +188,7 @@ gcc7build: clean
.PHONY: clangbuild
clangbuild: clean
clang -v
CXX=clang++ CC=clang $(MAKE) all MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
CXX=clang++ CC=clang CFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation" $(MAKE) all
m32build: clean
gcc -v
@ -232,10 +232,6 @@ gcc6test: clean
gcc-6 -v
$(MAKE) all CC=gcc-6 MOREFLAGS="-Werror"
clangtest: clean
clang -v
$(MAKE) all CXX=clang++ CC=clang MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
armtest: clean
$(MAKE) -C $(TESTDIR) datagen # use native, faster
$(MAKE) -C $(TESTDIR) test CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static" FUZZER_FLAGS=--no-big-tests

25
README.md
View File

@ -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
@ -21,14 +22,16 @@ 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
For reference, several fast compression algorithms were tested and compared
on a server running Linux Debian (`Linux version 4.14.0-3-amd64`),
with a Core i7-6700K CPU @ 4.0GHz,
on a server running Arch Linux (`Linux version 5.0.5-arch1-1`),
with a Core i9-9900K CPU @ 5.0GHz,
using [lzbench], an open-source in-memory benchmark by @inikep
compiled with [gcc] 7.3.0,
compiled with [gcc] 8.2.1,
on the [Silesia compression corpus].
[lzbench]: https://github.com/inikep/lzbench
@ -37,14 +40,14 @@ on the [Silesia compression corpus].
| Compressor name | Ratio | Compression| Decompress.|
| --------------- | ------| -----------| ---------- |
| **zstd 1.3.4 -1** | 2.877 | 470 MB/s | 1380 MB/s |
| zlib 1.2.11 -1 | 2.743 | 110 MB/s | 400 MB/s |
| brotli 1.0.2 -0 | 2.701 | 410 MB/s | 430 MB/s |
| quicklz 1.5.0 -1 | 2.238 | 550 MB/s | 710 MB/s |
| lzo1x 2.09 -1 | 2.108 | 650 MB/s | 830 MB/s |
| lz4 1.8.1 | 2.101 | 750 MB/s | 3700 MB/s |
| snappy 1.1.4 | 2.091 | 530 MB/s | 1800 MB/s |
| lzf 3.6 -1 | 2.077 | 400 MB/s | 860 MB/s |
| **zstd 1.4.0 -1** | 2.884 | 530 MB/s | 1360 MB/s |
| zlib 1.2.11 -1 | 2.743 | 110 MB/s | 440 MB/s |
| brotli 1.0.7 -0 | 2.701 | 430 MB/s | 470 MB/s |
| quicklz 1.5.0 -1 | 2.238 | 600 MB/s | 800 MB/s |
| lzo1x 2.09 -1 | 2.106 | 680 MB/s | 950 MB/s |
| lz4 1.8.3 | 2.101 | 800 MB/s | 4220 MB/s |
| snappy 1.1.4 | 2.073 | 580 MB/s | 2020 MB/s |
| lzf 3.6 -1 | 2.077 | 440 MB/s | 930 MB/s |
[zlib]: http://www.zlib.net/
[LZ4]: http://www.lz4.org/

4
build/VS2008/fullbench/fullbench.vcproj
View File

@ -408,6 +408,10 @@
RelativePath="..\..\..\programs\util.c"
>
</File>
<File
RelativePath="..\..\..\programs\timefn.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_fast.c"
>

12
build/VS2008/fuzzer/fuzzer.vcproj
View File

@ -45,7 +45,7 @@
Name="VCCLCompilerTool"
Optimization="0"
AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
PreprocessorDefinitions="WIN32;_DEBUG;_CONSOLE"
PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE"
MinimalRebuild="true"
BasicRuntimeChecks="3"
RuntimeLibrary="3"
@ -121,7 +121,7 @@
EnableIntrinsicFunctions="true"
OmitFramePointers="true"
AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
PreprocessorDefinitions="WIN32;NDEBUG;_CONSOLE"
PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE"
RuntimeLibrary="0"
EnableFunctionLevelLinking="true"
UsePrecompiledHeader="0"
@ -195,7 +195,7 @@
Name="VCCLCompilerTool"
Optimization="0"
AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
PreprocessorDefinitions="WIN32;_DEBUG;_CONSOLE"
PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE"
MinimalRebuild="true"
BasicRuntimeChecks="3"
RuntimeLibrary="3"
@ -272,7 +272,7 @@
EnableIntrinsicFunctions="true"
OmitFramePointers="true"
AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\programs"
PreprocessorDefinitions="WIN32;NDEBUG;_CONSOLE"
PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE"
RuntimeLibrary="0"
EnableFunctionLevelLinking="true"
UsePrecompiledHeader="0"
@ -332,6 +332,10 @@
RelativePath="..\..\..\programs\util.c"
>
</File>
<File
RelativePath="..\..\..\programs\timefn.c"
>
</File>
<File
RelativePath="..\..\..\programs\datagen.c"
>

4
build/VS2008/zstd/zstd.vcproj
View File

@ -336,6 +336,10 @@
RelativePath="..\..\..\programs\util.c"
>
</File>
<File
RelativePath="..\..\..\programs\timefn.c"
>
</File>
<File
RelativePath="..\..\..\programs\benchfn.c"
>

1
build/VS2010/fullbench-dll/fullbench-dll.vcxproj
View File

@ -167,6 +167,7 @@
<ItemGroup>
<ClCompile Include="..\..\..\lib\common\xxhash.c" />
<ClCompile Include="..\..\..\programs\util.c" />
<ClCompile Include="..\..\..\programs\timefn.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />
<ClCompile Include="..\..\..\programs\benchfn.c" />
<ClCompile Include="..\..\..\tests\fullbench.c" />

3
build/VS2010/fullbench/fullbench.vcxproj
View File

@ -156,7 +156,6 @@
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="..\..\..\lib\common\entropy_common.c" />
<ClCompile Include="..\..\..\programs\util.c" />
<ClCompile Include="..\..\..\lib\common\debug.c" />
<ClCompile Include="..\..\..\lib\common\fse_decompress.c" />
<ClCompile Include="..\..\..\lib\common\zstd_common.c" />
@ -178,6 +177,8 @@
<ClCompile Include="..\..\..\lib\decompress\zstd_decompress.c" />
<ClCompile Include="..\..\..\lib\decompress\zstd_decompress_block.c" />
<ClCompile Include="..\..\..\lib\decompress\zstd_ddict.c" />
<ClCompile Include="..\..\..\programs\util.c" />
<ClCompile Include="..\..\..\programs\timefn.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />
<ClCompile Include="..\..\..\programs\benchfn.c" />
<ClCompile Include="..\..\..\tests\fullbench.c" />

9
build/VS2010/fuzzer/fuzzer.vcxproj
View File

@ -90,7 +90,7 @@
</PrecompiledHeader>
<WarningLevel>Level4</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<TreatWarningAsError>true</TreatWarningAsError>
<EnablePREfast>false</EnablePREfast>
</ClCompile>
@ -105,7 +105,7 @@
</PrecompiledHeader>
<WarningLevel>Level4</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<TreatWarningAsError>true</TreatWarningAsError>
<EnablePREfast>false</EnablePREfast>
</ClCompile>
@ -122,7 +122,7 @@
<Optimization>MaxSpeed</Optimization>
<FunctionLevelLinking>true</FunctionLevelLinking>
<IntrinsicFunctions>true</IntrinsicFunctions>
<PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<EnablePREfast>false</EnablePREfast>
<TreatWarningAsError>false</TreatWarningAsError>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
@ -142,7 +142,7 @@
<Optimization>MaxSpeed</Optimization>
<FunctionLevelLinking>true</FunctionLevelLinking>
<IntrinsicFunctions>true</IntrinsicFunctions>
<PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<TreatWarningAsError>false</TreatWarningAsError>
<EnablePREfast>false</EnablePREfast>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
@ -182,6 +182,7 @@
<ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
<ClCompile Include="..\..\..\programs\util.c" />
<ClCompile Include="..\..\..\programs\timefn.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />
<ClCompile Include="..\..\..\tests\fuzzer.c" />
</ItemGroup>

1
build/VS2010/zstd/zstd.vcxproj
View File

@ -53,6 +53,7 @@
<ClCompile Include="..\..\..\lib\legacy\zstd_v06.c" />
<ClCompile Include="..\..\..\lib\legacy\zstd_v07.c" />
<ClCompile Include="..\..\..\programs\util.c" />
<ClCompile Include="..\..\..\programs\timefn.c" />
<ClCompile Include="..\..\..\programs\benchfn.c" />
<ClCompile Include="..\..\..\programs\benchzstd.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />

56
build/cmake/CMakeLists.txt
View File

@ -7,17 +7,57 @@
# in the COPYING file in the root directory of this source tree).
# ################################################################
cmake_minimum_required(VERSION 2.8.9)
project(zstd)
set(ZSTD_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../..")
if (NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
message(STATUS "No build type selected, defaulting to Release")
set(CMAKE_BUILD_TYPE "Release")
cmake_minimum_required(VERSION 2.8.9 FATAL_ERROR)
# As of 2018-12-26 ZSTD has been validated to build with cmake version 3.13.2 new policies.
# Set and use the newest cmake policies that are validated to work
set(ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION "3")
set(ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION "13") #Policies never changed at PATCH level
if("${CMAKE_MAJOR_VERSION}" LESS 3)
set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}")
elseif( "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}" EQUAL "${CMAKE_MAJOR_VERSION}" AND
"${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}" GREATER "${CMAKE_MINOR_VERSION}")
set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}")
else()
set(ZSTD_CMAKE_POLICY_VERSION "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}.${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}.0")
endif()
cmake_policy(VERSION ${ZSTD_CMAKE_POLICY_VERSION})
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMakeModules")
set(ZSTD_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../..")
set(LIBRARY_DIR ${ZSTD_SOURCE_DIR}/lib)
# Parse version
include(GetZstdLibraryVersion)
GetZstdLibraryVersion(${LIBRARY_DIR}/zstd.h zstd_VERSION_MAJOR zstd_VERSION_MINOR zstd_VERSION_PATCH)
if( CMAKE_MAJOR_VERSION LESS 3 )
## Provide cmake 3+ behavior for older versions of cmake
project(zstd)
set(PROJECT_VERSION_MAJOR ${zstd_VERSION_MAJOR})
set(PROJECT_VERSION_MINOR ${zstd_VERSION_MINOR})
set(PROJECT_VERSION_PATCH ${zstd_VERSION_PATCH})
set(PROJECT_VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
enable_language(C) # Main library is in C
enable_language(CXX) # Testing contributed code also utilizes CXX
else()
project(zstd
VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}"
LANGUAGES C # Main library is in C
CXX # Testing contributed code also utilizes CXX
)
endif()
message(STATUS "ZSTD VERSION: ${zstd_VERSION}")
set(zstd_HOMEPAGE_URL "http://www.zstd.net")
set(zstd_DESCRIPTION "Zstandard is a real-time compression algorithm, providing high compression ratios.")
# Set a default build type if none was specified
if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
message(STATUS "Setting build type to 'Release' as none was specified.")
set(CMAKE_BUILD_TYPE Release CACHE STRING "Choose the type of build." FORCE)
# Set the possible values of build type for cmake-gui
set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
endif()
include(GNUInstallDirs)
#-----------------------------------------------------------------------------

12
build/cmake/CMakeModules/AddZstdCompilationFlags.cmake
View File

@ -50,9 +50,11 @@ macro(ADD_ZSTD_COMPILATION_FLAGS)
CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO
CMAKE_CXX_FLAGS CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE
CMAKE_CXX_FLAGS_MINSIZEREL CMAKE_CXX_FLAGS_RELWITHDEBINFO)
separate_arguments(${flag_var})
list(REMOVE_DUPLICATES ${flag_var})
string(REPLACE ";" " " ${flag_var} "${${flag_var}}")
if( ${flag_var} )
separate_arguments(${flag_var})
list(REMOVE_DUPLICATES ${flag_var})
string(REPLACE ";" " " ${flag_var} "${${flag_var}}")
endif()
endforeach ()
if (MSVC AND ZSTD_USE_STATIC_RUNTIME)
@ -60,7 +62,9 @@ macro(ADD_ZSTD_COMPILATION_FLAGS)
CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO
CMAKE_CXX_FLAGS CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE
CMAKE_CXX_FLAGS_MINSIZEREL CMAKE_CXX_FLAGS_RELWITHDEBINFO)
string(REGEX REPLACE "/MD" "/MT" ${flag_var} "${${flag_var}}")
if ( ${flag_var} )
string(REGEX REPLACE "/MD" "/MT" ${flag_var} "${${flag_var}}")
endif()
endforeach ()
endif ()

5
build/cmake/CMakeModules/GetZstdLibraryVersion.cmake
View File

@ -1,9 +1,10 @@
function(GetZstdLibraryVersion _header _major _minor _release)
function(GetZstdLibraryVersion _header _major _minor _patch)
# Read file content
file(READ ${_header} CONTENT)
string(REGEX MATCH ".*define ZSTD_VERSION_MAJOR *([0-9]+).*define ZSTD_VERSION_MINOR *([0-9]+).*define ZSTD_VERSION_RELEASE *([0-9]+)" VERSION_REGEX "${CONTENT}")
set(${_major} ${CMAKE_MATCH_1} PARENT_SCOPE)
set(${_minor} ${CMAKE_MATCH_2} PARENT_SCOPE)
set(${_release} ${CMAKE_MATCH_3} PARENT_SCOPE)
set(${_patch} ${CMAKE_MATCH_3} PARENT_SCOPE)
endfunction()

2
build/cmake/README.md
View File

@ -3,7 +3,7 @@
Contributions to the cmake build configurations are welcome. Please
use case sensitivity that matches modern (ie. cmake version 2.6 and above)
conventions of using lower-case for commands, and upper-case for
varibles.
variables.
# CMake Style Recommendations

11
build/cmake/lib/CMakeLists.txt
View File

@ -18,14 +18,8 @@ if(NOT ZSTD_BUILD_SHARED AND NOT ZSTD_BUILD_STATIC)
endif()
# Define library directory, where sources and header files are located
set(LIBRARY_DIR ${ZSTD_SOURCE_DIR}/lib)
include_directories(${LIBRARY_DIR} ${LIBRARY_DIR}/common)
# Parse version
include(GetZstdLibraryVersion)
GetZstdLibraryVersion(${LIBRARY_DIR}/zstd.h LIBVER_MAJOR LIBVER_MINOR LIBVER_RELEASE)
message(STATUS "ZSTD VERSION ${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE}")
set(Sources
${LIBRARY_DIR}/common/entropy_common.c
${LIBRARY_DIR}/common/fse_decompress.c
@ -155,7 +149,8 @@ if (ZSTD_BUILD_SHARED)
libzstd_shared
PROPERTIES
OUTPUT_NAME zstd
SOVERSION ${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE})
VERSION ${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}
SOVERSION ${zstd_VERSION_MAJOR})
endif ()
if (ZSTD_BUILD_STATIC)
@ -170,7 +165,7 @@ if (UNIX)
set(PREFIX "${CMAKE_INSTALL_PREFIX}")
set(LIBDIR "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
set(INCLUDEDIR "${CMAKE_INSTALL_PREFIX}/include")
set(VERSION "${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE}")
set(VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
add_custom_target(libzstd.pc ALL
${CMAKE_COMMAND} -DIN="${LIBRARY_DIR}/libzstd.pc.in" -DOUT="libzstd.pc"
-DPREFIX="${PREFIX}" -DLIBDIR="${LIBDIR}" -DINCLUDEDIR="${INCLUDEDIR}" -DVERSION="${VERSION}"

4
build/cmake/programs/CMakeLists.txt
View File

@ -26,7 +26,7 @@ if (MSVC)
set(PlatformDependResources ${MSVC_RESOURCE_DIR}/zstd.rc)
endif ()
add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PlatformDependResources})
add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PlatformDependResources})
target_link_libraries(zstd libzstd_static)
if (CMAKE_SYSTEM_NAME MATCHES "(Solaris|SunOS)")
target_link_libraries(zstd rt)
@ -63,7 +63,7 @@ if (UNIX)
install(FILES ${CMAKE_CURRENT_BINARY_DIR}/zstdgrep.1 DESTINATION "${MAN_INSTALL_DIR}")
install(FILES ${CMAKE_CURRENT_BINARY_DIR}/zstdless.1 DESTINATION "${MAN_INSTALL_DIR}")
add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/fileio.c)
add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c)
target_link_libraries(zstd-frugal libzstd_static)
set_property(TARGET zstd-frugal APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_NOBENCH;ZSTD_NODICT")
endif ()

6
build/cmake/tests/CMakeLists.txt
View File

@ -43,13 +43,13 @@ include_directories(${TESTS_DIR} ${PROGRAMS_DIR} ${LIBRARY_DIR} ${LIBRARY_DIR}/c
add_executable(datagen ${PROGRAMS_DIR}/datagen.c ${TESTS_DIR}/datagencli.c)
target_link_libraries(datagen libzstd_static)
add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
target_link_libraries(fullbench libzstd_static)
add_executable(fuzzer ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${TESTS_DIR}/fuzzer.c)
add_executable(fuzzer ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/fuzzer.c)
target_link_libraries(fuzzer libzstd_static)
if (UNIX)
add_executable(paramgrill ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${TESTS_DIR}/paramgrill.c)
add_executable(paramgrill ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/paramgrill.c)
target_link_libraries(paramgrill libzstd_static m) #m is math library
endif ()

4
build/meson/README.md
View File

@ -7,7 +7,7 @@ modern software development tools and practices, such as unit tests,
coverage reports, Valgrind, CCache and the like.
This Meson build system is provided with no guarantee and maintained
by Dima Krasner <dima@dimakrasner.com>.
by Dima Krasner \<dima@dimakrasner.com\>.
It outputs one `libzstd`, either shared or static, depending on
`default_library` option.
@ -17,7 +17,7 @@ It outputs one `libzstd`, either shared or static, depending on
`cd` to this meson directory (`build/meson`)
```sh
meson --buildtype=release -D with-contrib=true -D with-tests=true -D with-contrib=true builddir
meson --buildtype=release -Dbuild_{programs,contrib}=true builddir
cd builddir
ninja # to build
ninja install # to install

6
build/meson/lib/meson.build
View File

@ -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
@ -116,9 +116,9 @@ libzstd = library('zstd',
libzstd_dep = declare_dependency(link_with: libzstd,
include_directories: libzstd_includes)
pkgconfig.generate(name: 'libzstd',
pkgconfig.generate(libzstd,
name: 'libzstd',
filebase: 'libzstd',
libraries: [libzstd],
description: 'fast lossless compression algorithm library',
version: zstd_libversion,
url: 'http://www.zstd.net/')

6
build/meson/meson.build
View File

@ -11,9 +11,11 @@
project('zstd',
['c', 'cpp'],
license: ['BSD', 'GPLv2'],
default_options : ['c_std=c99',
default_options : [
'c_std=c99',
'cpp_std=c++11',
'buildtype=release'],
'buildtype=release'
],
version: '1.3.8',
meson_version: '>=0.47.0')

2
build/meson/programs/meson.build
View File

@ -12,6 +12,7 @@ zstd_rootdir = '../../..'
zstd_programs_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'programs/fileio.c'),
join_paths(zstd_rootdir, 'programs/benchfn.c'),
join_paths(zstd_rootdir, 'programs/benchzstd.c'),
@ -63,6 +64,7 @@ zstd = executable('zstd',
install: true)
zstd_frugal_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/fileio.c')]

7
build/meson/tests/meson.build
View File

@ -40,6 +40,7 @@ datagen = executable('datagen',
fullbench_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'programs/benchfn.c'),
join_paths(zstd_rootdir, 'programs/benchzstd.c'),
join_paths(zstd_rootdir, 'tests/fullbench.c')]
@ -51,6 +52,7 @@ fullbench = executable('fullbench',
fuzzer_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'tests/fuzzer.c')]
fuzzer = executable('fuzzer',
fuzzer_sources,
@ -60,6 +62,7 @@ fuzzer = executable('fuzzer',
zbufftest_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'tests/zbufftest.c')]
zbufftest = executable('zbufftest',
zbufftest_sources,
@ -70,6 +73,7 @@ zbufftest = executable('zbufftest',
zstreamtest_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'tests/seqgen.c'),
join_paths(zstd_rootdir, 'tests/zstreamtest.c')]
zstreamtest = executable('zstreamtest',
@ -79,6 +83,7 @@ zstreamtest = executable('zstreamtest',
install: false)
paramgrill_sources = [join_paths(zstd_rootdir, 'programs/benchfn.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'programs/benchzstd.c'),
join_paths(zstd_rootdir, 'programs/datagen.c'),
join_paths(zstd_rootdir, 'programs/util.c'),
@ -116,6 +121,7 @@ legacy = executable('legacy',
install: false)
decodecorpus_sources = [join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'tests/decodecorpus.c')]
decodecorpus = executable('decodecorpus',
decodecorpus_sources,
@ -132,6 +138,7 @@ symbols = executable('symbols',
install: false)
poolTests_sources = [join_paths(zstd_rootdir, 'programs/util.c'),
join_paths(zstd_rootdir, 'programs/timefn.c'),
join_paths(zstd_rootdir, 'tests/poolTests.c'),
join_paths(zstd_rootdir, 'lib/common/pool.c'),
join_paths(zstd_rootdir, 'lib/common/threading.c'),

6
contrib/adaptive-compression/Makefile
View File

@ -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)
@ -22,10 +22,10 @@ FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) $(MULTITHREAD_LDFLAGS)
all: adapt datagen
adapt: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
adapt: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
$(CC) $(FLAGS) $^ -o $@
adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
$(CC) $(FLAGS) -DDEBUG_MODE=2 $^ -o adapt
datagen : $(PRGDIR)/datagen.c datagencli.c

1
contrib/adaptive-compression/adapt.c
View File

@ -13,6 +13,7 @@
#include <string.h> /* memset */
#include "zstd_internal.h"
#include "util.h"
#include "timefn.h" /* UTIL_time_t, UTIL_getTime, UTIL_getSpanTimeMicro */
#define DISPLAY(...) fprintf(stderr, __VA_ARGS__)
#define PRINT(...) fprintf(stdout, __VA_ARGS__)

2
contrib/docker/README.md
View File

@ -5,7 +5,7 @@ The `Dockerfile` script requires a version of `docker` >= 17.05
## Installing docker
The officiel docker install docs use a ppa with a modern version available:
The official docker install docs use a ppa with a modern version available:
https://docs.docker.com/install/linux/docker-ce/ubuntu/
## How to run

4
contrib/experimental_dict_builders/benchmarkDictBuilder/benchmark.c
View File

@ -127,7 +127,7 @@ dictInfo* createDictFromFiles(sampleInfo *info, unsigned maxDictSize,
/** compressWithDict() :
* Compress samples from sample buffer given dicionary stored on dictionary buffer and compression level
* Compress samples from sample buffer given dictionary stored on dictionary buffer and compression level
* @return compression ratio
*/
double compressWithDict(sampleInfo *srcInfo, dictInfo* dInfo, int compressionLevel, int displayLevel) {
@ -194,7 +194,7 @@ double compressWithDict(sampleInfo *srcInfo, dictInfo* dInfo, int compressionLev
totalCompressedSize += compressedSize;
}
/* Sum orignal sizes */
/* Sum original sizes */
for (i = 0; i<srcInfo->nbSamples; i++) {
totalOriginalSize += srcInfo->samplesSizes[i];
}

4
contrib/experimental_dict_builders/fastCover/fastCover.c
View File

@ -125,7 +125,7 @@ typedef struct {
*
* Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
*
* Once the dmer with hash value d is in the dictionay we set F(d) = F(d)/2.
* Once the dmer with hash value d is in the dictionary we set F(d) = F(d)/2.
*/
static FASTCOVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
U32 *freqs, U32 begin,U32 end,
@ -149,7 +149,7 @@ static FASTCOVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
while (activeSegment.end < end) {
/* Get hash value of current dmer */
const size_t index = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, parameters.f, ctx->d);
/* Add frequency of this index to score if this is the first occurence of index in active segment */
/* Add frequency of this index to score if this is the first occurrence of index in active segment */
if (ctx->segmentFreqs[index] == 0) {
activeSegment.score += freqs[index];
}

10
contrib/largeNbDicts/Makefile
View File

@ -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)
@ -28,14 +28,17 @@ default: largeNbDicts
all : largeNbDicts
largeNbDicts: util.o benchfn.o datagen.o xxhash.o largeNbDicts.c $(LIBZSTD)
largeNbDicts: util.o timefn.o benchfn.o datagen.o xxhash.o largeNbDicts.c $(LIBZSTD)
$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
.PHONY: $(LIBZSTD)
$(LIBZSTD):
$(MAKE) -C $(LIBDIR) libzstd.a CFLAGS="$(CFLAGS)"
benchfn.o : $(PROGDIR)/benchfn.c
benchfn.o: $(PROGDIR)/benchfn.c
$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
timefn.o: $(PROGDIR)/timefn.c
$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
datagen.o: $(PROGDIR)/datagen.c
@ -48,6 +51,7 @@ util.o: $(PROGDIR)/util.c
xxhash.o : $(LIBDIR)/common/xxhash.c
$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
clean:
$(RM) *.o
$(MAKE) -C $(LIBDIR) clean > /dev/null

2
contrib/largeNbDicts/largeNbDicts.c
View File

@ -424,7 +424,7 @@ static ddict_collection_t createDDictCollection(const void* dictBuffer, size_t d
}
/* mess with adresses, so that linear scanning dictionaries != linear address scanning */
/* mess with addresses, so that linear scanning dictionaries != linear address scanning */
void shuffleDictionaries(ddict_collection_t dicts)
{
size_t const nbDicts = dicts.nbDDict;

16
contrib/linux-kernel/0002-lib-Add-zstd-modules.patch
View File

@ -4,7 +4,7 @@ Date: Mon, 17 Jul 2017 17:08:19 -0700
Subject: [PATCH v5 2/5] lib: Add zstd modules
Add zstd compression and decompression kernel modules.
zstd offers a wide varity of compression speed and quality trade-offs.
zstd offers a wide variety of compression speed and quality trade-offs.
It can compress at speeds approaching lz4, and quality approaching lzma.
zstd decompressions at speeds more than twice as fast as zlib, and
decompression speed remains roughly the same across all compression levels.
@ -21,7 +21,7 @@ will be easier to keep the kernel zstd up to date.
I benchmarked zstd compression as a special character device. I ran zstd
and zlib compression at several levels, as well as performing no
compression, which measure the time spent copying the data to kernel space.
Data is passed to the compresser 4096 B at a time. The benchmark file is
Data is passed to the compressor 4096 B at a time. The benchmark file is
located in the upstream zstd source repository under
`contrib/linux-kernel/zstd_compress_test.c` [2].
@ -86,7 +86,7 @@ Tested in userland using the test-suite in the zstd repo under
`contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel
functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under
`contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8]
with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the
with ASAN, UBSAN, and MSAN. Additionally, it was tested while testing the
BtrFS and SquashFS patches coming next.
[1] https://clang.llvm.org/docs/ClangFormat.html
@ -4200,14 +4200,14 @@ index 0000000..ff18ae6
+ BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
+ U32 const fcsCode =
+ params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
+ BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
+ BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
+ size_t pos;
+
+ if (dstCapacity < ZSTD_frameHeaderSize_max)
+ return ERROR(dstSize_tooSmall);
+
+ ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
+ op[4] = frameHeaderDecriptionByte;
+ op[4] = frameHeaderDescriptionByte;
+ pos = 5;
+ if (!singleSegment)
+ op[pos++] = windowLogByte;
@ -8812,8 +8812,8 @@ index 0000000..ef3d174
+ U32 position = 0;
+ U32 symbol;
+ for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
+ int nbOccurences;
+ for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
+ int nbOccurrences;
+ for (nbOccurrences = 0; nbOccurrences < normalizedCounter[symbol]; nbOccurrences++) {
+ tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
+ position = (position + step) & tableMask;
+ while (position > highThreshold)
@ -9944,7 +9944,7 @@ index 0000000..2143da2
+ HUF_repeat_none, /**< Cannot use the previous table */
+ HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
+ 4}X_repeat */
+ HUF_repeat_valid /**< Can use the previous table and it is asumed to be valid */
+ HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */
+} HUF_repeat;
+/** HUF_compress4X_repeat() :
+* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.

4
contrib/linux-kernel/0006-squashfs-tools-Add-zstd-support.patch
View File

@ -11,7 +11,7 @@ Signed-off-by: Nick Terrell <terrelln@fb.com>
---
v4 -> v5:
- Fix patch documentation to reflect that Sean Purcell is the author
- Don't strip trailing whitespace of unreleated code
- Don't strip trailing whitespace of unrelated code
- Make zstd_display_options() static
v5 -> v6:
@ -224,7 +224,7 @@ index 0000000..dcab75a
+ * set the default options, this is to ensure any user supplied
+ * -X options on the appending mksquashfs command line are over-ridden.
+ *
+ * This function returns 0 on sucessful extraction of options, and -1 on error.
+ * This function returns 0 on successful extraction of options, and -1 on error.
+ */
+static int zstd_extract_options(int block_size, void *buffer, int size)
+{

4
contrib/linux-kernel/lib/zstd/compress.c
View File

@ -2436,14 +2436,14 @@ static size_t ZSTD_writeFrameHeader(void *dst, size_t dstCapacity, ZSTD_paramete
BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
U32 const fcsCode =
params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
size_t pos;
if (dstCapacity < ZSTD_frameHeaderSize_max)
return ERROR(dstSize_tooSmall);
ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
op[4] = frameHeaderDecriptionByte;
op[4] = frameHeaderDescriptionByte;
pos = 5;
if (!singleSegment)
op[pos++] = windowLogByte;

4
contrib/linux-kernel/lib/zstd/fse_compress.c
View File

@ -141,8 +141,8 @@ size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsi
U32 position = 0;
U32 symbol;
for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
int nbOccurences;
for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
int nbOccurrences;
for (nbOccurrences = 0; nbOccurrences < normalizedCounter[symbol]; nbOccurrences++) {
tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
position = (position + step) & tableMask;
while (position > highThreshold)

2
contrib/linux-kernel/lib/zstd/huf.h
View File

@ -134,7 +134,7 @@ typedef enum {
HUF_repeat_none, /**< Cannot use the previous table */
HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
4}X_repeat */
HUF_repeat_valid /**< Can use the previous table and it is asumed to be valid */
HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */
} HUF_repeat;
/** HUF_compress4X_repeat() :
* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.

6
contrib/linux-kernel/test/include/linux/compiler.h
View File

@ -1,5 +1,5 @@
#ifndef LINUX_COMIPLER_H_
#define LINUX_COMIPLER_H_
#ifndef LINUX_COMPILER_H_
#define LINUX_COMPILER_H_
#ifndef __always_inline
# define __always_inline inline
@ -9,4 +9,4 @@
# define noinline __attribute__((__noinline__))
#endif
#endif // LINUX_COMIPLER_H_
#endif // LINUX_COMPILER_H_

6
contrib/pzstd/Makefile
View File

@ -190,13 +190,15 @@ $(ZSTDDIR)/libzstd.a: $(ZSTD_FILES)
CFLAGS="$(ALL_CFLAGS)" LDFLAGS="$(ALL_LDFLAGS)" $(MAKE) -C $(ZSTDDIR) libzstd.a
# Rules to build the tests
test/RoundTripTest$(EXT): test/RoundTripTest.o $(PROGDIR)/datagen.o Options.o \
test/RoundTripTest$(EXT): test/RoundTripTest.o $(PROGDIR)/datagen.o \
$(PROGDIR)/util.o Options.o \
Pzstd.o SkippableFrame.o $(ZSTDDIR)/libzstd.a
$(LD_COMMAND)
test/%Test$(EXT): PZSTD_LDFLAGS += $(GTEST_LIB)
test/%Test$(EXT): LIBS += -lgtest -lgtest_main
test/%Test$(EXT): test/%Test.o $(PROGDIR)/datagen.o Options.o Pzstd.o \
test/%Test$(EXT): test/%Test.o $(PROGDIR)/datagen.o \
$(PROGDIR)/util.o Options.o Pzstd.o \
SkippableFrame.o $(ZSTDDIR)/libzstd.a
$(LD_COMMAND)

2
contrib/pzstd/Pzstd.cpp
View File

@ -55,7 +55,7 @@ static std::uint64_t handleOneInput(const Options &options,
SharedState& state) {
auto inputSize = fileSizeOrZero(inputFile);
// WorkQueue outlives ThreadPool so in the case of error we are certain
// we don't accidently try to call push() on it after it is destroyed
// we don't accidentally try to call push() on it after it is destroyed
WorkQueue<std::shared_ptr<BufferWorkQueue>> outs{options.numThreads + 1};
std::uint64_t bytesRead;
std::uint64_t bytesWritten;

2
contrib/pzstd/utils/Range.h
View File

@ -9,7 +9,7 @@
/**
* A subset of `folly/Range.h`.
* All code copied verbatiam modulo formatting
* All code copied verbatim modulo formatting
*/
#pragma once

2
contrib/pzstd/utils/ResourcePool.h
View File

@ -54,7 +54,7 @@ class ResourcePool {
/**
* @returns A unique pointer to a resource. The resource is null iff
* there are no avaiable resources and `factory()` returns null.
* there are no available resources and `factory()` returns null.
*/
UniquePtr get() {
std::lock_guard<std::mutex> lock(mutex_);

4
doc/README.md
View File

@ -12,8 +12,8 @@ __`zstd_compression_format.md`__ : This document defines the Zstandard compressi
Compliant decoders must adhere to this document,
and compliant encoders must generate data that follows it.
Should you look for ressources to develop your own port of Zstandard algorithm,
you may find the following ressources useful :
Should you look for resources to develop your own port of Zstandard algorithm,
you may find the following resources useful :
__`educational_decoder`__ : This directory contains an implementation of a Zstandard decoder,
compliant with the Zstandard compression format.

2
doc/educational_decoder/Makefile
View File

@ -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)

2
doc/educational_decoder/zstd_decompress.c
View File

@ -358,7 +358,7 @@ static u32 copy_literals(const size_t seq, istream_t *litstream,
ostream_t *const out);
// Given an offset code from a sequence command (either an actual offset value
// or an index for previous offset), computes the correct offset and udpates
// or an index for previous offset), computes the correct offset and updates
// the offset history
static size_t compute_offset(sequence_command_t seq, u64 *const offset_hist);

935
doc/zstd_manual.html
View File

File diff suppressed because it is too large Load Diff

16
examples/Makefile
View File

@ -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)

43
examples/utils.h → examples/common.h
View File

@ -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.
@ -56,7 +83,7 @@ static size_t fsize_orDie(const char *filename)
* 2. if off_t -> size_t type conversion results in discrepancy,
* the file size is too large for type size_t.
*/
if ((fileSize < 0) || (fileSize != (off_t)size)) {
if ((fileSize < 0) || (fileSize != (off_t)size)) {
fprintf(stderr, "%s : filesize too large \n", filename);
exit(ERROR_largeFile);
}
@ -150,10 +177,10 @@ static void* malloc_orDie(size_t size)
* @return If successful this function will load file into buffer and
* return file size, otherwise it will printout an error to stderr and exit.
*/
static size_t loadFile_orDie(const char* fileName, void* buffer, int bufferSize)
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);

26
examples/dictionary_compression.c
View File

@ -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);

55
examples/dictionary_decompression.c
View File

@ -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);

35
examples/multiple_simple_compression.c
View File

@ -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;
@ -28,7 +26,7 @@ typedef struct {
* allocate memory for buffers big enough to compress all files
* as well as memory for output file name (ofn)
*/
static resources createResources_orDie(int argc, const char** argv, char **ofn, int* ofnBufferLen)
static resources createResources_orDie(int argc, const char** argv, char **ofn, size_t* ofnBufferLen)
{
size_t maxFilenameLength=0;
size_t maxFileSize = 0;
@ -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)
@ -94,21 +93,21 @@ int main(int argc, const char** argv)
/* memory allocation for outFilename and resources */
char* outFilename;
int outFilenameBufferLen;
resources const ress = createResources_orDie(argc, argv, &outFilename, &outFilenameBufferLen);
size_t outFilenameBufferLen;
resources const ress = createResources_orDie(argc, argv, &outFilename, &outFilenameBufferLen);
/* compress files with shared context, input and output buffers */
int argNb;
for (argNb = 1; argNb < argc; argNb++) {
const char* const inFilename = argv[argNb];
int inFilenameLen = strlen(inFilename);
assert(inFilenameLen + 5 <= outFilenameBufferLen);
size_t const inFilenameLen = strlen(inFilename);
CHECK(inFilenameLen + 5 <= outFilenameBufferLen, "File name too long!");
memcpy(outFilename, inFilename, inFilenameLen);
memcpy(outFilename+inFilenameLen, ".zst", 5);
compressFile_orDie(ress, inFilename, outFilename);
}
/* free momery */
/* free memory */
freeResources(ress,outFilename);
printf("compressed %i files \n", argc-1);

73
examples/multiple_streaming_compression.c
View File

@ -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);

19
examples/simple_compression.c
View File

@ -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);

39
examples/simple_decompression.c
View File

@ -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);

89
examples/streaming_compression.c
View File

@ -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);
}

44
examples/streaming_decompression.c
View File

@ -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);

130
examples/streaming_memory_usage.c
View File

@ -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
View File

@ -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

6
lib/README.md
View File

@ -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

2
lib/common/compiler.h
View File

@ -40,7 +40,7 @@
/**
* FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
* parameters. They must be inlined for the compiler to elimininate the constant
* parameters. They must be inlined for the compiler to eliminate the constant
* branches.
*/
#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR

2
lib/common/fse.h
View File

@ -358,7 +358,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
typedef enum {
FSE_repeat_none, /**< Cannot use the previous table */
FSE_repeat_check, /**< Can use the previous table but it must be checked */
FSE_repeat_valid /**< Can use the previous table and it is asumed to be valid */
FSE_repeat_valid /**< Can use the previous table and it is assumed to be valid */
} FSE_repeat;
/* *****************************************

4
lib/common/threading.c
View File

@ -14,8 +14,8 @@
* This file will hold wrapper for systems, which do not support pthreads
*/
/* create fake symbol to avoid empty trnaslation unit warning */
int g_ZSTD_threading_useles_symbol;
/* create fake symbol to avoid empty translation unit warning */
int g_ZSTD_threading_useless_symbol;
#if defined(ZSTD_MULTITHREAD) && defined(_WIN32)

4
lib/common/xxhash.c
View File

@ -66,10 +66,10 @@
/* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */
/*!XXH_FORCE_NATIVE_FORMAT :
* By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
* By default, xxHash library provides endian-independent Hash values, based on little-endian convention.
* Results are therefore identical for little-endian and big-endian CPU.
* This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
* Should endian-independance be of no importance for your application, you may set the #define below to 1,
* Should endian-independence be of no importance for your application, you may set the #define below to 1,
* to improve speed for Big-endian CPU.
* This option has no impact on Little_Endian CPU.
*/

57
lib/common/zstd_internal.h
View File

@ -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) */

4
lib/compress/fse_compress.c
View File

@ -129,9 +129,9 @@ size_t FSE_buildCTable_wksp(FSE_CTable* ct,
{ U32 position = 0;
U32 symbol;
for (symbol=0; symbol<=maxSymbolValue; symbol++) {
int nbOccurences;
int nbOccurrences;
int const freq = normalizedCounter[symbol];
for (nbOccurences=0; nbOccurences<freq; nbOccurences++) {
for (nbOccurrences=0; nbOccurrences<freq; nbOccurrences++) {
tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
position = (position + step) & tableMask;
while (position > highThreshold)

719
lib/compress/zstd_compress.c
View File

File diff suppressed because it is too large Load Diff

25
lib/compress/zstd_compress_internal.h
View File

@ -36,9 +36,9 @@ extern "C" {
#define ZSTD_DUBT_UNSORTED_MARK 1 /* For btlazy2 strategy, index 1 now means "unsorted".
It could be confused for a real successor at index "1", if sorted as larger than its predecessor.
It's not a big deal though : candidate will just be sorted again.
Additionnally, candidate position 1 will be lost.
Additionally, candidate position 1 will be lost.
But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss.
The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be misdhandled after table re-use with a different strategy
The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy
Constant required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */
@ -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);
@ -839,7 +842,7 @@ size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx,
/* ZSTD_writeLastEmptyBlock() :
* output an empty Block with end-of-frame mark to complete a frame
* @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
* or an error code if `dstCapcity` is too small (<ZSTD_blockHeaderSize)
* or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
*/
size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity);

329
lib/compress/zstd_fast.c
View File

@ -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);
}
}

2
lib/compress/zstd_lazy.h
View File

@ -19,7 +19,7 @@ extern "C" {
U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);
void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). pre-emptively increase value of ZSTD_DUBT_UNSORTED_MARK */
void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */
size_t ZSTD_compressBlock_btlazy2(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],

2
lib/compress/zstd_ldm.c
View File

@ -429,7 +429,7 @@ size_t ZSTD_ldm_generateSequences(
*/
assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize);
/* The input could be very large (in zstdmt), so it must be broken up into
* chunks to enforce the maximmum distance and handle overflow correction.
* chunks to enforce the maximum distance and handle overflow correction.
*/
assert(sequences->pos <= sequences->size);
assert(sequences->size <= sequences->capacity);

38
lib/compress/zstd_opt.c
View File

@ -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;
@ -870,7 +885,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
/* large match -> immediate encoding */
{ U32 const maxML = matches[nbMatches-1].len;
U32 const maxOffset = matches[nbMatches-1].off;
DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new serie",
DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series",
nbMatches, maxML, maxOffset, (U32)(ip-prefixStart));
if (maxML > sufficient_len) {
@ -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);
@ -1117,7 +1133,7 @@ MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
/* ZSTD_initStats_ultra():
* make a first compression pass, just to seed stats with more accurate starting values.
* only works on first block, with no dictionary and no ldm.
* this function cannot error, hence its constract must be respected.
* this function cannot error, hence its contract must be respected.
*/
static void
ZSTD_initStats_ultra(ZSTD_matchState_t* ms,

90
lib/compress/zstdmt_compress.c
View File

@ -22,6 +22,7 @@
/* ====== Dependencies ====== */
#include <string.h> /* memcpy, memset */
#include <limits.h> /* INT_MAX, UINT_MAX */
#include "mem.h" /* MEM_STATIC */
#include "pool.h" /* threadpool */
#include "threading.h" /* mutex */
#include "zstd_compress_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
@ -456,7 +457,7 @@ typedef struct {
* Must be acquired after the main mutex when acquiring both.
*/
ZSTD_pthread_mutex_t ldmWindowMutex;
ZSTD_pthread_cond_t ldmWindowCond; /* Signaled when ldmWindow is udpated */
ZSTD_pthread_cond_t ldmWindowCond; /* Signaled when ldmWindow is updated */
ZSTD_window_t ldmWindow; /* A thread-safe copy of ldmState.window */
} serialState_t;
@ -647,7 +648,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
buffer_t dstBuff = job->dstBuff;
size_t lastCBlockSize = 0;
/* ressources */
/* resources */
if (cctx==NULL) JOB_ERROR(ERROR(memory_allocation));
if (dstBuff.start == NULL) { /* streaming job : doesn't provide a dstBuffer */
dstBuff = ZSTDMT_getBuffer(job->bufPool);
@ -672,7 +673,7 @@ 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,
@ -864,14 +865,10 @@ 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)
MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, ZSTD_customMem cMem)
{
ZSTDMT_CCtx* mtctx;
U32 nbJobs = nbWorkers + 2;
@ -906,6 +903,17 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
return mtctx;
}
ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
{
#ifdef ZSTD_MULTITHREAD
return ZSTDMT_createCCtx_advanced_internal(nbWorkers, cMem);
#else
(void)nbWorkers;
(void)cMem;
return NULL;
#endif
}
ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers)
{
return ZSTDMT_createCCtx_advanced(nbWorkers, ZSTD_defaultCMem);
@ -986,26 +994,13 @@ 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 +1016,29 @@ 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 +1048,7 @@ 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 +1255,7 @@ 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 +1388,7 @@ 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;
@ -1547,7 +1539,7 @@ size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel) {
/* ZSTDMT_writeLastEmptyBlock()
* Write a single empty block with an end-of-frame to finish a frame.
* Job must be created from streaming variant.
* This function is always successfull if expected conditions are fulfilled.
* This function is always successful if expected conditions are fulfilled.
*/
static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job)
{
@ -1987,7 +1979,7 @@ 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 +2043,7 @@ 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 +2057,7 @@ 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 +2074,7 @@ 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 */

69
lib/compress/zstdmt_compress.h
View File

@ -17,10 +17,25 @@
/* 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 */
* Now, it's recommended to use ZSTD_compress2 and ZSTD_compressStream2()
* instead.
*
* 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.
*
* This API requires ZSTD_MULTITHREAD to be defined during compilation,
* otherwise ZSTDMT_createCCtx*() will fail.
*/
#ifdef ZSTD_LEGACY_MULTITHREADED_API
# define ZSTDMT_API ZSTDLIB_API
#else
# define ZSTDMT_API
#endif
/* === Dependencies === */
#include <stddef.h> /* size_t */
@ -40,17 +55,19 @@
/* === 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,
/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
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 +76,31 @@ 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 */
@ -92,7 +109,7 @@ ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
* List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
typedef enum {
ZSTDMT_p_jobSize, /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */
ZSTDMT_p_overlapLog, /* Each job may reload a part of previous job to enhance compressionr ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
ZSTDMT_p_overlapLog, /* Each job may reload a part of previous job to enhance compression ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
ZSTDMT_p_rsyncable /* Enables rsyncable mode. */
} ZSTDMT_parameter;
@ -101,12 +118,12 @@ 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 +133,7 @@ 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);

8
lib/decompress/zstd_ddict.c
View File

@ -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;
}

473
lib/decompress/zstd_decompress.c
View File

@ -106,6 +106,7 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
dctx->ddictLocal = NULL;
dctx->dictEnd = NULL;
dctx->ddictIsCold = 0;
dctx->dictUses = ZSTD_dont_use;
dctx->inBuff = NULL;
dctx->inBuffSize = 0;
dctx->outBuffSize = 0;
@ -147,13 +148,20 @@ ZSTD_DCtx* ZSTD_createDCtx(void)
return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
}
static void ZSTD_clearDict(ZSTD_DCtx* dctx)
{
ZSTD_freeDDict(dctx->ddictLocal);
dctx->ddictLocal = NULL;
dctx->ddict = NULL;
dctx->dictUses = ZSTD_dont_use;
}
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;
ZSTD_clearDict(dctx);
ZSTD_free(dctx->inBuff, cMem);
dctx->inBuff = NULL;
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
@ -203,7 +211,7 @@ 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 +246,7 @@ 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 +259,7 @@ 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 +277,13 @@ 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 +355,11 @@ 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 +434,89 @@ 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 +525,34 @@ 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 +585,9 @@ 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 +598,9 @@ 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 +623,16 @@ 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 +645,7 @@ 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 +660,7 @@ 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 +673,15 @@ 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 +716,8 @@ 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 +740,7 @@ 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 +749,29 @@ 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 +780,7 @@ 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;
}
@ -730,9 +794,26 @@ size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
}
static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx)
{
switch (dctx->dictUses) {
default:
assert(0 /* Impossible */);
/* fall-through */
case ZSTD_dont_use:
ZSTD_clearDict(dctx);
return NULL;
case ZSTD_use_indefinitely:
return dctx->ddict;
case ZSTD_use_once:
dctx->dictUses = ZSTD_dont_use;
return dctx->ddict;
}
}
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, ZSTD_getDDict(dctx));
}
@ -741,7 +822,7 @@ 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 +872,7 @@ 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 +897,7 @@ 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 +947,7 @@ 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 +956,10 @@ 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 +980,7 @@ 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 +1001,7 @@ 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 +1025,7 @@ 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 +1044,16 @@ 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 +1064,9 @@ 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 +1077,9 @@ 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 +1087,13 @@ 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 +1111,7 @@ 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 +1145,11 @@ 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 +1168,7 @@ 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);
}
@ -1104,7 +1187,7 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
}
/*! ZSTD_getDictID_fromFrame() :
* Provides the dictID required to decompresse frame stored within `src`.
* Provides the dictID required to decompress frame stored within `src`.
* If @return == 0, the dictID could not be decoded.
* This could for one of the following reasons :
* - The frame does not require a dictionary (most common case).
@ -1176,15 +1259,14 @@ 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);
ZSTD_freeDDict(dctx->ddictLocal);
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
ZSTD_clearDict(dctx);
if (dict && dictSize >= 8) {
dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem);
if (dctx->ddictLocal == NULL) return ERROR(memory_allocation);
} else {
dctx->ddictLocal = NULL;
RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation);
dctx->ddict = dctx->ddictLocal;
dctx->dictUses = ZSTD_use_indefinitely;
}
dctx->ddict = dctx->ddictLocal;
return 0;
}
@ -1200,7 +1282,9 @@ size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSi
size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
{
return ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType);
FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType));
dctx->dictUses = ZSTD_use_once;
return 0;
}
size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize)
@ -1215,9 +1299,8 @@ size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSiz
size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
{
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_reset(zds, ZSTD_reset_session_only) );
FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
return ZSTD_FRAMEHEADERSIZE_PREFIX;
}
@ -1225,7 +1308,7 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di
size_t ZSTD_initDStream(ZSTD_DStream* zds)
{
DEBUGLOG(4, "ZSTD_initDStream");
return ZSTD_initDStream_usingDict(zds, NULL, 0);
return ZSTD_initDStream_usingDDict(zds, NULL);
}
/* ZSTD_initDStream_usingDDict() :
@ -1233,9 +1316,9 @@ size_t ZSTD_initDStream(ZSTD_DStream* zds)
* this function cannot fail */
size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
{
size_t const initResult = ZSTD_initDStream(dctx);
dctx->ddict = ddict;
return initResult;
FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) );
FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) );
return ZSTD_FRAMEHEADERSIZE_PREFIX;
}
/* ZSTD_resetDStream() :
@ -1243,19 +1326,19 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
* this function cannot fail */
size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
{
DEBUGLOG(4, "ZSTD_resetDStream");
dctx->streamStage = zdss_loadHeader;
dctx->lhSize = dctx->inPos = dctx->outStart = dctx->outEnd = 0;
dctx->legacyVersion = 0;
dctx->hostageByte = 0;
FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only));
return ZSTD_FRAMEHEADERSIZE_PREFIX;
}
size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
{
if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
dctx->ddict = ddict;
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
ZSTD_clearDict(dctx);
if (ddict) {
dctx->ddict = ddict;
dctx->dictUses = ZSTD_use_indefinitely;
}
return 0;
}
@ -1267,9 +1350,9 @@ 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 +1394,15 @@ 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;
@ -1329,19 +1412,20 @@ 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)
{
if ( (reset == ZSTD_reset_session_only)
|| (reset == ZSTD_reset_session_and_parameters) ) {
(void)ZSTD_initDStream(dctx);
dctx->streamStage = zdss_init;
dctx->noForwardProgress = 0;
}
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);
ZSTD_clearDict(dctx);
dctx->format = ZSTD_f_zstd1;
dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
}
@ -1360,7 +1444,8 @@ 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 +1463,9 @@ 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 +1491,16 @@ 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) {
@ -1423,15 +1508,18 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
{
case zdss_init :
DEBUGLOG(5, "stage zdss_init => transparent reset ");
ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
zds->streamStage = zdss_loadHeader;
zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
zds->legacyVersion = 0;
zds->hostageByte = 0;
/* fall-through */
case zdss_loadHeader :
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;
@ -1443,12 +1531,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
if (legacyVersion) {
const void* const dict = zds->ddict ? ZSTD_DDict_dictContent(zds->ddict) : NULL;
size_t const dictSize = zds->ddict ? ZSTD_DDict_dictSize(zds->ddict) : 0;
ZSTD_DDict const* const ddict = ZSTD_getDDict(zds);
const void* const dict = ddict ? ZSTD_DDict_dictContent(ddict) : NULL;
size_t const dictSize = ddict ? ZSTD_DDict_dictSize(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;
@ -1482,7 +1571,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
if (cSize <= (size_t)(iend-istart)) {
/* shortcut : using single-pass mode */
size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, ZSTD_getDDict(zds));
if (ZSTD_isError(decompressedSize)) return decompressedSize;
DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()")
ip = istart + cSize;
@ -1495,13 +1584,13 @@ 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, ZSTD_getDDict(zds)));
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 +1600,8 @@ 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 +1615,15 @@ 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 +1665,9 @@ 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 +1708,7 @@ 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 +1717,8 @@ 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 {

98
lib/decompress/zstd_decompress_block.c
View File

@ -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;
@ -801,7 +801,7 @@ ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD)
/* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum
* offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1)
* bits before reloading. This value is the maximum number of bytes we read
* after reloading when we are decoding long offets.
* after reloading when we are decoding long offsets.
*/
#define LONG_OFFSETS_MAX_EXTRA_BITS_32 \
(ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32 \
@ -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;
}
@ -1176,7 +1180,7 @@ ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize,
/* ZSTD_decompressSequencesLong() :
* decompression function triggered when a minimum share of offsets is considered "long",
* aka out of cache.
* note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes mearning "farther than memory cache distance".
* note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance".
* This function will try to mitigate main memory latency through the use of prefetching */
static size_t
ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx,
@ -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);

7
lib/decompress/zstd_decompress_internal.h
View File

@ -89,6 +89,12 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
typedef enum { zdss_init=0, zdss_loadHeader,
zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
typedef enum {
ZSTD_use_indefinitely = -1, /* Use the dictionary indefinitely */
ZSTD_dont_use = 0, /* Do not use the dictionary (if one exists free it) */
ZSTD_use_once = 1 /* Use the dictionary once and set to ZSTD_dont_use */
} ZSTD_dictUses_e;
struct ZSTD_DCtx_s
{
const ZSTD_seqSymbol* LLTptr;
@ -123,6 +129,7 @@ struct ZSTD_DCtx_s
const ZSTD_DDict* ddict; /* set by ZSTD_initDStream_usingDDict(), or ZSTD_DCtx_refDDict() */
U32 dictID;
int ddictIsCold; /* if == 1 : dictionary is "new" for working context, and presumed "cold" (not in cpu cache) */
ZSTD_dictUses_e dictUses;
/* streaming */
ZSTD_dStreamStage streamStage;

71
lib/dictBuilder/cover.c
View File

@ -391,7 +391,7 @@ static void COVER_group(COVER_ctx_t *ctx, const void *group,
*
* Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
*
* Once the dmer d is in the dictionay we set F(d) = 0.
* Once the dmer d is in the dictionary we set F(d) = 0.
*/
static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
COVER_map_t *activeDmers, U32 begin,
@ -435,7 +435,7 @@ static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer);
activeSegment.begin += 1;
*delDmerOcc -= 1;
/* If this is the last occurence of the dmer, subtract its score */
/* If this is the last occurrence of the dmer, subtract its score */
if (*delDmerOcc == 0) {
COVER_map_remove(activeDmers, delDmer);
activeSegment.score -= freqs[delDmer];
@ -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 */

29
lib/dictBuilder/cover.h
View File

@ -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 segment from each epoch.
*
* @param maxDictSize The maximum allowed dictionary 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
*/

38
lib/dictBuilder/fastcover.c
View File

@ -132,7 +132,7 @@ typedef struct {
*
* Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
*
* Once the dmer with hash value d is in the dictionay we set F(d) = 0.
* Once the dmer with hash value d is in the dictionary we set F(d) = 0.
*/
static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
U32 *freqs, U32 begin, U32 end,
@ -161,7 +161,7 @@ static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
/* Get hash value of current dmer */
const size_t idx = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, f, d);
/* Add frequency of this index to score if this is the first occurence of index in active segment */
/* Add frequency of this index to score if this is the first occurrence of index in active segment */
if (segmentFreqs[idx] == 0) {
activeSegment.score += freqs[idx];
}
@ -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 */

26
lib/dictBuilder/zdict.h
View File

@ -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.

5
lib/dll/example/build_package.bat
View File

@ -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

87
lib/dll/libzstd.def
View File

@ -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

54
lib/legacy/zstd_legacy.h
View File

@ -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)

39
lib/legacy/zstd_v01.c
View File

@ -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;
@ -1757,7 +1759,7 @@ static size_t ZSTD_execSequence(BYTE* op,
BYTE* const base, BYTE* const oend)
{
static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */
const BYTE* const ostart = op;
const size_t litLength = sequence.litLength;
BYTE* const endMatch = op + litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */
@ -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;
}
/*******************************

19
lib/legacy/zstd_v01.h
View File

@ -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

43
lib/legacy/zstd_v02.c
View File

@ -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;
@ -3096,7 +3098,7 @@ static size_t ZSTD_execSequence(BYTE* op,
BYTE* const base, BYTE* const oend)
{
static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */
const BYTE* const ostart = op;
BYTE* const oLitEnd = op + sequence.litLength;
BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */
@ -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();

19
lib/legacy/zstd_v02.h
View File

@ -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

44
lib/legacy/zstd_v03.c
View File

@ -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;
@ -2737,7 +2739,7 @@ static size_t ZSTD_execSequence(BYTE* op,
BYTE* const base, BYTE* const oend)
{
static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */
static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */
const BYTE* const ostart = op;
BYTE* const oLitEnd = op + sequence.litLength;
BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */
@ -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();

19
lib/legacy/zstd_v03.h
View File

@ -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

44
lib/legacy/zstd_v04.c
View File

@ -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;
@ -2860,7 +2862,7 @@ static size_t ZSTD_execSequence(BYTE* op,
const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd)
{
static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */
BYTE* const oLitEnd = op + sequence.litLength;
const size_t sequenceLength = sequence.litLength + sequence.matchLength;
BYTE* const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
@ -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)

19
lib/legacy/zstd_v04.h
View File

@ -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

39
lib/legacy/zstd_v05.c
View File

@ -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;
@ -3217,7 +3219,7 @@ static size_t ZSTDv05_execSequence(BYTE* op,
const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd)
{
static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */
BYTE* const oLitEnd = op + sequence.litLength;
const size_t sequenceLength = sequence.litLength + sequence.matchLength;
BYTE* const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
@ -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;
}
/* ******************************

19
lib/legacy/zstd_v05.h
View File

@ -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

44
lib/legacy/zstd_v06.c
View File

@ -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 };
@ -3406,7 +3408,7 @@ static size_t ZSTDv06_execSequence(BYTE* op,
if (sequence.offset < 8) {
/* close range match, overlap */
static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */
int const sub2 = dec64table[sequence.offset];
op[0] = match[0];
op[1] = match[1];
@ -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;
}
/*_******************************

15
lib/legacy/zstd_v06.h
View File

@ -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

49
lib/legacy/zstd_v07.c
View File

@ -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 };
@ -3631,7 +3633,7 @@ size_t ZSTDv07_execSequence(BYTE* op,
if (sequence.offset < 8) {
/* close range match, overlap */
static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */
static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */
int const sub2 = dec64table[sequence.offset];
op[0] = match[0];
op[1] = match[1];
@ -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;
}
/*_******************************

15
lib/legacy/zstd_v07.h
View File

@ -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 */

1085
lib/zstd.h
View File

File diff suppressed because it is too large Load Diff

20
programs/Makefile
View File

@ -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)
@ -165,7 +165,7 @@ $(ZSTDDECOMP_O): CFLAGS += $(ALIGN_LOOP)
zstd : CPPFLAGS += $(THREAD_CPP) $(ZLIBCPP) $(LZMACPP) $(LZ4CPP)
zstd : LDFLAGS += $(THREAD_LD) $(ZLIBLD) $(LZMALD) $(LZ4LD) $(DEBUGFLAGS_LD)
zstd : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT)
zstd : $(ZSTDLIB_FILES) zstdcli.o util.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o
zstd : $(ZSTDLIB_FILES) zstdcli.o util.o timefn.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o
@echo "$(THREAD_MSG)"
@echo "$(ZLIB_MSG)"
@echo "$(LZMA_MSG)"
@ -183,13 +183,13 @@ zstd-release: zstd
zstd32 : CPPFLAGS += $(THREAD_CPP)
zstd32 : LDFLAGS += $(THREAD_LD)
zstd32 : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT)
zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c
zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c timefn.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c
ifneq (,$(filter Windows%,$(OS)))
windres/generate_res.bat
endif
$(CC) -m32 $(FLAGS) $^ $(RES32_FILE) -o $@$(EXT)
zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o datagen.o dibio.o
zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o timefn.o datagen.o dibio.o
$(CC) $(FLAGS) $^ -o $@$(EXT) $(LDFLAGS)
zstd-nomt : THREAD_CPP :=
@ -222,13 +222,13 @@ zstd-pgo :
# minimal target, with only zstd compression and decompression. no bench. no legacy.
zstd-small: CFLAGS = -Os -s
zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c fileio.c
zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c timefn.c fileio.c
$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT $^ -o $@$(EXT)
zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c fileio.c
zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c timefn.c fileio.c
$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NOCOMPRESS $^ -o $@$(EXT)
zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c fileio.c
zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c timefn.c fileio.c
$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NODECOMPRESS $^ -o $@$(EXT)
zstdmt: zstd
@ -265,9 +265,9 @@ man: zstd.1 zstdgrep.1 zstdless.1
.PHONY: clean-man
clean-man:
rm zstd.1
rm zstdgrep.1
rm zstdless.1
$(RM) zstd.1
$(RM) zstdgrep.1
$(RM) zstdless.1
.PHONY: preview-man
preview-man: clean-man man

87
programs/benchfn.c
View File

@ -13,25 +13,20 @@
/* *************************************
* Includes
***************************************/
#include "platform.h" /* Large Files support */
#include "util.h" /* UTIL_getFileSize, UTIL_sleep */
#include <stdlib.h> /* malloc, free */
#include <string.h> /* memset */
#include <stdio.h> /* fprintf, fopen */
#undef NDEBUG /* assert must not be disabled */
#include <assert.h> /* assert */
#include "mem.h"
#include "timefn.h" /* UTIL_time_t, UTIL_getTime */
#include "benchfn.h"
/* *************************************
* Constants
***************************************/
#define TIMELOOP_MICROSEC (1*1000000ULL) /* 1 second */
#define TIMELOOP_MICROSEC SEC_TO_MICRO /* 1 second */
#define TIMELOOP_NANOSEC (1*1000000000ULL) /* 1 second */
#define ACTIVEPERIOD_MICROSEC (70*TIMELOOP_MICROSEC) /* 70 seconds */
#define COOLPERIOD_SEC 10
#define KB *(1 <<10)
#define MB *(1 <<20)
@ -39,14 +34,16 @@
/* *************************************
* Errors
* Debug errors
***************************************/
#ifndef DEBUG
# define DEBUG 0
#if defined(DEBUG) && (DEBUG >= 1)
# include <stdio.h> /* fprintf */
# define DISPLAY(...) fprintf(stderr, __VA_ARGS__)
# define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }
#else
# define DEBUGOUTPUT(...)
#endif
#define DISPLAY(...) fprintf(stderr, __VA_ARGS__)
#define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }
/* error without displaying */
#define RETURN_QUIET_ERROR(retValue, ...) { \
@ -116,15 +113,7 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
{ size_t i;
for(i = 0; i < p.blockCount; i++) {
memset(p.dstBuffers[i], 0xE5, p.dstCapacities[i]); /* warm up and erase result buffer */
}
#if 0
/* based on testing these seem to lower accuracy of multiple calls of 1 nbLoops vs 1 call of multiple nbLoops
* (Makes former slower)
*/
UTIL_sleepMilli(5); /* give processor time to other processes */
UTIL_waitForNextTick();
#endif
}
} }
/* benchmark */
{ UTIL_time_t const clockStart = UTIL_getTime();
@ -146,9 +135,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
} }
} /* for (loopNb = 0; loopNb < nbLoops; loopNb++) */
{ U64 const totalTime = UTIL_clockSpanNano(clockStart);
{ PTime const totalTime = UTIL_clockSpanNano(clockStart);
BMK_runTime_t rt;
rt.nanoSecPerRun = totalTime / nbLoops;
rt.nanoSecPerRun = (double)totalTime / nbLoops;
rt.sumOfReturn = dstSize;
return BMK_setValid_runTime(rt);
} }
@ -158,9 +147,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
/* ==== Benchmarking any function, providing intermediate results ==== */
struct BMK_timedFnState_s {
U64 timeSpent_ns;
U64 timeBudget_ns;
U64 runBudget_ns;
PTime timeSpent_ns;
PTime timeBudget_ns;
PTime runBudget_ns;
BMK_runTime_t fastestRun;
unsigned nbLoops;
UTIL_time_t coolTime;
@ -174,8 +163,20 @@ BMK_timedFnState_t* BMK_createTimedFnState(unsigned total_ms, unsigned run_ms)
return r;
}
void BMK_freeTimedFnState(BMK_timedFnState_t* state) {
free(state);
void BMK_freeTimedFnState(BMK_timedFnState_t* state) { free(state); }
BMK_timedFnState_t*
BMK_initStatic_timedFnState(void* buffer, size_t size, unsigned total_ms, unsigned run_ms)
{
typedef char check_size[ 2 * (sizeof(BMK_timedFnState_shell) >= sizeof(struct BMK_timedFnState_s)) - 1]; /* static assert : a compilation failure indicates that BMK_timedFnState_shell is not large enough */
typedef struct { check_size c; BMK_timedFnState_t tfs; } tfs_align; /* force tfs to be aligned at its next best position */
size_t const tfs_alignment = offsetof(tfs_align, tfs); /* provides the minimal alignment restriction for BMK_timedFnState_t */
BMK_timedFnState_t* const r = (BMK_timedFnState_t*)buffer;
if (buffer == NULL) return NULL;
if (size < sizeof(struct BMK_timedFnState_s)) return NULL;
if ((size_t)buffer % tfs_alignment) return NULL; /* buffer must be properly aligned */
BMK_resetTimedFnState(r, total_ms, run_ms);
return r;
}
void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms, unsigned run_ms)
@ -184,9 +185,9 @@ void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms,
if (!run_ms) run_ms = 1;
if (run_ms > total_ms) run_ms = total_ms;
timedFnState->timeSpent_ns = 0;
timedFnState->timeBudget_ns = (U64)total_ms * TIMELOOP_NANOSEC / 1000;
timedFnState->runBudget_ns = (U64)run_ms * TIMELOOP_NANOSEC / 1000;
timedFnState->fastestRun.nanoSecPerRun = (U64)(-1LL);
timedFnState->timeBudget_ns = (PTime)total_ms * TIMELOOP_NANOSEC / 1000;
timedFnState->runBudget_ns = (PTime)run_ms * TIMELOOP_NANOSEC / 1000;
timedFnState->fastestRun.nanoSecPerRun = (double)TIMELOOP_NANOSEC * 2000000000; /* hopefully large enough : must be larger than any potential measurement */
timedFnState->fastestRun.sumOfReturn = (size_t)(-1LL);
timedFnState->nbLoops = 1;
timedFnState->coolTime = UTIL_getTime();
@ -208,37 +209,27 @@ int BMK_isCompleted_TimedFn(const BMK_timedFnState_t* timedFnState)
BMK_runOutcome_t BMK_benchTimedFn(BMK_timedFnState_t* cont,
BMK_benchParams_t p)
{
U64 const runBudget_ns = cont->runBudget_ns;
U64 const runTimeMin_ns = runBudget_ns / 2;
PTime const runBudget_ns = cont->runBudget_ns;
PTime const runTimeMin_ns = runBudget_ns / 2;
int completed = 0;
BMK_runTime_t bestRunTime = cont->fastestRun;
while (!completed) {
BMK_runOutcome_t runResult;
/* Overheat protection */
if (UTIL_clockSpanMicro(cont->coolTime) > ACTIVEPERIOD_MICROSEC) {
DEBUGOUTPUT("\rcooling down ... \r");
UTIL_sleep(COOLPERIOD_SEC);
cont->coolTime = UTIL_getTime();
}
/* reinitialize capacity */
runResult = BMK_benchFunction(p, cont->nbLoops);
BMK_runOutcome_t const runResult = BMK_benchFunction(p, cont->nbLoops);
if(!BMK_isSuccessful_runOutcome(runResult)) { /* error : move out */
return runResult;
}
{ BMK_runTime_t const newRunTime = BMK_extract_runTime(runResult);
U64 const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops;
double const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops;
cont->timeSpent_ns += loopDuration_ns;
cont->timeSpent_ns += (unsigned long long)loopDuration_ns;
/* estimate nbLoops for next run to last approximately 1 second */
if (loopDuration_ns > (runBudget_ns / 50)) {
U64 const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun);
cont->nbLoops = (U32)(runBudget_ns / fastestRun_ns) + 1;
double const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun);
cont->nbLoops = (unsigned)(runBudget_ns / fastestRun_ns) + 1;
} else {
/* previous run was too short : blindly increase workload by x multiplier */
const unsigned multiplier = 10;

Some files were not shown because too many files have changed in this diff Show More