rpcs3_version: Bump to 0.0.9

vk: Properly use declared pitch when loading simple images
video-out: Allow applications to successfully change display resolution
2026-10-12 02:09:17 +00:00 · 2020-03-01 00:17:15 +03:00 · 2020-03-01 00:16:52 +03:00 · 2020-03-01 00:16:52 +03:00 · 2020-03-01 00:16:02 +03:00 · 2020-03-01 00:16:02 +03:00
1288 changed files with 215453 additions and 197901 deletions
@@ -11,11 +11,11 @@ BreakConstructorInitializersBeforeComma: true
 BreakBeforeBinaryOperators: false
 BreakBeforeTernaryOperators: false
 AlwaysBreakTemplateDeclarations: true
-AllowShortIfStatementsOnASingleLine: true
-AllowShortBlocksOnASingleLine: true
+AllowShortIfStatementsOnASingleLine: false
+AllowShortBlocksOnASingleLine: false
 AllowShortCaseLabelsOnASingleLine: true
 AllowShortFunctionsOnASingleLine: false
-AllowShortLoopsOnASingleLine: true
+AllowShortLoopsOnASingleLine: false
 Cpp11BracedListStyle: true
 IndentCaseLabels: false
 SortIncludes: false
@@ -29,5 +29,3 @@ BinPackParameters: true
 AlwaysBreakAfterReturnType: None
 KeepEmptyLinesAtTheStartOfBlocks: true
 IndentWrappedFunctionNames: false
-
-#SpaceAfterTemplateKeyword: false
@@ -1,7 +1,7 @@
 root = true

 [*.{h,cpp,hpp}]
-charset = utf-8
+charset = utf-8-bom
 indent_style = tab
 indent_size = 4
 trim_trailing_whitespace = true
@@ -0,0 +1,2 @@
+patreon: Nekotekina
+custom: https://rpcs3.net/alipay
@@ -1,24 +0,0 @@
-<!---
-
-THIS IS NOT A SUPPORT FORUM, FOR SUPPORT GO TO:
-https://forums.rpcs3.net
-or our discord:
-https://discord.me/RPCS3
-
-PLEASE READ THE GUIDELINES BEFORE OPENING AN ISSUE:
-https://github.com/RPCS3/rpcs3/blob/master/CONTRIBUTING.md
-
-====================================================
-
-When submitting an issue, please check the following:
-
- You have read the above.
- You have provided the version (commit hash) of RPCS3 you are using.
- You have provided sufficient detail for the issue to be reproduced.
- You have provided system specs.
- Please also provide:
-  - For crashes, a backtrace.
-  - For graphical issues, comparison screenshots with real hardware.
-
-Remember that the GitHub Issue Tracker is not the place to ask for support or to submit Game Compatibility reports. You must use our forums for that.
--->
@@ -0,0 +1,28 @@
+---
+name: Regression report
+about: If something worked before, but now it doesn't
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+<!---
+Please do not ask for help or report compatibility regressions here, use RPCS3 Discord server or forums instead.
+
+Please read Contributing guide under Helpful resources on the right. →
+--->
+
+## Quick summary
+Please describe what exactly has stopped working correctly
+
+## Details
+Please provide _exact_ build (or commit) information that introduced the regression you're reporting.
+Please see How to find the build that caused a regression in wiki: https://wiki.rpcs3.net/index.php?title=Help:Using_different_versions_of_RPCS3#How_to_find_the_build_that_caused_a_regression.3F
+You can find old builds here: https://rpcs3.net/compatibility?b
+
+Please remember to attach TWO logs: one for the build that exhibits regression, and one for the previous build that works as expected.
+
+If the regression caused a graphical issue, please provide RSX capture and a Renderdoc capture that demonstrate the issue.
+To create an RSX capture, enable Debugger view (View → Show Debugger) and use the RSX Capture button. Captues will be stored in RPCS3 folder → captures.
+To create Renderdoc capture, please refer to Renderdoc documentation https://renderdoc.org/docs/how/how_capture_frame.html
@@ -0,0 +1,26 @@
+---
+name: Bug report
+about: If something doesn't work correctly in RPCS3
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+<!---
+Please do not ask for help or general inquiry here, use RPCS3 Discord server instead.
+
+Please read Contributing guide under Helpful resources on the right. →
+--->
+
+## Quick summary
+Please summarize the issue here
+
+## Details
+Please provide as much detail as you can here, including
+- expected (real hw) and observed (emulator) behavior
+- full logs (not from UI)
+- back traces (for hard crashes)
+- screenshots, Renderdoc, and RSX captures (for visual issues)
+- your system configuration (OS, CPU, GPU, driver versions, etc)
+- anything else you deem to be important
@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Quickstart guide
+    url: https://rpcs3.net/quickstart
+    about: Everything you need to know to install and configure emulator, and add games
+  - name: Ask for help
+    url: https://discord.me/RPCS3
+    about: If you have some questions or need help, please use our Discord server instead of GitHub
+  - name: Report game compatibility
+    url: https://forums.rpcs3.net/thread-196671.html
+    about: Please use RPCS3 forums to submit or update game compatibility status
@@ -31,69 +31,80 @@
 *.wav

 /build
-/bin
 /lib
 /tmp
 /ipch
 /rpcs3/Debug
 /rpcs3/Release
 /llvm_build
+/3rdparty/llvm_build
 /Vulkan/Vulkan-build
 /Vulkan/glslang-build

+!/bin
+/bin/*
+
 # Themes
 !/bin/GuiConfigs/
 /bin/GuiConfigs/*.ini
-
-/bin/rpcs3.ini
-/bin/rpcs3.ipdb
-/bin/rpcs3.iobj
-/bin/FragmentProgram.txt
-/bin/VertexProgram.txt
-/bin/*.hlsl
-/bin/BreakPoints.dat
-/bin/textures
-/bin/*.lib
-/bin/*.exp
-rpcs3/git-version.h
+/bin/GuiConfigs/*.ini.*
+/bin/GuiConfigs/*.dat
+/bin/GuiConfigs/*.dat.*

 # Visual Studio Files
 .vs/*
+.vscode/*
+*.ipch
 *.vspx
 *.psess
 *.VC.*
 *.vcxproj.user
-
-# Copyrighted files
-/bin/data/
-/bin/dev_flash/data/font
-/bin/dev_flash/sys
-/bin/dev_flash/vsh
-
-# Ignore installed games except test homebrews
-!/bin/dev_hdd0/game/
-/bin/dev_hdd0/game/*
-!/bin/dev_hdd0/game/TEST12345/
-/bin/dev_hdd0/disc/*
+enc_temp_folder/*
+CMakeSettings.json

 # Ignore other system generated files
-bin/dev_hdd0/*.txt
 x64/*
 rpcs3/x64/*
-rpcs3-tests/x64/*
+rpcs3/git-version.h

 # cmake
 Makefile
 *CMakeFiles*
 CMakeCache.txt
 *cmake_install.cmake*
+CPackConfig.cmake
+CPackSourceConfig.cmake
+compile_commands.json

 # cotire
 rpcs3/cotire/*
 rpcs3/rpcs3_*_cotire.cmake
+rpcs3/Emu/rpcs3_emu_CXX_Release_cotire.cmake
+rpcs3/Emu/rpcs3_emu_CXX_cotire.cmake
+
+# kdevelop
+*.kdev4
+.kdev4/*

 # Qt
 moc_*.cpp
-qrc_resources.cpp
+qrc_*.cpp
 rpcs3_automoc.cpp
 ui_*.h
+rpcs3/rpcs3_autogen/*
+
+# QtCreator
+CMakeLists.txt.user
+
+# CLion
+/.idea/*
+/cmake-build-*/
+
+# macOS
+.DS_Store
+
+# 7zlib
+/3rdparty/7z/**/*.lib
+
+# yaml-cpp
+yaml-cpp.pc
@@ -1,6 +1,7 @@
 [submodule "rpcs3-ffmpeg"]
 	path = 3rdparty/ffmpeg
-	url = https://github.com/hrydgard/ppsspp-ffmpeg
+	url = https://github.com/RPCS3/ffmpeg-core
+	ignore = dirty
 [submodule "asmjit"]
 	path = asmjit
 	url = https://github.com/kobalicek/asmjit
@@ -8,37 +9,49 @@
 [submodule "llvm"]
 	path = llvm
 	url = https://github.com/RPCS3/llvm
-	branch = release_60
-[submodule "GSL"]
-	path = 3rdparty/GSL
-	url = https://github.com/Microsoft/GSL.git
-[submodule "libpng"]
-	path = 3rdparty/libpng
-	url = https://github.com/RPCS3/libpng
 	ignore = dirty
 [submodule "Vulkan/glslang"]
 	path = Vulkan/glslang
 	url = https://github.com/KhronosGroup/glslang.git
-[submodule "Vulkan/Vulkan-LoaderAndValidationLayers"]
-	path = Vulkan/Vulkan-LoaderAndValidationLayers
-	url = https://github.com/KhronosGroup/Vulkan-LoaderAndValidationLayers
-[submodule "Utilities/yaml-cpp"]
-	path = Utilities/yaml-cpp
-	url = https://github.com/RPCS3/yaml-cpp
+	ignore = dirty
 [submodule "3rdparty/cereal"]
 	path = 3rdparty/cereal
 	url = https://github.com/USCiLab/cereal.git
+	ignore = dirty
 [submodule "3rdparty/zlib"]
 	path = 3rdparty/zlib
 	url = https://github.com/madler/zlib
+	ignore = dirty
 [submodule "3rdparty/hidapi"]
 	path = 3rdparty/hidapi
 	url = https://github.com/RPCS3/hidapi
 	branch = master
 	ignore = dirty
-[submodule "3rdparty/Optional"]
-	path = 3rdparty/Optional
-	url = https://github.com/akrzemi1/Optional.git
 [submodule "3rdparty/pugixml"]
 	path = 3rdparty/pugixml
 	url = https://github.com/zeux/pugixml
+	ignore = dirty
+[submodule "3rdparty/xxHash"]
+	path = 3rdparty/xxHash
+	url = https://github.com/Cyan4973/xxHash
+	ignore = dirty
+[submodule "3rdparty/yaml-cpp"]
+	path = 3rdparty/yaml-cpp
+	url = https://github.com/jbeder/yaml-cpp.git
+	ignore = dirty
+[submodule "3rdparty/libpng"]
+	path = 3rdparty/libpng
+	url = https://github.com/glennrp/libpng.git
+	ignore = dirty
+[submodule "3rdparty/libusb"]
+	path = 3rdparty/libusb
+	url = https://github.com/libusb/libusb.git
+	ignore = dirty
+[submodule "3rdparty/FAudio"]
+	path = 3rdparty/FAudio
+	url = https://github.com/FNA-XNA/FAudio.git
+	ignore = dirty
+[submodule "3rdparty/span"]
+	path = 3rdparty/span
+	url = https://github.com/tcbrindle/span
+	ignore = dirty
@@ -1,124 +1,41 @@
 language: cpp
-sudo: required
-
-os:
-  - linux
-  #- osx
-
-# osx_image: xcode6.4
-
-compiler:
-  - clang
-  - gcc
-
-cache:
-  ccache: true
-  directories:
-    - $HOME/hombebrew_cache
-
-matrix:
-  exclude:
-    - os: osx
-      compiler: gcc
+jobs:
+    include:
+        - os: linux
+          dist: xenial
+          env:
+            - NAME="Linux build"
+            - COMPILER="gcc"
+            - DEPLOY_APPIMAGE="true"
+          services: docker
+          cache: ccache
+          compiler: gcc
+          install: "docker pull rpcs3/rpcs3-travis-xenial:1.2"
+          script: 'travis_wait docker run -v $(pwd):/rpcs3 -v "$HOME/.ccache":/root/.ccache --env-file .travis/travis.env rpcs3/rpcs3-travis-xenial:1.2 /bin/bash -ex /rpcs3/.travis/build-linux.bash'
+        - os: linux
+          dist: xenial
+          env:
+            - NAME="Linux build"
+            - COMPILER="clang"
+          services: docker
+          cache: ccache
+          compiler: clang
+          install: "docker pull rpcs3/rpcs3-travis-xenial:1.2"
+          script: 'travis_wait docker run -v $(pwd):/rpcs3 -v "$HOME/.ccache":/root/.ccache --env-file .travis/travis.env rpcs3/rpcs3-travis-xenial:1.2 /bin/bash -ex /rpcs3/.travis/build-linux.bash'
+        - os: osx
+          osx_image: xcode11.3
+          addons:
+            homebrew:
+                packages:
+                    - ccache
+                    - glew
+                    - ninja
+                    - qt
+          script: "/bin/bash -ex .travis/build-mac.bash"
+          cache: ccache
+    allow_failures:
+        - os: osx

 git:
  depth: false # Unshallow clone to obtain proper GIT_VERSION
  submodules: false
-
-before_install:
-  - if [ "$TRAVIS_OS_NAME" = "linux" ] && [ "$CXX" = "g++" ]; then
-      export CXX="g++-5" CC="gcc-5" CXXFLAGS="-Wno-format-security";
-    fi;
-  - if [ "$TRAVIS_OS_NAME" = "linux" ]; then
-      wget http://download.qt.io/official_releases/online_installers/qt-unified-linux-x64-online.run ;
-      chmod a+x ./qt-unified-linux-x64-online.run ;
-      export QT_QPA_PLATFORM=minimal ;
-      travis_wait 60 ./qt-unified-linux-x64-online.run --script qt-installer-noninteractive.qs --no-force-installations --verbose ;
-    fi;
-
-  # Install updated libglew-dev since the version provided by trusty is outdated
-  - if [ "$TRAVIS_OS_NAME" = "linux" ]; then
-      wget https://mirrors.kernel.org/ubuntu/pool/universe/g/glew/libglew-dev_2.0.0-5_amd64.deb;
-      wget https://mirrors.kernel.org/ubuntu/pool/universe/g/glew/libglew2.0_2.0.0-5_amd64.deb;
-      wget https://mirrors.kernel.org/ubuntu/pool/universe/v/vulkan/libvulkan1_1.0.61.1+dfsg1-1ubuntu1~16.04.1_amd64.deb;
-      wget https://mirrors.kernel.org/ubuntu/pool/universe/v/vulkan/libvulkan-dev_1.0.61.1+dfsg1-1ubuntu1~16.04.1_amd64.deb;
-      sudo dpkg -i libglew2.0_2.0.0-5_amd64.deb libglew-dev_2.0.0-5_amd64.deb libvulkan1_1.0.61.1+dfsg1-1ubuntu1~16.04.1_amd64.deb libvulkan-dev_1.0.61.1+dfsg1-1ubuntu1~16.04.1_amd64.deb;
-    else
-      brew update;
-      brew install ccache glew llvm40;
-    fi;
-
-before_script:
-  - git submodule update --init asmjit 3rdparty/ffmpeg 3rdparty/pugixml 3rdparty/GSL 3rdparty/libpng Utilities/yaml-cpp 3rdparty/cereal 3rdparty/hidapi 3rdparty/Optional Vulkan/glslang Vulkan/Vulkan-LoaderAndValidationLayers
-  - mkdir build
-  - cd build
-  - export CMAKE_PREFIX_PATH=~/Qt/5.10.0/gcc_64/lib/cmake
-  - export CXXFLAGS="$CXXFLAGS -DTRAVIS=true";
-  - if [ "$TRAVIS_PULL_REQUEST" = false ]; then
-      export CXXFLAGS="$CXXFLAGS -DBRANCH=$TRAVIS_REPO_SLUG/$TRAVIS_BRANCH";
-    else
-      export CXXFLAGS="$CXXFLAGS -DBRANCH=$TRAVIS_REPO_SLUG/$TRAVIS_BRANCH/#$TRAVIS_PULL_REQUEST";
-    fi;
-  - cmake .. -DCMAKE_INSTALL_PREFIX=/usr -G Ninja;
-  - ninja
-  - # AppImage generation
-  - if [ -n "$UPLOAD_URL" ] && [ "$TRAVIS_BRANCH" = "master" ] && [ "$CC" = "clang" ] && [ "$TRAVIS_PULL_REQUEST" = false ]; then
-      export LD_LIBRARY_PATH=~/Qt/5.10.0/gcc_64/lib;
-      DESTDIR=appdir ninja install ; find appdir/ ;
-      find ../bin ;
-      wget -c "https://github.com/probonopd/linuxdeployqt/releases/download/continuous/linuxdeployqt-continuous-x86_64.AppImage" ;
-      chmod a+x linuxdeployqt*.AppImage ;
-      export PATH=~/Qt/5.10.0/gcc_64/bin/:${PATH} ;
-      ./linuxdeployqt*.AppImage --appimage-extract ;
-      ./linuxdeployqt*.AppImage ./appdir/usr/share/applications/*.desktop -bundle-non-qt-libs ;
-      mkdir ./appdir/usr/plugins/xcbglintegrations/ ;
-      mkdir ./appdir/usr/plugins/imageformats/ ;
-      cp ~/Qt/5.10.0/gcc_64/lib/libQt5Svg.so.5 ./appdir/usr/lib/ ;
-      cp ~/Qt/5.10.0/gcc_64/plugins/xcbglintegrations/* ./appdir/usr/plugins/xcbglintegrations/ ;
-      cp ~/Qt/5.10.0/gcc_64/plugins/imageformats/* ./appdir/usr/plugins/imageformats/ ;
-      cp ~/Qt/5.10.0/gcc_64/plugins/platforms/* ./appdir/usr/plugins/platforms/ ;
-      rm ./appdir/usr/lib/libfreetype.so.6 ;
-      export PATH=${TRAVIS_BUILD_DIR}/build/squashfs-root/usr/bin/:${PATH} ;
-      ./squashfs-root/usr/bin/appimagetool ${TRAVIS_BUILD_DIR}/build/appdir ;
-      find ./appdir -executable -type f -exec ldd {} \; | grep " => /usr" | cut -d " " -f 2-3 | sort | uniq ;
-      curl ${UPLOAD_URL}${TRAVIS_COMMIT:0:7}-${TRAVIS_BUILD_NUMBER}_linux64 --upload-file ./RPCS3*.AppImage;
-   fi;
-
-script:
-  # Add a command to show all the variables. May be useful for debugging Travis.
-  #- echo "--Shell Export Lists START--" ; export -p; echo "--Shell Export Lists STOP--";
-  # And to ensure the versions of toolchain
-  - echo "--CXX version?"; "$CXX" --version; echo "--CXX version confirmed";
-
-addons:
-  apt:
-    sources:
-      - ubuntu-toolchain-r-test
-      - llvm-toolchain-trusty-4.0
-      - sourceline: 'ppa:jonathonf/binutils' # We need to update binutils to a newer version to link against the ffmpeg libs on.
-    packages:
-      - binutils
-      - cmake
-      - ninja-build
-      - libasound2-dev
-      - libopenal-dev
-      - freeglut3-dev
-      #- libglew-dev
-      #- libvulkan1
-      #- libvulkan-dev
-      - libc6-dev
-      - llvm-4.0
-      - llvm-4.0-dev
-      # Clang 5.0 is now bundled in travis, so we no longer need the ppa version.
-      #- clang-4.0
-      - libedit-dev
-      - g++-5
-      - gcc-5
-      - libstdc++-5-dev
-      - lib32stdc++6
-      - zlib1g-dev
-      # We need to install qt 5.10.0 manually because the version trusty provides is too old.
-      #- qtbase5-dev
-      - libudev-dev
-      - libevdev-dev
-      - libpulse-dev
@@ -0,0 +1,35 @@
+#!/bin/env bash -ex
+shopt -s nocasematch
+
+# Setup Qt variables
+export QT_BASE_DIR=/opt/qt${QTVERMIN}
+export PATH=$QT_BASE_DIR/bin:$PATH
+export LD_LIBRARY_PATH=$QT_BASE_DIR/lib/x86_64-linux-gnu:$QT_BASE_DIR/lib
+
+cd rpcs3
+
+git submodule update --quiet --init asmjit 3rdparty/ffmpeg 3rdparty/pugixml 3rdparty/span 3rdparty/libpng 3rdparty/cereal 3rdparty/hidapi 3rdparty/xxHash 3rdparty/yaml-cpp 3rdparty/libusb 3rdparty/FAudio Vulkan/glslang
+
+# Download pre-compiled llvm libs
+curl -sLO https://github.com/RPCS3/llvm/releases/download/continuous-linux-master/llvmlibs-linux.tar.gz
+mkdir llvmlibs
+tar -xzf ./llvmlibs-linux.tar.gz -C llvmlibs
+
+mkdir build ; cd build
+
+if [ $COMPILER = "gcc" ]; then
+	# These are set in the dockerfile
+	export CC=${GCC_BINARY}
+	export CXX=${GXX_BINARY}
+else
+	export CC=${CLANG_BINARY}
+	export CXX=${CLANGXX_BINARY}
+fi
+
+cmake .. -DCMAKE_INSTALL_PREFIX=/usr -DBUILD_LLVM_SUBMODULE=OFF -DUSE_COTIRE=OFF -DLLVM_DIR=llvmlibs/lib/cmake/llvm/ -DUSE_NATIVE_INSTRUCTIONS=OFF -G Ninja
+
+ninja; build_status=$?;
+
+cd ..
+# If it compiled succesfully let's deploy
+if [ $build_status -eq 0 ] && [ -n "$GITHUB_TOKEN" ] && [ "$TRAVIS_BRANCH" = "master" ] && [ "$TRAVIS_PULL_REQUEST" = false ]; then /bin/bash -ex .travis/deploy-linux.bash ; fi
@@ -0,0 +1,22 @@
+export CCACHE_SLOPPINESS=pch_defines,time_macros
+export CMAKE_PREFIX_PATH=/usr/local/opt/qt5/
+export PATH="/usr/local/opt/ccache/libexec:$PATH"
+
+# Setup vulkan and gfx-rs/portability
+curl -sLO https://github.com/gfx-rs/portability/releases/download/latest/gfx-portability-macos-latest.zip
+unzip -: gfx-portability-macos-latest.zip
+curl -sLO https://github.com/KhronosGroup/Vulkan-Headers/archive/sdk-1.1.106.0.zip
+unzip -: sdk-*.zip
+mkdir vulkan-sdk
+ln -s ${PWD}/Vulkan-Headers*/include vulkan-sdk/include
+mkdir vulkan-sdk/lib
+cp target/release/libportability.dylib vulkan-sdk/lib/libVulkan.dylib
+# Let macdeployqt locate and install Vulkan library
+install_name_tool -id ${PWD}/vulkan-sdk/lib/libVulkan.dylib vulkan-sdk/lib/libVulkan.dylib
+export VULKAN_SDK=${PWD}/vulkan-sdk
+
+git submodule update --quiet --init asmjit 3rdparty/ffmpeg 3rdparty/pugixml 3rdparty/span 3rdparty/libpng 3rdparty/cereal 3rdparty/hidapi 3rdparty/libusb 3rdparty/xxHash 3rdparty/yaml-cpp 3rdparty/FAudio Vulkan/glslang
+
+mkdir build; cd build
+cmake .. -DWITH_LLVM=OFF -DUSE_NATIVE_INSTRUCTIONS=OFF -G Ninja
+ninja
@@ -0,0 +1,54 @@
+#!/bin/env bash -ex
+shopt -s nocasematch
+cd build
+if [ "$DEPLOY_APPIMAGE" = "true" ]; then
+	DESTDIR=appdir ninja install
+	curl -sLO "https://github.com/probonopd/linuxdeployqt/releases/download/continuous/linuxdeployqt-continuous-x86_64.AppImage"
+	chmod a+x linuxdeployqt*.AppImage
+	./linuxdeployqt*.AppImage --appimage-extract
+	./squashfs-root/AppRun ./appdir/usr/share/applications/*.desktop -bundle-non-qt-libs
+	ls ./appdir/usr/lib/
+	rm -r ./appdir/usr/share/doc
+	rm ./appdir/usr/lib/libxcb*
+	cp $(readlink -f /lib/x86_64-linux-gnu/libnsl.so.1) ./appdir/usr/lib/libnsl.so.1
+	export PATH=/rpcs3/build/squashfs-root/usr/bin/:${PATH}
+
+	# Embed newer libstdc++ for distros that don't come with it (ubuntu 16.04)
+	mkdir -p appdir/usr/optional/ ; mkdir -p appdir/usr/optional/libstdc++/
+	cp /usr/lib/x86_64-linux-gnu/libstdc++.so.6 ./appdir/usr/optional/libstdc++/
+	rm ./appdir/AppRun
+	curl -sL https://github.com/RPCS3/AppImageKit-checkrt/releases/download/continuous2/AppRun-patched-x86_64 -o ./appdir/AppRun
+	chmod a+x ./appdir/AppRun
+	curl -sL https://github.com/RPCS3/AppImageKit-checkrt/releases/download/continuous2/exec-x86_64.so -o ./appdir/usr/optional/exec.so
+	
+	# Compile checker binary for AppImageKit-checkrt
+	
+	# This may need updating if you update the compiler or rpcs3 uses newer c++ features
+	# See https://github.com/gcc-mirror/gcc/blob/master/libstdc%2B%2B-v3/config/abi/pre/gnu.ver
+	# for which definitions correlate to which CXXABI version.
+	# Currently we target a minimum of GLIBCXX_3.4.26 and CXXABI_1.3.11
+	printf "#include <bits/stdc++.h>\nint main(){std::make_exception_ptr(0);std::pmr::get_default_resource();}" | $CXX -x c++ -std=c++2a -o ./appdir/usr/optional/checker -
+	
+	# Package it up and send it off
+	./squashfs-root/usr/bin/appimagetool /rpcs3/build/appdir
+	ls
+	COMM_TAG="$(grep 'version{.*}' ../rpcs3/rpcs3_version.cpp | awk -F[{,] '{printf "%d.%d.%d", $2, $3, $4}')"
+	COMM_COUNT="$(git rev-list --count HEAD)"
+	curl -sLO https://github.com/hcorion/uploadtool/raw/master/upload.sh
+	
+	mv ./RPCS3*.AppImage rpcs3-v${COMM_TAG}-${COMM_COUNT}-${TRAVIS_COMMIT:0:8}_linux64.AppImage
+	
+	FILESIZE=($(stat -c %s ./rpcs3*.AppImage))
+	SHA256SUM=($(sha256sum ./rpcs3*.AppImage))
+	
+	unset TRAVIS_REPO_SLUG
+	REPO_SLUG=RPCS3/rpcs3-binaries-linux \
+		UPLOADTOOL_BODY="$SHA256SUM;${FILESIZE}B"\
+		RELEASE_NAME=build-${TRAVIS_COMMIT}\
+		RELEASE_TITLE=${COMM_TAG}-${COMM_COUNT}\
+		REPO_COMMIT=d812f1254a1157c80fd402f94446310560f54e5f\
+		bash upload.sh rpcs3*.AppImage
+fi
+if [ "$DEPLOY_PPA" = "true" ]; then
+	export DEBFULLNAME="RPCS3 Build Bot"
+fi
@@ -0,0 +1,9 @@
+# Variables set by Travis CI
+TRAVIS_PULL_REQUEST
+TRAVIS_BRANCH
+TRAVIS_COMMIT
+# Variables for Travis build matrix
+COMPILER
+DEPLOY_APPIMAGE
+# Private Travis CI variables
+GITHUB_TOKEN
@@ -0,0 +1,202 @@
+/* 7z.h -- 7z interface
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_H
+#define __7Z_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define k7zStartHeaderSize 0x20
+#define k7zSignatureSize 6
+
+extern const Byte k7zSignature[k7zSignatureSize];
+
+typedef struct
+{
+  const Byte *Data;
+  size_t Size;
+} CSzData;
+
+/* CSzCoderInfo & CSzFolder support only default methods */
+
+typedef struct
+{
+  size_t PropsOffset;
+  UInt32 MethodID;
+  Byte NumStreams;
+  Byte PropsSize;
+} CSzCoderInfo;
+
+typedef struct
+{
+  UInt32 InIndex;
+  UInt32 OutIndex;
+} CSzBond;
+
+#define SZ_NUM_CODERS_IN_FOLDER_MAX 4
+#define SZ_NUM_BONDS_IN_FOLDER_MAX 3
+#define SZ_NUM_PACK_STREAMS_IN_FOLDER_MAX 4
+
+typedef struct
+{
+  UInt32 NumCoders;
+  UInt32 NumBonds;
+  UInt32 NumPackStreams;
+  UInt32 UnpackStream;
+  UInt32 PackStreams[SZ_NUM_PACK_STREAMS_IN_FOLDER_MAX];
+  CSzBond Bonds[SZ_NUM_BONDS_IN_FOLDER_MAX];
+  CSzCoderInfo Coders[SZ_NUM_CODERS_IN_FOLDER_MAX];
+} CSzFolder;
+
+
+SRes SzGetNextFolderItem(CSzFolder *f, CSzData *sd);
+
+typedef struct
+{
+  UInt32 Low;
+  UInt32 High;
+} CNtfsFileTime;
+
+typedef struct
+{
+  Byte *Defs; /* MSB 0 bit numbering */
+  UInt32 *Vals;
+} CSzBitUi32s;
+
+typedef struct
+{
+  Byte *Defs; /* MSB 0 bit numbering */
+  // UInt64 *Vals;
+  CNtfsFileTime *Vals;
+} CSzBitUi64s;
+
+#define SzBitArray_Check(p, i) (((p)[(i) >> 3] & (0x80 >> ((i) & 7))) != 0)
+
+#define SzBitWithVals_Check(p, i) ((p)->Defs && ((p)->Defs[(i) >> 3] & (0x80 >> ((i) & 7))) != 0)
+
+typedef struct
+{
+  UInt32 NumPackStreams;
+  UInt32 NumFolders;
+
+  UInt64 *PackPositions;          // NumPackStreams + 1
+  CSzBitUi32s FolderCRCs;         // NumFolders
+
+  size_t *FoCodersOffsets;        // NumFolders + 1
+  UInt32 *FoStartPackStreamIndex; // NumFolders + 1
+  UInt32 *FoToCoderUnpackSizes;   // NumFolders + 1
+  Byte *FoToMainUnpackSizeIndex;  // NumFolders
+  UInt64 *CoderUnpackSizes;       // for all coders in all folders
+
+  Byte *CodersData;
+} CSzAr;
+
+UInt64 SzAr_GetFolderUnpackSize(const CSzAr *p, UInt32 folderIndex);
+
+SRes SzAr_DecodeFolder(const CSzAr *p, UInt32 folderIndex,
+    ILookInStream *stream, UInt64 startPos,
+    Byte *outBuffer, size_t outSize,
+    ISzAllocPtr allocMain);
+
+typedef struct
+{
+  CSzAr db;
+
+  UInt64 startPosAfterHeader;
+  UInt64 dataPos;
+  
+  UInt32 NumFiles;
+
+  UInt64 *UnpackPositions;  // NumFiles + 1
+  // Byte *IsEmptyFiles;
+  Byte *IsDirs;
+  CSzBitUi32s CRCs;
+
+  CSzBitUi32s Attribs;
+  // CSzBitUi32s Parents;
+  CSzBitUi64s MTime;
+  CSzBitUi64s CTime;
+
+  UInt32 *FolderToFile;   // NumFolders + 1
+  UInt32 *FileToFolder;   // NumFiles
+
+  size_t *FileNameOffsets; /* in 2-byte steps */
+  Byte *FileNames;  /* UTF-16-LE */
+} CSzArEx;
+
+#define SzArEx_IsDir(p, i) (SzBitArray_Check((p)->IsDirs, i))
+
+#define SzArEx_GetFileSize(p, i) ((p)->UnpackPositions[(i) + 1] - (p)->UnpackPositions[i])
+
+void SzArEx_Init(CSzArEx *p);
+void SzArEx_Free(CSzArEx *p, ISzAllocPtr alloc);
+UInt64 SzArEx_GetFolderStreamPos(const CSzArEx *p, UInt32 folderIndex, UInt32 indexInFolder);
+int SzArEx_GetFolderFullPackSize(const CSzArEx *p, UInt32 folderIndex, UInt64 *resSize);
+
+/*
+if dest == NULL, the return value specifies the required size of the buffer,
+  in 16-bit characters, including the null-terminating character.
+if dest != NULL, the return value specifies the number of 16-bit characters that
+  are written to the dest, including the null-terminating character. */
+
+size_t SzArEx_GetFileNameUtf16(const CSzArEx *p, size_t fileIndex, UInt16 *dest);
+
+/*
+size_t SzArEx_GetFullNameLen(const CSzArEx *p, size_t fileIndex);
+UInt16 *SzArEx_GetFullNameUtf16_Back(const CSzArEx *p, size_t fileIndex, UInt16 *dest);
+*/
+
+
+
+/*
+  SzArEx_Extract extracts file from archive
+
+  *outBuffer must be 0 before first call for each new archive.
+
+  Extracting cache:
+    If you need to decompress more than one file, you can send
+    these values from previous call:
+      *blockIndex,
+      *outBuffer,
+      *outBufferSize
+    You can consider "*outBuffer" as cache of solid block. If your archive is solid,
+    it will increase decompression speed.
+  
+    If you use external function, you can declare these 3 cache variables
+    (blockIndex, outBuffer, outBufferSize) as static in that external function.
+    
+    Free *outBuffer and set *outBuffer to 0, if you want to flush cache.
+*/
+
+SRes SzArEx_Extract(
+    const CSzArEx *db,
+    ILookInStream *inStream,
+    UInt32 fileIndex,         /* index of file */
+    UInt32 *blockIndex,       /* index of solid block */
+    Byte **outBuffer,         /* pointer to pointer to output buffer (allocated with allocMain) */
+    size_t *outBufferSize,    /* buffer size for output buffer */
+    size_t *offset,           /* offset of stream for required file in *outBuffer */
+    size_t *outSizeProcessed, /* size of file in *outBuffer */
+    ISzAllocPtr allocMain,
+    ISzAllocPtr allocTemp);
+
+
+/*
+SzArEx_Open Errors:
+SZ_ERROR_NO_ARCHIVE
+SZ_ERROR_ARCHIVE
+SZ_ERROR_UNSUPPORTED
+SZ_ERROR_MEM
+SZ_ERROR_CRC
+SZ_ERROR_INPUT_EOF
+SZ_ERROR_FAIL
+*/
+
+SRes SzArEx_Open(CSzArEx *p, ILookInStream *inStream,
+    ISzAllocPtr allocMain, ISzAllocPtr allocTemp);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,80 @@
+/* 7zAlloc.c -- Allocation functions
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <stdlib.h>
+
+#include "7zAlloc.h"
+
+/* #define _SZ_ALLOC_DEBUG */
+/* use _SZ_ALLOC_DEBUG to debug alloc/free operations */
+
+#ifdef _SZ_ALLOC_DEBUG
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
+#include <stdio.h>
+int g_allocCount = 0;
+int g_allocCountTemp = 0;
+
+#endif
+
+void *SzAlloc(ISzAllocPtr p, size_t size)
+{
+  UNUSED_VAR(p);
+  if (size == 0)
+    return 0;
+  #ifdef _SZ_ALLOC_DEBUG
+  fprintf(stderr, "\nAlloc %10u bytes; count = %10d", (unsigned)size, g_allocCount);
+  g_allocCount++;
+  #endif
+  return malloc(size);
+}
+
+void SzFree(ISzAllocPtr p, void *address)
+{
+  UNUSED_VAR(p);
+  #ifdef _SZ_ALLOC_DEBUG
+  if (address != 0)
+  {
+    g_allocCount--;
+    fprintf(stderr, "\nFree; count = %10d", g_allocCount);
+  }
+  #endif
+  free(address);
+}
+
+void *SzAllocTemp(ISzAllocPtr p, size_t size)
+{
+  UNUSED_VAR(p);
+  if (size == 0)
+    return 0;
+  #ifdef _SZ_ALLOC_DEBUG
+  fprintf(stderr, "\nAlloc_temp %10u bytes;  count = %10d", (unsigned)size, g_allocCountTemp);
+  g_allocCountTemp++;
+  #ifdef _WIN32
+  return HeapAlloc(GetProcessHeap(), 0, size);
+  #endif
+  #endif
+  return malloc(size);
+}
+
+void SzFreeTemp(ISzAllocPtr p, void *address)
+{
+  UNUSED_VAR(p);
+  #ifdef _SZ_ALLOC_DEBUG
+  if (address != 0)
+  {
+    g_allocCountTemp--;
+    fprintf(stderr, "\nFree_temp; count = %10d", g_allocCountTemp);
+  }
+  #ifdef _WIN32
+  HeapFree(GetProcessHeap(), 0, address);
+  return;
+  #endif
+  #endif
+  free(address);
+}
@@ -0,0 +1,19 @@
+/* 7zAlloc.h -- Allocation functions
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_ALLOC_H
+#define __7Z_ALLOC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+void *SzAlloc(ISzAllocPtr p, size_t size);
+void SzFree(ISzAllocPtr p, void *address);
+
+void *SzAllocTemp(ISzAllocPtr p, size_t size);
+void SzFreeTemp(ISzAllocPtr p, void *address);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,36 @@
+/* 7zBuf.c -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zBuf.h"
+
+void Buf_Init(CBuf *p)
+{
+  p->data = 0;
+  p->size = 0;
+}
+
+int Buf_Create(CBuf *p, size_t size, ISzAllocPtr alloc)
+{
+  p->size = 0;
+  if (size == 0)
+  {
+    p->data = 0;
+    return 1;
+  }
+  p->data = (Byte *)ISzAlloc_Alloc(alloc, size);
+  if (p->data)
+  {
+    p->size = size;
+    return 1;
+  }
+  return 0;
+}
+
+void Buf_Free(CBuf *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->data);
+  p->data = 0;
+  p->size = 0;
+}
@@ -0,0 +1,35 @@
+/* 7zBuf.h -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_BUF_H
+#define __7Z_BUF_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+typedef struct
+{
+  Byte *data;
+  size_t size;
+} CBuf;
+
+void Buf_Init(CBuf *p);
+int Buf_Create(CBuf *p, size_t size, ISzAllocPtr alloc);
+void Buf_Free(CBuf *p, ISzAllocPtr alloc);
+
+typedef struct
+{
+  Byte *data;
+  size_t size;
+  size_t pos;
+} CDynBuf;
+
+void DynBuf_Construct(CDynBuf *p);
+void DynBuf_SeekToBeg(CDynBuf *p);
+int DynBuf_Write(CDynBuf *p, const Byte *buf, size_t size, ISzAllocPtr alloc);
+void DynBuf_Free(CDynBuf *p, ISzAllocPtr alloc);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,52 @@
+/* 7zBuf2.c -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zBuf.h"
+
+void DynBuf_Construct(CDynBuf *p)
+{
+  p->data = 0;
+  p->size = 0;
+  p->pos = 0;
+}
+
+void DynBuf_SeekToBeg(CDynBuf *p)
+{
+  p->pos = 0;
+}
+
+int DynBuf_Write(CDynBuf *p, const Byte *buf, size_t size, ISzAllocPtr alloc)
+{
+  if (size > p->size - p->pos)
+  {
+    size_t newSize = p->pos + size;
+    Byte *data;
+    newSize += newSize / 4;
+    data = (Byte *)ISzAlloc_Alloc(alloc, newSize);
+    if (!data)
+      return 0;
+    p->size = newSize;
+    if (p->pos != 0)
+      memcpy(data, p->data, p->pos);
+    ISzAlloc_Free(alloc, p->data);
+    p->data = data;
+  }
+  if (size != 0)
+  {
+    memcpy(p->data + p->pos, buf, size);
+    p->pos += size;
+  }
+  return 1;
+}
+
+void DynBuf_Free(CDynBuf *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->data);
+  p->data = 0;
+  p->size = 0;
+  p->pos = 0;
+}
@@ -0,0 +1,128 @@
+/* 7zCrc.c -- CRC32 init
+2017-06-06 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+
+#define kCrcPoly 0xEDB88320
+
+#ifdef MY_CPU_LE
+  #define CRC_NUM_TABLES 8
+#else
+  #define CRC_NUM_TABLES 9
+
+  #define CRC_UINT32_SWAP(v) ((v >> 24) | ((v >> 8) & 0xFF00) | ((v << 8) & 0xFF0000) | (v << 24))
+
+  UInt32 MY_FAST_CALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
+  UInt32 MY_FAST_CALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+
+#ifndef MY_CPU_BE
+  UInt32 MY_FAST_CALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
+  UInt32 MY_FAST_CALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+
+typedef UInt32 (MY_FAST_CALL *CRC_FUNC)(UInt32 v, const void *data, size_t size, const UInt32 *table);
+
+CRC_FUNC g_CrcUpdateT4;
+CRC_FUNC g_CrcUpdateT8;
+CRC_FUNC g_CrcUpdate;
+
+UInt32 g_CrcTable[256 * CRC_NUM_TABLES];
+
+UInt32 MY_FAST_CALL CrcUpdate(UInt32 v, const void *data, size_t size)
+{
+  return g_CrcUpdate(v, data, size, g_CrcTable);
+}
+
+UInt32 MY_FAST_CALL CrcCalc(const void *data, size_t size)
+{
+  return g_CrcUpdate(CRC_INIT_VAL, data, size, g_CrcTable) ^ CRC_INIT_VAL;
+}
+
+#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  const Byte *pEnd = p + size;
+  for (; p != pEnd; p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+void MY_FAST_CALL CrcGenerateTable()
+{
+  UInt32 i;
+  for (i = 0; i < 256; i++)
+  {
+    UInt32 r = i;
+    unsigned j;
+    for (j = 0; j < 8; j++)
+      r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1)));
+    g_CrcTable[i] = r;
+  }
+  for (i = 256; i < 256 * CRC_NUM_TABLES; i++)
+  {
+    UInt32 r = g_CrcTable[(size_t)i - 256];
+    g_CrcTable[i] = g_CrcTable[r & 0xFF] ^ (r >> 8);
+  }
+
+  #if CRC_NUM_TABLES < 4
+  
+  g_CrcUpdate = CrcUpdateT1;
+  
+  #else
+ 
+  #ifdef MY_CPU_LE
+
+    g_CrcUpdateT4 = CrcUpdateT4;
+    g_CrcUpdate = CrcUpdateT4;
+
+    #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT8;
+  
+      #ifdef MY_CPU_X86_OR_AMD64
+      if (!CPU_Is_InOrder())
+      #endif
+        g_CrcUpdate = CrcUpdateT8;
+    #endif
+
+  #else
+  {
+    #ifndef MY_CPU_BE
+    UInt32 k = 0x01020304;
+    const Byte *p = (const Byte *)&k;
+    if (p[0] == 4 && p[1] == 3)
+    {
+      g_CrcUpdateT4 = CrcUpdateT4;
+      g_CrcUpdate = CrcUpdateT4;
+      #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT8;
+      g_CrcUpdate = CrcUpdateT8;
+      #endif
+    }
+    else if (p[0] != 1 || p[1] != 2)
+      g_CrcUpdate = CrcUpdateT1;
+    else
+    #endif
+    {
+      for (i = 256 * CRC_NUM_TABLES - 1; i >= 256; i--)
+      {
+        UInt32 x = g_CrcTable[(size_t)i - 256];
+        g_CrcTable[i] = CRC_UINT32_SWAP(x);
+      }
+      g_CrcUpdateT4 = CrcUpdateT1_BeT4;
+      g_CrcUpdate = CrcUpdateT1_BeT4;
+      #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT1_BeT8;
+      g_CrcUpdate = CrcUpdateT1_BeT8;
+      #endif
+    }
+  }
+  #endif
+
+  #endif
+}
@@ -0,0 +1,25 @@
+/* 7zCrc.h -- CRC32 calculation
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_CRC_H
+#define __7Z_CRC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+extern UInt32 g_CrcTable[];
+
+/* Call CrcGenerateTable one time before other CRC functions */
+void MY_FAST_CALL CrcGenerateTable(void);
+
+#define CRC_INIT_VAL 0xFFFFFFFF
+#define CRC_GET_DIGEST(crc) ((crc) ^ CRC_INIT_VAL)
+#define CRC_UPDATE_BYTE(crc, b) (g_CrcTable[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdate(UInt32 crc, const void *data, size_t size);
+UInt32 MY_FAST_CALL CrcCalc(const void *data, size_t size);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,115 @@
+/* 7zCrcOpt.c -- CRC32 calculation
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifndef MY_CPU_BE
+
+#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    v ^= *(const UInt32 *)p;
+    v =
+          (table + 0x300)[((v      ) & 0xFF)]
+        ^ (table + 0x200)[((v >>  8) & 0xFF)]
+        ^ (table + 0x100)[((v >> 16) & 0xFF)]
+        ^ (table + 0x000)[((v >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+UInt32 MY_FAST_CALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  for (; size >= 8; size -= 8, p += 8)
+  {
+    UInt32 d;
+    v ^= *(const UInt32 *)p;
+    v =
+          (table + 0x700)[((v      ) & 0xFF)]
+        ^ (table + 0x600)[((v >>  8) & 0xFF)]
+        ^ (table + 0x500)[((v >> 16) & 0xFF)]
+        ^ (table + 0x400)[((v >> 24))];
+    d = *((const UInt32 *)p + 1);
+    v ^=
+          (table + 0x300)[((d      ) & 0xFF)]
+        ^ (table + 0x200)[((d >>  8) & 0xFF)]
+        ^ (table + 0x100)[((d >> 16) & 0xFF)]
+        ^ (table + 0x000)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+#endif
+
+
+#ifndef MY_CPU_LE
+
+#define CRC_UINT32_SWAP(v) ((v >> 24) | ((v >> 8) & 0xFF00) | ((v << 8) & 0xFF0000) | (v << 24))
+
+#define CRC_UPDATE_BYTE_2_BE(crc, b) (table[(((crc) >> 24) ^ (b))] ^ ((crc) << 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT32_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    v ^= *(const UInt32 *)p;
+    v =
+          (table + 0x000)[((v      ) & 0xFF)]
+        ^ (table + 0x100)[((v >>  8) & 0xFF)]
+        ^ (table + 0x200)[((v >> 16) & 0xFF)]
+        ^ (table + 0x300)[((v >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT32_SWAP(v);
+}
+
+UInt32 MY_FAST_CALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT32_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 8; size -= 8, p += 8)
+  {
+    UInt32 d;
+    v ^= *(const UInt32 *)p;
+    v =
+          (table + 0x400)[((v      ) & 0xFF)]
+        ^ (table + 0x500)[((v >>  8) & 0xFF)]
+        ^ (table + 0x600)[((v >> 16) & 0xFF)]
+        ^ (table + 0x700)[((v >> 24))];
+    d = *((const UInt32 *)p + 1);
+    v ^=
+          (table + 0x000)[((d      ) & 0xFF)]
+        ^ (table + 0x100)[((d >>  8) & 0xFF)]
+        ^ (table + 0x200)[((d >> 16) & 0xFF)]
+        ^ (table + 0x300)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT32_SWAP(v);
+}
+
+#endif
@@ -0,0 +1,591 @@
+/* 7zDec.c -- Decoding from 7z folder
+2019-02-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+/* #define _7ZIP_PPMD_SUPPPORT */
+
+#include "7z.h"
+#include "7zCrc.h"
+
+#include "Bcj2.h"
+#include "Bra.h"
+#include "CpuArch.h"
+#include "Delta.h"
+#include "LzmaDec.h"
+#include "Lzma2Dec.h"
+#ifdef _7ZIP_PPMD_SUPPPORT
+#include "Ppmd7.h"
+#endif
+
+#define k_Copy 0
+#define k_Delta 3
+#define k_LZMA2 0x21
+#define k_LZMA  0x30101
+#define k_BCJ   0x3030103
+#define k_BCJ2  0x303011B
+#define k_PPC   0x3030205
+#define k_IA64  0x3030401
+#define k_ARM   0x3030501
+#define k_ARMT  0x3030701
+#define k_SPARC 0x3030805
+
+
+#ifdef _7ZIP_PPMD_SUPPPORT
+
+#define k_PPMD 0x30401
+
+typedef struct
+{
+  IByteIn vt;
+  const Byte *cur;
+  const Byte *end;
+  const Byte *begin;
+  UInt64 processed;
+  BoolInt extra;
+  SRes res;
+  const ILookInStream *inStream;
+} CByteInToLook;
+
+static Byte ReadByte(const IByteIn *pp)
+{
+  CByteInToLook *p = CONTAINER_FROM_VTBL(pp, CByteInToLook, vt);
+  if (p->cur != p->end)
+    return *p->cur++;
+  if (p->res == SZ_OK)
+  {
+    size_t size = p->cur - p->begin;
+    p->processed += size;
+    p->res = ILookInStream_Skip(p->inStream, size);
+    size = (1 << 25);
+    p->res = ILookInStream_Look(p->inStream, (const void **)&p->begin, &size);
+    p->cur = p->begin;
+    p->end = p->begin + size;
+    if (size != 0)
+      return *p->cur++;;
+  }
+  p->extra = True;
+  return 0;
+}
+
+static SRes SzDecodePpmd(const Byte *props, unsigned propsSize, UInt64 inSize, const ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CPpmd7 ppmd;
+  CByteInToLook s;
+  SRes res = SZ_OK;
+
+  s.vt.Read = ReadByte;
+  s.inStream = inStream;
+  s.begin = s.end = s.cur = NULL;
+  s.extra = False;
+  s.res = SZ_OK;
+  s.processed = 0;
+
+  if (propsSize != 5)
+    return SZ_ERROR_UNSUPPORTED;
+
+  {
+    unsigned order = props[0];
+    UInt32 memSize = GetUi32(props + 1);
+    if (order < PPMD7_MIN_ORDER ||
+        order > PPMD7_MAX_ORDER ||
+        memSize < PPMD7_MIN_MEM_SIZE ||
+        memSize > PPMD7_MAX_MEM_SIZE)
+      return SZ_ERROR_UNSUPPORTED;
+    Ppmd7_Construct(&ppmd);
+    if (!Ppmd7_Alloc(&ppmd, memSize, allocMain))
+      return SZ_ERROR_MEM;
+    Ppmd7_Init(&ppmd, order);
+  }
+  {
+    CPpmd7z_RangeDec rc;
+    Ppmd7z_RangeDec_CreateVTable(&rc);
+    rc.Stream = &s.vt;
+    if (!Ppmd7z_RangeDec_Init(&rc))
+      res = SZ_ERROR_DATA;
+    else if (s.extra)
+      res = (s.res != SZ_OK ? s.res : SZ_ERROR_DATA);
+    else
+    {
+      SizeT i;
+      for (i = 0; i < outSize; i++)
+      {
+        int sym = Ppmd7_DecodeSymbol(&ppmd, &rc.vt);
+        if (s.extra || sym < 0)
+          break;
+        outBuffer[i] = (Byte)sym;
+      }
+      if (i != outSize)
+        res = (s.res != SZ_OK ? s.res : SZ_ERROR_DATA);
+      else if (s.processed + (s.cur - s.begin) != inSize || !Ppmd7z_RangeDec_IsFinishedOK(&rc))
+        res = SZ_ERROR_DATA;
+    }
+  }
+  Ppmd7_Free(&ppmd, allocMain);
+  return res;
+}
+
+#endif
+
+
+static SRes SzDecodeLzma(const Byte *props, unsigned propsSize, UInt64 inSize, ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CLzmaDec state;
+  SRes res = SZ_OK;
+
+  LzmaDec_Construct(&state);
+  RINOK(LzmaDec_AllocateProbs(&state, props, propsSize, allocMain));
+  state.dic = outBuffer;
+  state.dicBufSize = outSize;
+  LzmaDec_Init(&state);
+
+  for (;;)
+  {
+    const void *inBuf = NULL;
+    size_t lookahead = (1 << 18);
+    if (lookahead > inSize)
+      lookahead = (size_t)inSize;
+    res = ILookInStream_Look(inStream, &inBuf, &lookahead);
+    if (res != SZ_OK)
+      break;
+
+    {
+      SizeT inProcessed = (SizeT)lookahead, dicPos = state.dicPos;
+      ELzmaStatus status;
+      res = LzmaDec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
+      lookahead -= inProcessed;
+      inSize -= inProcessed;
+      if (res != SZ_OK)
+        break;
+
+      if (status == LZMA_STATUS_FINISHED_WITH_MARK)
+      {
+        if (outSize != state.dicPos || inSize != 0)
+          res = SZ_ERROR_DATA;
+        break;
+      }
+
+      if (outSize == state.dicPos && inSize == 0 && status == LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK)
+        break;
+
+      if (inProcessed == 0 && dicPos == state.dicPos)
+      {
+        res = SZ_ERROR_DATA;
+        break;
+      }
+
+      res = ILookInStream_Skip(inStream, inProcessed);
+      if (res != SZ_OK)
+        break;
+    }
+  }
+
+  LzmaDec_FreeProbs(&state, allocMain);
+  return res;
+}
+
+
+#ifndef _7Z_NO_METHOD_LZMA2
+
+static SRes SzDecodeLzma2(const Byte *props, unsigned propsSize, UInt64 inSize, ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CLzma2Dec state;
+  SRes res = SZ_OK;
+
+  Lzma2Dec_Construct(&state);
+  if (propsSize != 1)
+    return SZ_ERROR_DATA;
+  RINOK(Lzma2Dec_AllocateProbs(&state, props[0], allocMain));
+  state.decoder.dic = outBuffer;
+  state.decoder.dicBufSize = outSize;
+  Lzma2Dec_Init(&state);
+
+  for (;;)
+  {
+    const void *inBuf = NULL;
+    size_t lookahead = (1 << 18);
+    if (lookahead > inSize)
+      lookahead = (size_t)inSize;
+    res = ILookInStream_Look(inStream, &inBuf, &lookahead);
+    if (res != SZ_OK)
+      break;
+
+    {
+      SizeT inProcessed = (SizeT)lookahead, dicPos = state.decoder.dicPos;
+      ELzmaStatus status;
+      res = Lzma2Dec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
+      lookahead -= inProcessed;
+      inSize -= inProcessed;
+      if (res != SZ_OK)
+        break;
+
+      if (status == LZMA_STATUS_FINISHED_WITH_MARK)
+      {
+        if (outSize != state.decoder.dicPos || inSize != 0)
+          res = SZ_ERROR_DATA;
+        break;
+      }
+
+      if (inProcessed == 0 && dicPos == state.decoder.dicPos)
+      {
+        res = SZ_ERROR_DATA;
+        break;
+      }
+
+      res = ILookInStream_Skip(inStream, inProcessed);
+      if (res != SZ_OK)
+        break;
+    }
+  }
+
+  Lzma2Dec_FreeProbs(&state, allocMain);
+  return res;
+}
+
+#endif
+
+
+static SRes SzDecodeCopy(UInt64 inSize, ILookInStream *inStream, Byte *outBuffer)
+{
+  while (inSize > 0)
+  {
+    const void *inBuf;
+    size_t curSize = (1 << 18);
+    if (curSize > inSize)
+      curSize = (size_t)inSize;
+    RINOK(ILookInStream_Look(inStream, &inBuf, &curSize));
+    if (curSize == 0)
+      return SZ_ERROR_INPUT_EOF;
+    memcpy(outBuffer, inBuf, curSize);
+    outBuffer += curSize;
+    inSize -= curSize;
+    RINOK(ILookInStream_Skip(inStream, curSize));
+  }
+  return SZ_OK;
+}
+
+static BoolInt IS_MAIN_METHOD(UInt32 m)
+{
+  switch (m)
+  {
+    case k_Copy:
+    case k_LZMA:
+    #ifndef _7Z_NO_METHOD_LZMA2
+    case k_LZMA2:
+    #endif
+    #ifdef _7ZIP_PPMD_SUPPPORT
+    case k_PPMD:
+    #endif
+      return True;
+  }
+  return False;
+}
+
+static BoolInt IS_SUPPORTED_CODER(const CSzCoderInfo *c)
+{
+  return
+      c->NumStreams == 1
+      /* && c->MethodID <= (UInt32)0xFFFFFFFF */
+      && IS_MAIN_METHOD((UInt32)c->MethodID);
+}
+
+#define IS_BCJ2(c) ((c)->MethodID == k_BCJ2 && (c)->NumStreams == 4)
+
+static SRes CheckSupportedFolder(const CSzFolder *f)
+{
+  if (f->NumCoders < 1 || f->NumCoders > 4)
+    return SZ_ERROR_UNSUPPORTED;
+  if (!IS_SUPPORTED_CODER(&f->Coders[0]))
+    return SZ_ERROR_UNSUPPORTED;
+  if (f->NumCoders == 1)
+  {
+    if (f->NumPackStreams != 1 || f->PackStreams[0] != 0 || f->NumBonds != 0)
+      return SZ_ERROR_UNSUPPORTED;
+    return SZ_OK;
+  }
+  
+  
+  #ifndef _7Z_NO_METHODS_FILTERS
+
+  if (f->NumCoders == 2)
+  {
+    const CSzCoderInfo *c = &f->Coders[1];
+    if (
+        /* c->MethodID > (UInt32)0xFFFFFFFF || */
+        c->NumStreams != 1
+        || f->NumPackStreams != 1
+        || f->PackStreams[0] != 0
+        || f->NumBonds != 1
+        || f->Bonds[0].InIndex != 1
+        || f->Bonds[0].OutIndex != 0)
+      return SZ_ERROR_UNSUPPORTED;
+    switch ((UInt32)c->MethodID)
+    {
+      case k_Delta:
+      case k_BCJ:
+      case k_PPC:
+      case k_IA64:
+      case k_SPARC:
+      case k_ARM:
+      case k_ARMT:
+        break;
+      default:
+        return SZ_ERROR_UNSUPPORTED;
+    }
+    return SZ_OK;
+  }
+
+  #endif
+
+  
+  if (f->NumCoders == 4)
+  {
+    if (!IS_SUPPORTED_CODER(&f->Coders[1])
+        || !IS_SUPPORTED_CODER(&f->Coders[2])
+        || !IS_BCJ2(&f->Coders[3]))
+      return SZ_ERROR_UNSUPPORTED;
+    if (f->NumPackStreams != 4
+        || f->PackStreams[0] != 2
+        || f->PackStreams[1] != 6
+        || f->PackStreams[2] != 1
+        || f->PackStreams[3] != 0
+        || f->NumBonds != 3
+        || f->Bonds[0].InIndex != 5 || f->Bonds[0].OutIndex != 0
+        || f->Bonds[1].InIndex != 4 || f->Bonds[1].OutIndex != 1
+        || f->Bonds[2].InIndex != 3 || f->Bonds[2].OutIndex != 2)
+      return SZ_ERROR_UNSUPPORTED;
+    return SZ_OK;
+  }
+  
+  return SZ_ERROR_UNSUPPORTED;
+}
+
+#define CASE_BRA_CONV(isa) case k_ ## isa: isa ## _Convert(outBuffer, outSize, 0, 0); break;
+
+static SRes SzFolder_Decode2(const CSzFolder *folder,
+    const Byte *propsData,
+    const UInt64 *unpackSizes,
+    const UInt64 *packPositions,
+    ILookInStream *inStream, UInt64 startPos,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain,
+    Byte *tempBuf[])
+{
+  UInt32 ci;
+  SizeT tempSizes[3] = { 0, 0, 0};
+  SizeT tempSize3 = 0;
+  Byte *tempBuf3 = 0;
+
+  RINOK(CheckSupportedFolder(folder));
+
+  for (ci = 0; ci < folder->NumCoders; ci++)
+  {
+    const CSzCoderInfo *coder = &folder->Coders[ci];
+
+    if (IS_MAIN_METHOD((UInt32)coder->MethodID))
+    {
+      UInt32 si = 0;
+      UInt64 offset;
+      UInt64 inSize;
+      Byte *outBufCur = outBuffer;
+      SizeT outSizeCur = outSize;
+      if (folder->NumCoders == 4)
+      {
+        UInt32 indices[] = { 3, 2, 0 };
+        UInt64 unpackSize = unpackSizes[ci];
+        si = indices[ci];
+        if (ci < 2)
+        {
+          Byte *temp;
+          outSizeCur = (SizeT)unpackSize;
+          if (outSizeCur != unpackSize)
+            return SZ_ERROR_MEM;
+          temp = (Byte *)ISzAlloc_Alloc(allocMain, outSizeCur);
+          if (!temp && outSizeCur != 0)
+            return SZ_ERROR_MEM;
+          outBufCur = tempBuf[1 - ci] = temp;
+          tempSizes[1 - ci] = outSizeCur;
+        }
+        else if (ci == 2)
+        {
+          if (unpackSize > outSize) /* check it */
+            return SZ_ERROR_PARAM;
+          tempBuf3 = outBufCur = outBuffer + (outSize - (size_t)unpackSize);
+          tempSize3 = outSizeCur = (SizeT)unpackSize;
+        }
+        else
+          return SZ_ERROR_UNSUPPORTED;
+      }
+      offset = packPositions[si];
+      inSize = packPositions[(size_t)si + 1] - offset;
+      RINOK(LookInStream_SeekTo(inStream, startPos + offset));
+
+      if (coder->MethodID == k_Copy)
+      {
+        if (inSize != outSizeCur) /* check it */
+          return SZ_ERROR_DATA;
+        RINOK(SzDecodeCopy(inSize, inStream, outBufCur));
+      }
+      else if (coder->MethodID == k_LZMA)
+      {
+        RINOK(SzDecodeLzma(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #ifndef _7Z_NO_METHOD_LZMA2
+      else if (coder->MethodID == k_LZMA2)
+      {
+        RINOK(SzDecodeLzma2(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #endif
+      #ifdef _7ZIP_PPMD_SUPPPORT
+      else if (coder->MethodID == k_PPMD)
+      {
+        RINOK(SzDecodePpmd(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #endif
+      else
+        return SZ_ERROR_UNSUPPORTED;
+    }
+    else if (coder->MethodID == k_BCJ2)
+    {
+      UInt64 offset = packPositions[1];
+      UInt64 s3Size = packPositions[2] - offset;
+      
+      if (ci != 3)
+        return SZ_ERROR_UNSUPPORTED;
+      
+      tempSizes[2] = (SizeT)s3Size;
+      if (tempSizes[2] != s3Size)
+        return SZ_ERROR_MEM;
+      tempBuf[2] = (Byte *)ISzAlloc_Alloc(allocMain, tempSizes[2]);
+      if (!tempBuf[2] && tempSizes[2] != 0)
+        return SZ_ERROR_MEM;
+      
+      RINOK(LookInStream_SeekTo(inStream, startPos + offset));
+      RINOK(SzDecodeCopy(s3Size, inStream, tempBuf[2]));
+
+      if ((tempSizes[0] & 3) != 0 ||
+          (tempSizes[1] & 3) != 0 ||
+          tempSize3 + tempSizes[0] + tempSizes[1] != outSize)
+        return SZ_ERROR_DATA;
+
+      {
+        CBcj2Dec p;
+        
+        p.bufs[0] = tempBuf3;   p.lims[0] = tempBuf3 + tempSize3;
+        p.bufs[1] = tempBuf[0]; p.lims[1] = tempBuf[0] + tempSizes[0];
+        p.bufs[2] = tempBuf[1]; p.lims[2] = tempBuf[1] + tempSizes[1];
+        p.bufs[3] = tempBuf[2]; p.lims[3] = tempBuf[2] + tempSizes[2];
+        
+        p.dest = outBuffer;
+        p.destLim = outBuffer + outSize;
+        
+        Bcj2Dec_Init(&p);
+        RINOK(Bcj2Dec_Decode(&p));
+
+        {
+          unsigned i;
+          for (i = 0; i < 4; i++)
+            if (p.bufs[i] != p.lims[i])
+              return SZ_ERROR_DATA;
+          
+          if (!Bcj2Dec_IsFinished(&p))
+            return SZ_ERROR_DATA;
+
+          if (p.dest != p.destLim
+             || p.state != BCJ2_STREAM_MAIN)
+            return SZ_ERROR_DATA;
+        }
+      }
+    }
+    #ifndef _7Z_NO_METHODS_FILTERS
+    else if (ci == 1)
+    {
+      if (coder->MethodID == k_Delta)
+      {
+        if (coder->PropsSize != 1)
+          return SZ_ERROR_UNSUPPORTED;
+        {
+          Byte state[DELTA_STATE_SIZE];
+          Delta_Init(state);
+          Delta_Decode(state, (unsigned)(propsData[coder->PropsOffset]) + 1, outBuffer, outSize);
+        }
+      }
+      else
+      {
+        if (coder->PropsSize != 0)
+          return SZ_ERROR_UNSUPPORTED;
+        switch (coder->MethodID)
+        {
+          case k_BCJ:
+          {
+            UInt32 state;
+            x86_Convert_Init(state);
+            x86_Convert(outBuffer, outSize, 0, &state, 0);
+            break;
+          }
+          CASE_BRA_CONV(PPC)
+          CASE_BRA_CONV(IA64)
+          CASE_BRA_CONV(SPARC)
+          CASE_BRA_CONV(ARM)
+          CASE_BRA_CONV(ARMT)
+          default:
+            return SZ_ERROR_UNSUPPORTED;
+        }
+      }
+    }
+    #endif
+    else
+      return SZ_ERROR_UNSUPPORTED;
+  }
+
+  return SZ_OK;
+}
+
+
+SRes SzAr_DecodeFolder(const CSzAr *p, UInt32 folderIndex,
+    ILookInStream *inStream, UInt64 startPos,
+    Byte *outBuffer, size_t outSize,
+    ISzAllocPtr allocMain)
+{
+  SRes res;
+  CSzFolder folder;
+  CSzData sd;
+  
+  const Byte *data = p->CodersData + p->FoCodersOffsets[folderIndex];
+  sd.Data = data;
+  sd.Size = p->FoCodersOffsets[(size_t)folderIndex + 1] - p->FoCodersOffsets[folderIndex];
+  
+  res = SzGetNextFolderItem(&folder, &sd);
+  
+  if (res != SZ_OK)
+    return res;
+
+  if (sd.Size != 0
+      || folder.UnpackStream != p->FoToMainUnpackSizeIndex[folderIndex]
+      || outSize != SzAr_GetFolderUnpackSize(p, folderIndex))
+    return SZ_ERROR_FAIL;
+  {
+    unsigned i;
+    Byte *tempBuf[3] = { 0, 0, 0};
+
+    res = SzFolder_Decode2(&folder, data,
+        &p->CoderUnpackSizes[p->FoToCoderUnpackSizes[folderIndex]],
+        p->PackPositions + p->FoStartPackStreamIndex[folderIndex],
+        inStream, startPos,
+        outBuffer, (SizeT)outSize, allocMain, tempBuf);
+    
+    for (i = 0; i < 3; i++)
+      ISzAlloc_Free(allocMain, tempBuf[i]);
+
+    if (res == SZ_OK)
+      if (SzBitWithVals_Check(&p->FolderCRCs, folderIndex))
+        if (CrcCalc(outBuffer, outSize) != p->FolderCRCs.Vals[folderIndex])
+          res = SZ_ERROR_CRC;
+
+    return res;
+  }
+}
@@ -0,0 +1,286 @@
+/* 7zFile.c -- File IO
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zFile.h"
+
+#ifndef USE_WINDOWS_FILE
+
+#ifndef UNDER_CE
+#include <errno.h>
+#endif
+
+#else
+
+/*
+   ReadFile and WriteFile functions in Windows have BUG:
+   If you Read or Write 64MB or more (probably min_failure_size = 64MB - 32KB + 1)
+   from/to Network file, it returns ERROR_NO_SYSTEM_RESOURCES
+   (Insufficient system resources exist to complete the requested service).
+   Probably in some version of Windows there are problems with other sizes:
+   for 32 MB (maybe also for 16 MB).
+   And message can be "Network connection was lost"
+*/
+
+#define kChunkSizeMax (1 << 22)
+
+#endif
+
+void File_Construct(CSzFile *p)
+{
+  #ifdef USE_WINDOWS_FILE
+  p->handle = INVALID_HANDLE_VALUE;
+  #else
+  p->file = NULL;
+  #endif
+}
+
+#if !defined(UNDER_CE) || !defined(USE_WINDOWS_FILE)
+static WRes File_Open(CSzFile *p, const char *name, int writeMode)
+{
+  #ifdef USE_WINDOWS_FILE
+  p->handle = CreateFileA(name,
+      writeMode ? GENERIC_WRITE : GENERIC_READ,
+      FILE_SHARE_READ, NULL,
+      writeMode ? CREATE_ALWAYS : OPEN_EXISTING,
+      FILE_ATTRIBUTE_NORMAL, NULL);
+  return (p->handle != INVALID_HANDLE_VALUE) ? 0 : GetLastError();
+  #else
+  p->file = fopen(name, writeMode ? "wb+" : "rb");
+  return (p->file != 0) ? 0 :
+    #ifdef UNDER_CE
+    2; /* ENOENT */
+    #else
+    errno;
+    #endif
+  #endif
+}
+
+WRes InFile_Open(CSzFile *p, const char *name) { return File_Open(p, name, 0); }
+WRes OutFile_Open(CSzFile *p, const char *name) { return File_Open(p, name, 1); }
+#endif
+
+#ifdef USE_WINDOWS_FILE
+static WRes File_OpenW(CSzFile *p, const WCHAR *name, int writeMode)
+{
+  p->handle = CreateFileW(name,
+      writeMode ? GENERIC_WRITE : GENERIC_READ,
+      FILE_SHARE_READ, NULL,
+      writeMode ? CREATE_ALWAYS : OPEN_EXISTING,
+      FILE_ATTRIBUTE_NORMAL, NULL);
+  return (p->handle != INVALID_HANDLE_VALUE) ? 0 : GetLastError();
+}
+WRes InFile_OpenW(CSzFile *p, const WCHAR *name) { return File_OpenW(p, name, 0); }
+WRes OutFile_OpenW(CSzFile *p, const WCHAR *name) { return File_OpenW(p, name, 1); }
+#endif
+
+WRes File_Close(CSzFile *p)
+{
+  #ifdef USE_WINDOWS_FILE
+  if (p->handle != INVALID_HANDLE_VALUE)
+  {
+    if (!CloseHandle(p->handle))
+      return GetLastError();
+    p->handle = INVALID_HANDLE_VALUE;
+  }
+  #else
+  if (p->file != NULL)
+  {
+    int res = fclose(p->file);
+    if (res != 0)
+      return res;
+    p->file = NULL;
+  }
+  #endif
+  return 0;
+}
+
+WRes File_Read(CSzFile *p, void *data, size_t *size)
+{
+  size_t originalSize = *size;
+  if (originalSize == 0)
+    return 0;
+
+  #ifdef USE_WINDOWS_FILE
+
+  *size = 0;
+  do
+  {
+    DWORD curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : (DWORD)originalSize;
+    DWORD processed = 0;
+    BOOL res = ReadFile(p->handle, data, curSize, &processed, NULL);
+    data = (void *)((Byte *)data + processed);
+    originalSize -= processed;
+    *size += processed;
+    if (!res)
+      return GetLastError();
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+  return 0;
+
+  #else
+  
+  *size = fread(data, 1, originalSize, p->file);
+  if (*size == originalSize)
+    return 0;
+  return ferror(p->file);
+  
+  #endif
+}
+
+WRes File_Write(CSzFile *p, const void *data, size_t *size)
+{
+  size_t originalSize = *size;
+  if (originalSize == 0)
+    return 0;
+  
+  #ifdef USE_WINDOWS_FILE
+
+  *size = 0;
+  do
+  {
+    DWORD curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : (DWORD)originalSize;
+    DWORD processed = 0;
+    BOOL res = WriteFile(p->handle, data, curSize, &processed, NULL);
+    data = (void *)((Byte *)data + processed);
+    originalSize -= processed;
+    *size += processed;
+    if (!res)
+      return GetLastError();
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+  return 0;
+
+  #else
+
+  *size = fwrite(data, 1, originalSize, p->file);
+  if (*size == originalSize)
+    return 0;
+  return ferror(p->file);
+  
+  #endif
+}
+
+WRes File_Seek(CSzFile *p, Int64 *pos, ESzSeek origin)
+{
+  #ifdef USE_WINDOWS_FILE
+
+  LARGE_INTEGER value;
+  DWORD moveMethod;
+  value.LowPart = (DWORD)*pos;
+  value.HighPart = (LONG)((UInt64)*pos >> 16 >> 16); /* for case when UInt64 is 32-bit only */
+  switch (origin)
+  {
+    case SZ_SEEK_SET: moveMethod = FILE_BEGIN; break;
+    case SZ_SEEK_CUR: moveMethod = FILE_CURRENT; break;
+    case SZ_SEEK_END: moveMethod = FILE_END; break;
+    default: return ERROR_INVALID_PARAMETER;
+  }
+  value.LowPart = SetFilePointer(p->handle, value.LowPart, &value.HighPart, moveMethod);
+  if (value.LowPart == 0xFFFFFFFF)
+  {
+    WRes res = GetLastError();
+    if (res != NO_ERROR)
+      return res;
+  }
+  *pos = ((Int64)value.HighPart << 32) | value.LowPart;
+  return 0;
+
+  #else
+  
+  int moveMethod;
+  int res;
+  switch (origin)
+  {
+    case SZ_SEEK_SET: moveMethod = SEEK_SET; break;
+    case SZ_SEEK_CUR: moveMethod = SEEK_CUR; break;
+    case SZ_SEEK_END: moveMethod = SEEK_END; break;
+    default: return 1;
+  }
+  res = fseek(p->file, (long)*pos, moveMethod);
+  *pos = ftell(p->file);
+  return res;
+  
+  #endif
+}
+
+WRes File_GetLength(CSzFile *p, UInt64 *length)
+{
+  #ifdef USE_WINDOWS_FILE
+  
+  DWORD sizeHigh;
+  DWORD sizeLow = GetFileSize(p->handle, &sizeHigh);
+  if (sizeLow == 0xFFFFFFFF)
+  {
+    DWORD res = GetLastError();
+    if (res != NO_ERROR)
+      return res;
+  }
+  *length = (((UInt64)sizeHigh) << 32) + sizeLow;
+  return 0;
+  
+  #else
+  
+  long pos = ftell(p->file);
+  int res = fseek(p->file, 0, SEEK_END);
+  *length = ftell(p->file);
+  fseek(p->file, pos, SEEK_SET);
+  return res;
+  
+  #endif
+}
+
+
+/* ---------- FileSeqInStream ---------- */
+
+static SRes FileSeqInStream_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CFileSeqInStream *p = CONTAINER_FROM_VTBL(pp, CFileSeqInStream, vt);
+  return File_Read(&p->file, buf, size) == 0 ? SZ_OK : SZ_ERROR_READ;
+}
+
+void FileSeqInStream_CreateVTable(CFileSeqInStream *p)
+{
+  p->vt.Read = FileSeqInStream_Read;
+}
+
+
+/* ---------- FileInStream ---------- */
+
+static SRes FileInStream_Read(const ISeekInStream *pp, void *buf, size_t *size)
+{
+  CFileInStream *p = CONTAINER_FROM_VTBL(pp, CFileInStream, vt);
+  return (File_Read(&p->file, buf, size) == 0) ? SZ_OK : SZ_ERROR_READ;
+}
+
+static SRes FileInStream_Seek(const ISeekInStream *pp, Int64 *pos, ESzSeek origin)
+{
+  CFileInStream *p = CONTAINER_FROM_VTBL(pp, CFileInStream, vt);
+  return File_Seek(&p->file, pos, origin);
+}
+
+void FileInStream_CreateVTable(CFileInStream *p)
+{
+  p->vt.Read = FileInStream_Read;
+  p->vt.Seek = FileInStream_Seek;
+}
+
+
+/* ---------- FileOutStream ---------- */
+
+static size_t FileOutStream_Write(const ISeqOutStream *pp, const void *data, size_t size)
+{
+  CFileOutStream *p = CONTAINER_FROM_VTBL(pp, CFileOutStream, vt);
+  File_Write(&p->file, data, &size);
+  return size;
+}
+
+void FileOutStream_CreateVTable(CFileOutStream *p)
+{
+  p->vt.Write = FileOutStream_Write;
+}
@@ -0,0 +1,83 @@
+/* 7zFile.h -- File IO
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_FILE_H
+#define __7Z_FILE_H
+
+#ifdef _WIN32
+#define USE_WINDOWS_FILE
+#endif
+
+#ifdef USE_WINDOWS_FILE
+#include <windows.h>
+#else
+#include <stdio.h>
+#endif
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/* ---------- File ---------- */
+
+typedef struct
+{
+  #ifdef USE_WINDOWS_FILE
+  HANDLE handle;
+  #else
+  FILE *file;
+  #endif
+} CSzFile;
+
+void File_Construct(CSzFile *p);
+#if !defined(UNDER_CE) || !defined(USE_WINDOWS_FILE)
+WRes InFile_Open(CSzFile *p, const char *name);
+WRes OutFile_Open(CSzFile *p, const char *name);
+#endif
+#ifdef USE_WINDOWS_FILE
+WRes InFile_OpenW(CSzFile *p, const WCHAR *name);
+WRes OutFile_OpenW(CSzFile *p, const WCHAR *name);
+#endif
+WRes File_Close(CSzFile *p);
+
+/* reads max(*size, remain file's size) bytes */
+WRes File_Read(CSzFile *p, void *data, size_t *size);
+
+/* writes *size bytes */
+WRes File_Write(CSzFile *p, const void *data, size_t *size);
+
+WRes File_Seek(CSzFile *p, Int64 *pos, ESzSeek origin);
+WRes File_GetLength(CSzFile *p, UInt64 *length);
+
+
+/* ---------- FileInStream ---------- */
+
+typedef struct
+{
+  ISeqInStream vt;
+  CSzFile file;
+} CFileSeqInStream;
+
+void FileSeqInStream_CreateVTable(CFileSeqInStream *p);
+
+
+typedef struct
+{
+  ISeekInStream vt;
+  CSzFile file;
+} CFileInStream;
+
+void FileInStream_CreateVTable(CFileInStream *p);
+
+
+typedef struct
+{
+  ISeqOutStream vt;
+  CSzFile file;
+} CFileOutStream;
+
+void FileOutStream_CreateVTable(CFileOutStream *p);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,176 @@
+/* 7zStream.c -- 7z Stream functions
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zTypes.h"
+
+SRes SeqInStream_Read2(const ISeqInStream *stream, void *buf, size_t size, SRes errorType)
+{
+  while (size != 0)
+  {
+    size_t processed = size;
+    RINOK(ISeqInStream_Read(stream, buf, &processed));
+    if (processed == 0)
+      return errorType;
+    buf = (void *)((Byte *)buf + processed);
+    size -= processed;
+  }
+  return SZ_OK;
+}
+
+SRes SeqInStream_Read(const ISeqInStream *stream, void *buf, size_t size)
+{
+  return SeqInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+
+SRes SeqInStream_ReadByte(const ISeqInStream *stream, Byte *buf)
+{
+  size_t processed = 1;
+  RINOK(ISeqInStream_Read(stream, buf, &processed));
+  return (processed == 1) ? SZ_OK : SZ_ERROR_INPUT_EOF;
+}
+
+
+
+SRes LookInStream_SeekTo(const ILookInStream *stream, UInt64 offset)
+{
+  Int64 t = offset;
+  return ILookInStream_Seek(stream, &t, SZ_SEEK_SET);
+}
+
+SRes LookInStream_LookRead(const ILookInStream *stream, void *buf, size_t *size)
+{
+  const void *lookBuf;
+  if (*size == 0)
+    return SZ_OK;
+  RINOK(ILookInStream_Look(stream, &lookBuf, size));
+  memcpy(buf, lookBuf, *size);
+  return ILookInStream_Skip(stream, *size);
+}
+
+SRes LookInStream_Read2(const ILookInStream *stream, void *buf, size_t size, SRes errorType)
+{
+  while (size != 0)
+  {
+    size_t processed = size;
+    RINOK(ILookInStream_Read(stream, buf, &processed));
+    if (processed == 0)
+      return errorType;
+    buf = (void *)((Byte *)buf + processed);
+    size -= processed;
+  }
+  return SZ_OK;
+}
+
+SRes LookInStream_Read(const ILookInStream *stream, void *buf, size_t size)
+{
+  return LookInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+
+
+
+#define GET_LookToRead2 CLookToRead2 *p = CONTAINER_FROM_VTBL(pp, CLookToRead2, vt);
+
+static SRes LookToRead2_Look_Lookahead(const ILookInStream *pp, const void **buf, size_t *size)
+{
+  SRes res = SZ_OK;
+  GET_LookToRead2
+  size_t size2 = p->size - p->pos;
+  if (size2 == 0 && *size != 0)
+  {
+    p->pos = 0;
+    p->size = 0;
+    size2 = p->bufSize;
+    res = ISeekInStream_Read(p->realStream, p->buf, &size2);
+    p->size = size2;
+  }
+  if (*size > size2)
+    *size = size2;
+  *buf = p->buf + p->pos;
+  return res;
+}
+
+static SRes LookToRead2_Look_Exact(const ILookInStream *pp, const void **buf, size_t *size)
+{
+  SRes res = SZ_OK;
+  GET_LookToRead2
+  size_t size2 = p->size - p->pos;
+  if (size2 == 0 && *size != 0)
+  {
+    p->pos = 0;
+    p->size = 0;
+    if (*size > p->bufSize)
+      *size = p->bufSize;
+    res = ISeekInStream_Read(p->realStream, p->buf, size);
+    size2 = p->size = *size;
+  }
+  if (*size > size2)
+    *size = size2;
+  *buf = p->buf + p->pos;
+  return res;
+}
+
+static SRes LookToRead2_Skip(const ILookInStream *pp, size_t offset)
+{
+  GET_LookToRead2
+  p->pos += offset;
+  return SZ_OK;
+}
+
+static SRes LookToRead2_Read(const ILookInStream *pp, void *buf, size_t *size)
+{
+  GET_LookToRead2
+  size_t rem = p->size - p->pos;
+  if (rem == 0)
+    return ISeekInStream_Read(p->realStream, buf, size);
+  if (rem > *size)
+    rem = *size;
+  memcpy(buf, p->buf + p->pos, rem);
+  p->pos += rem;
+  *size = rem;
+  return SZ_OK;
+}
+
+static SRes LookToRead2_Seek(const ILookInStream *pp, Int64 *pos, ESzSeek origin)
+{
+  GET_LookToRead2
+  p->pos = p->size = 0;
+  return ISeekInStream_Seek(p->realStream, pos, origin);
+}
+
+void LookToRead2_CreateVTable(CLookToRead2 *p, int lookahead)
+{
+  p->vt.Look = lookahead ?
+      LookToRead2_Look_Lookahead :
+      LookToRead2_Look_Exact;
+  p->vt.Skip = LookToRead2_Skip;
+  p->vt.Read = LookToRead2_Read;
+  p->vt.Seek = LookToRead2_Seek;
+}
+
+
+
+static SRes SecToLook_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CSecToLook *p = CONTAINER_FROM_VTBL(pp, CSecToLook, vt);
+  return LookInStream_LookRead(p->realStream, buf, size);
+}
+
+void SecToLook_CreateVTable(CSecToLook *p)
+{
+  p->vt.Read = SecToLook_Read;
+}
+
+static SRes SecToRead_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CSecToRead *p = CONTAINER_FROM_VTBL(pp, CSecToRead, vt);
+  return ILookInStream_Read(p->realStream, buf, size);
+}
+
+void SecToRead_CreateVTable(CSecToRead *p)
+{
+  p->vt.Read = SecToRead_Read;
+}
@@ -0,0 +1,375 @@
+/* 7zTypes.h -- Basic types
+2018-08-04 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_TYPES_H
+#define __7Z_TYPES_H
+
+#ifdef _WIN32
+/* #include <windows.h> */
+#endif
+
+#include <stddef.h>
+
+#ifndef EXTERN_C_BEGIN
+#ifdef __cplusplus
+#define EXTERN_C_BEGIN extern "C" {
+#define EXTERN_C_END }
+#else
+#define EXTERN_C_BEGIN
+#define EXTERN_C_END
+#endif
+#endif
+
+EXTERN_C_BEGIN
+
+#define SZ_OK 0
+
+#define SZ_ERROR_DATA 1
+#define SZ_ERROR_MEM 2
+#define SZ_ERROR_CRC 3
+#define SZ_ERROR_UNSUPPORTED 4
+#define SZ_ERROR_PARAM 5
+#define SZ_ERROR_INPUT_EOF 6
+#define SZ_ERROR_OUTPUT_EOF 7
+#define SZ_ERROR_READ 8
+#define SZ_ERROR_WRITE 9
+#define SZ_ERROR_PROGRESS 10
+#define SZ_ERROR_FAIL 11
+#define SZ_ERROR_THREAD 12
+
+#define SZ_ERROR_ARCHIVE 16
+#define SZ_ERROR_NO_ARCHIVE 17
+
+typedef int SRes;
+
+
+#ifdef _WIN32
+
+/* typedef DWORD WRes; */
+typedef unsigned WRes;
+#define MY_SRes_HRESULT_FROM_WRes(x) HRESULT_FROM_WIN32(x)
+
+#else
+
+typedef int WRes;
+#define MY__FACILITY_WIN32 7
+#define MY__FACILITY__WRes MY__FACILITY_WIN32
+#define MY_SRes_HRESULT_FROM_WRes(x) ((HRESULT)(x) <= 0 ? ((HRESULT)(x)) : ((HRESULT) (((x) & 0x0000FFFF) | (MY__FACILITY__WRes << 16) | 0x80000000)))
+
+#endif
+
+
+#ifndef RINOK
+#define RINOK(x) { int __result__ = (x); if (__result__ != 0) return __result__; }
+#endif
+
+typedef unsigned char Byte;
+typedef short Int16;
+typedef unsigned short UInt16;
+
+#ifdef _LZMA_UINT32_IS_ULONG
+typedef long Int32;
+typedef unsigned long UInt32;
+#else
+typedef int Int32;
+typedef unsigned int UInt32;
+#endif
+
+#ifdef _SZ_NO_INT_64
+
+/* define _SZ_NO_INT_64, if your compiler doesn't support 64-bit integers.
+   NOTES: Some code will work incorrectly in that case! */
+
+typedef long Int64;
+typedef unsigned long UInt64;
+
+#else
+
+#if defined(_MSC_VER) || defined(__BORLANDC__)
+typedef __int64 Int64;
+typedef unsigned __int64 UInt64;
+#define UINT64_CONST(n) n
+#else
+typedef long long int Int64;
+typedef unsigned long long int UInt64;
+#define UINT64_CONST(n) n ## ULL
+#endif
+
+#endif
+
+#ifdef _LZMA_NO_SYSTEM_SIZE_T
+typedef UInt32 SizeT;
+#else
+typedef size_t SizeT;
+#endif
+
+typedef int BoolInt;
+/* typedef BoolInt Bool; */
+#define True 1
+#define False 0
+
+
+#ifdef _WIN32
+#define MY_STD_CALL __stdcall
+#else
+#define MY_STD_CALL
+#endif
+
+#ifdef _MSC_VER
+
+#if _MSC_VER >= 1300
+#define MY_NO_INLINE __declspec(noinline)
+#else
+#define MY_NO_INLINE
+#endif
+
+#define MY_FORCE_INLINE __forceinline
+
+#define MY_CDECL __cdecl
+#define MY_FAST_CALL __fastcall
+
+#else
+
+#define MY_NO_INLINE
+#define MY_FORCE_INLINE
+#define MY_CDECL
+#define MY_FAST_CALL
+
+/* inline keyword : for C++ / C99 */
+
+/* GCC, clang: */
+/*
+#if defined (__GNUC__) && (__GNUC__ >= 4)
+#define MY_FORCE_INLINE __attribute__((always_inline))
+#define MY_NO_INLINE __attribute__((noinline))
+#endif
+*/
+
+#endif
+
+
+/* The following interfaces use first parameter as pointer to structure */
+
+typedef struct IByteIn IByteIn;
+struct IByteIn
+{
+  Byte (*Read)(const IByteIn *p); /* reads one byte, returns 0 in case of EOF or error */
+};
+#define IByteIn_Read(p) (p)->Read(p)
+
+
+typedef struct IByteOut IByteOut;
+struct IByteOut
+{
+  void (*Write)(const IByteOut *p, Byte b);
+};
+#define IByteOut_Write(p, b) (p)->Write(p, b)
+
+
+typedef struct ISeqInStream ISeqInStream;
+struct ISeqInStream
+{
+  SRes (*Read)(const ISeqInStream *p, void *buf, size_t *size);
+    /* if (input(*size) != 0 && output(*size) == 0) means end_of_stream.
+       (output(*size) < input(*size)) is allowed */
+};
+#define ISeqInStream_Read(p, buf, size) (p)->Read(p, buf, size)
+
+/* it can return SZ_ERROR_INPUT_EOF */
+SRes SeqInStream_Read(const ISeqInStream *stream, void *buf, size_t size);
+SRes SeqInStream_Read2(const ISeqInStream *stream, void *buf, size_t size, SRes errorType);
+SRes SeqInStream_ReadByte(const ISeqInStream *stream, Byte *buf);
+
+
+typedef struct ISeqOutStream ISeqOutStream;
+struct ISeqOutStream
+{
+  size_t (*Write)(const ISeqOutStream *p, const void *buf, size_t size);
+    /* Returns: result - the number of actually written bytes.
+       (result < size) means error */
+};
+#define ISeqOutStream_Write(p, buf, size) (p)->Write(p, buf, size)
+
+typedef enum
+{
+  SZ_SEEK_SET = 0,
+  SZ_SEEK_CUR = 1,
+  SZ_SEEK_END = 2
+} ESzSeek;
+
+
+typedef struct ISeekInStream ISeekInStream;
+struct ISeekInStream
+{
+  SRes (*Read)(const ISeekInStream *p, void *buf, size_t *size);  /* same as ISeqInStream::Read */
+  SRes (*Seek)(const ISeekInStream *p, Int64 *pos, ESzSeek origin);
+};
+#define ISeekInStream_Read(p, buf, size)   (p)->Read(p, buf, size)
+#define ISeekInStream_Seek(p, pos, origin) (p)->Seek(p, pos, origin)
+
+
+typedef struct ILookInStream ILookInStream;
+struct ILookInStream
+{
+  SRes (*Look)(const ILookInStream *p, const void **buf, size_t *size);
+    /* if (input(*size) != 0 && output(*size) == 0) means end_of_stream.
+       (output(*size) > input(*size)) is not allowed
+       (output(*size) < input(*size)) is allowed */
+  SRes (*Skip)(const ILookInStream *p, size_t offset);
+    /* offset must be <= output(*size) of Look */
+
+  SRes (*Read)(const ILookInStream *p, void *buf, size_t *size);
+    /* reads directly (without buffer). It's same as ISeqInStream::Read */
+  SRes (*Seek)(const ILookInStream *p, Int64 *pos, ESzSeek origin);
+};
+
+#define ILookInStream_Look(p, buf, size)   (p)->Look(p, buf, size)
+#define ILookInStream_Skip(p, offset)      (p)->Skip(p, offset)
+#define ILookInStream_Read(p, buf, size)   (p)->Read(p, buf, size)
+#define ILookInStream_Seek(p, pos, origin) (p)->Seek(p, pos, origin)
+
+
+SRes LookInStream_LookRead(const ILookInStream *stream, void *buf, size_t *size);
+SRes LookInStream_SeekTo(const ILookInStream *stream, UInt64 offset);
+
+/* reads via ILookInStream::Read */
+SRes LookInStream_Read2(const ILookInStream *stream, void *buf, size_t size, SRes errorType);
+SRes LookInStream_Read(const ILookInStream *stream, void *buf, size_t size);
+
+
+
+typedef struct
+{
+  ILookInStream vt;
+  const ISeekInStream *realStream;
+ 
+  size_t pos;
+  size_t size; /* it's data size */
+  
+  /* the following variables must be set outside */
+  Byte *buf;
+  size_t bufSize;
+} CLookToRead2;
+
+void LookToRead2_CreateVTable(CLookToRead2 *p, int lookahead);
+
+#define LookToRead2_Init(p) { (p)->pos = (p)->size = 0; }
+
+
+typedef struct
+{
+  ISeqInStream vt;
+  const ILookInStream *realStream;
+} CSecToLook;
+
+void SecToLook_CreateVTable(CSecToLook *p);
+
+
+
+typedef struct
+{
+  ISeqInStream vt;
+  const ILookInStream *realStream;
+} CSecToRead;
+
+void SecToRead_CreateVTable(CSecToRead *p);
+
+
+typedef struct ICompressProgress ICompressProgress;
+
+struct ICompressProgress
+{
+  SRes (*Progress)(const ICompressProgress *p, UInt64 inSize, UInt64 outSize);
+    /* Returns: result. (result != SZ_OK) means break.
+       Value (UInt64)(Int64)-1 for size means unknown value. */
+};
+#define ICompressProgress_Progress(p, inSize, outSize) (p)->Progress(p, inSize, outSize)
+
+
+
+typedef struct ISzAlloc ISzAlloc;
+typedef const ISzAlloc * ISzAllocPtr;
+
+struct ISzAlloc
+{
+  void *(*Alloc)(ISzAllocPtr p, size_t size);
+  void (*Free)(ISzAllocPtr p, void *address); /* address can be 0 */
+};
+
+#define ISzAlloc_Alloc(p, size) (p)->Alloc(p, size)
+#define ISzAlloc_Free(p, a) (p)->Free(p, a)
+
+/* deprecated */
+#define IAlloc_Alloc(p, size) ISzAlloc_Alloc(p, size)
+#define IAlloc_Free(p, a) ISzAlloc_Free(p, a)
+
+
+
+
+
+#ifndef MY_offsetof
+  #ifdef offsetof
+    #define MY_offsetof(type, m) offsetof(type, m)
+    /*
+    #define MY_offsetof(type, m) FIELD_OFFSET(type, m)
+    */
+  #else
+    #define MY_offsetof(type, m) ((size_t)&(((type *)0)->m))
+  #endif
+#endif
+
+
+
+#ifndef MY_container_of
+
+/*
+#define MY_container_of(ptr, type, m) container_of(ptr, type, m)
+#define MY_container_of(ptr, type, m) CONTAINING_RECORD(ptr, type, m)
+#define MY_container_of(ptr, type, m) ((type *)((char *)(ptr) - offsetof(type, m)))
+#define MY_container_of(ptr, type, m) (&((type *)0)->m == (ptr), ((type *)(((char *)(ptr)) - MY_offsetof(type, m))))
+*/
+
+/*
+  GCC shows warning: "perhaps the 'offsetof' macro was used incorrectly"
+    GCC 3.4.4 : classes with constructor
+    GCC 4.8.1 : classes with non-public variable members"
+*/
+
+#define MY_container_of(ptr, type, m) ((type *)((char *)(1 ? (ptr) : &((type *)0)->m) - MY_offsetof(type, m)))
+
+
+#endif
+
+#define CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) ((type *)(ptr))
+
+/*
+#define CONTAINER_FROM_VTBL(ptr, type, m) CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m)
+*/
+#define CONTAINER_FROM_VTBL(ptr, type, m) MY_container_of(ptr, type, m)
+
+#define CONTAINER_FROM_VTBL_CLS(ptr, type, m) CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m)
+/*
+#define CONTAINER_FROM_VTBL_CLS(ptr, type, m) CONTAINER_FROM_VTBL(ptr, type, m)
+*/
+
+
+
+#ifdef _WIN32
+
+#define CHAR_PATH_SEPARATOR '\\'
+#define WCHAR_PATH_SEPARATOR L'\\'
+#define STRING_PATH_SEPARATOR "\\"
+#define WSTRING_PATH_SEPARATOR L"\\"
+
+#else
+
+#define CHAR_PATH_SEPARATOR '/'
+#define WCHAR_PATH_SEPARATOR L'/'
+#define STRING_PATH_SEPARATOR "/"
+#define WSTRING_PATH_SEPARATOR L"/"
+
+#endif
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,27 @@
+#define MY_VER_MAJOR 19
+#define MY_VER_MINOR 00
+#define MY_VER_BUILD 0
+#define MY_VERSION_NUMBERS "19.00"
+#define MY_VERSION MY_VERSION_NUMBERS
+
+#ifdef MY_CPU_NAME
+  #define MY_VERSION_CPU MY_VERSION " (" MY_CPU_NAME ")"
+#else
+  #define MY_VERSION_CPU MY_VERSION
+#endif
+
+#define MY_DATE "2019-02-21"
+#undef MY_COPYRIGHT
+#undef MY_VERSION_COPYRIGHT_DATE
+#define MY_AUTHOR_NAME "Igor Pavlov"
+#define MY_COPYRIGHT_PD "Igor Pavlov : Public domain"
+#define MY_COPYRIGHT_CR "Copyright (c) 1999-2018 Igor Pavlov"
+
+#ifdef USE_COPYRIGHT_CR
+  #define MY_COPYRIGHT MY_COPYRIGHT_CR
+#else
+  #define MY_COPYRIGHT MY_COPYRIGHT_PD
+#endif
+
+#define MY_COPYRIGHT_DATE MY_COPYRIGHT " : " MY_DATE
+#define MY_VERSION_COPYRIGHT_DATE MY_VERSION_CPU " : " MY_COPYRIGHT " : " MY_DATE
@@ -0,0 +1,55 @@
+#define MY_VS_FFI_FILEFLAGSMASK  0x0000003FL
+#define MY_VOS_NT_WINDOWS32  0x00040004L
+#define MY_VOS_CE_WINDOWS32  0x00050004L
+
+#define MY_VFT_APP  0x00000001L
+#define MY_VFT_DLL  0x00000002L
+
+// #include <WinVer.h>
+
+#ifndef MY_VERSION
+#include "7zVersion.h"
+#endif
+
+#define MY_VER MY_VER_MAJOR,MY_VER_MINOR,MY_VER_BUILD,0
+
+#ifdef DEBUG
+#define DBG_FL VS_FF_DEBUG
+#else
+#define DBG_FL 0
+#endif
+
+#define MY_VERSION_INFO(fileType, descr, intName, origName)  \
+LANGUAGE 9, 1 \
+1 VERSIONINFO \
+  FILEVERSION MY_VER \
+  PRODUCTVERSION MY_VER \
+  FILEFLAGSMASK MY_VS_FFI_FILEFLAGSMASK \
+  FILEFLAGS DBG_FL \
+  FILEOS MY_VOS_NT_WINDOWS32 \
+  FILETYPE fileType \
+  FILESUBTYPE 0x0L \
+BEGIN \
+    BLOCK "StringFileInfo" \
+    BEGIN  \
+        BLOCK "040904b0" \
+        BEGIN \
+            VALUE "CompanyName", "Igor Pavlov" \
+            VALUE "FileDescription", descr \
+            VALUE "FileVersion", MY_VERSION  \
+            VALUE "InternalName", intName \
+            VALUE "LegalCopyright", MY_COPYRIGHT \
+            VALUE "OriginalFilename", origName \
+            VALUE "ProductName", "7-Zip" \
+            VALUE "ProductVersion", MY_VERSION \
+        END \
+    END \
+    BLOCK "VarFileInfo" \
+    BEGIN \
+        VALUE "Translation", 0x409, 1200 \
+    END \
+END
+
+#define MY_VERSION_INFO_APP(descr, intName) MY_VERSION_INFO(MY_VFT_APP, descr, intName, intName ".exe")
+
+#define MY_VERSION_INFO_DLL(descr, intName) MY_VERSION_INFO(MY_VFT_DLL, descr, intName, intName ".dll")
@@ -0,0 +1,306 @@
+/* Aes.c -- AES encryption / decryption
+2017-01-24 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Aes.h"
+#include "CpuArch.h"
+
+static UInt32 T[256 * 4];
+static const Byte Sbox[256] = {
+  0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
+  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
+  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
+  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
+  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
+  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
+  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
+  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
+  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
+  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
+  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
+  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
+  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
+  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
+  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
+  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16};
+
+void MY_FAST_CALL AesCbc_Encode(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCbc_Decode(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCtr_Code(UInt32 *ivAes, Byte *data, size_t numBlocks);
+
+void MY_FAST_CALL AesCbc_Encode_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCbc_Decode_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCtr_Code_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks);
+
+AES_CODE_FUNC g_AesCbc_Encode;
+AES_CODE_FUNC g_AesCbc_Decode;
+AES_CODE_FUNC g_AesCtr_Code;
+
+static UInt32 D[256 * 4];
+static Byte InvS[256];
+
+static const Byte Rcon[11] = { 0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36 };
+
+#define xtime(x) ((((x) << 1) ^ (((x) & 0x80) != 0 ? 0x1B : 0)) & 0xFF)
+
+#define Ui32(a0, a1, a2, a3) ((UInt32)(a0) | ((UInt32)(a1) << 8) | ((UInt32)(a2) << 16) | ((UInt32)(a3) << 24))
+
+#define gb0(x) ( (x)          & 0xFF)
+#define gb1(x) (((x) >> ( 8)) & 0xFF)
+#define gb2(x) (((x) >> (16)) & 0xFF)
+#define gb3(x) (((x) >> (24)))
+
+#define gb(n, x) gb ## n(x)
+
+#define TT(x) (T + (x << 8))
+#define DD(x) (D + (x << 8))
+
+
+void AesGenTables(void)
+{
+  unsigned i;
+  for (i = 0; i < 256; i++)
+    InvS[Sbox[i]] = (Byte)i;
+  
+  for (i = 0; i < 256; i++)
+  {
+    {
+      UInt32 a1 = Sbox[i];
+      UInt32 a2 = xtime(a1);
+      UInt32 a3 = a2 ^ a1;
+      TT(0)[i] = Ui32(a2, a1, a1, a3);
+      TT(1)[i] = Ui32(a3, a2, a1, a1);
+      TT(2)[i] = Ui32(a1, a3, a2, a1);
+      TT(3)[i] = Ui32(a1, a1, a3, a2);
+    }
+    {
+      UInt32 a1 = InvS[i];
+      UInt32 a2 = xtime(a1);
+      UInt32 a4 = xtime(a2);
+      UInt32 a8 = xtime(a4);
+      UInt32 a9 = a8 ^ a1;
+      UInt32 aB = a8 ^ a2 ^ a1;
+      UInt32 aD = a8 ^ a4 ^ a1;
+      UInt32 aE = a8 ^ a4 ^ a2;
+      DD(0)[i] = Ui32(aE, a9, aD, aB);
+      DD(1)[i] = Ui32(aB, aE, a9, aD);
+      DD(2)[i] = Ui32(aD, aB, aE, a9);
+      DD(3)[i] = Ui32(a9, aD, aB, aE);
+    }
+  }
+  
+  g_AesCbc_Encode = AesCbc_Encode;
+  g_AesCbc_Decode = AesCbc_Decode;
+  g_AesCtr_Code = AesCtr_Code;
+  
+  #ifdef MY_CPU_X86_OR_AMD64
+  if (CPU_Is_Aes_Supported())
+  {
+    g_AesCbc_Encode = AesCbc_Encode_Intel;
+    g_AesCbc_Decode = AesCbc_Decode_Intel;
+    g_AesCtr_Code = AesCtr_Code_Intel;
+  }
+  #endif
+}
+
+
+#define HT(i, x, s) TT(x)[gb(x, s[(i + x) & 3])]
+
+#define HT4(m, i, s, p) m[i] = \
+    HT(i, 0, s) ^ \
+    HT(i, 1, s) ^ \
+    HT(i, 2, s) ^ \
+    HT(i, 3, s) ^ w[p + i]
+
+#define HT16(m, s, p) \
+    HT4(m, 0, s, p); \
+    HT4(m, 1, s, p); \
+    HT4(m, 2, s, p); \
+    HT4(m, 3, s, p); \
+
+#define FT(i, x) Sbox[gb(x, m[(i + x) & 3])]
+#define FT4(i) dest[i] = Ui32(FT(i, 0), FT(i, 1), FT(i, 2), FT(i, 3)) ^ w[i];
+
+
+#define HD(i, x, s) DD(x)[gb(x, s[(i - x) & 3])]
+
+#define HD4(m, i, s, p) m[i] = \
+    HD(i, 0, s) ^ \
+    HD(i, 1, s) ^ \
+    HD(i, 2, s) ^ \
+    HD(i, 3, s) ^ w[p + i];
+
+#define HD16(m, s, p) \
+    HD4(m, 0, s, p); \
+    HD4(m, 1, s, p); \
+    HD4(m, 2, s, p); \
+    HD4(m, 3, s, p); \
+
+#define FD(i, x) InvS[gb(x, m[(i - x) & 3])]
+#define FD4(i) dest[i] = Ui32(FD(i, 0), FD(i, 1), FD(i, 2), FD(i, 3)) ^ w[i];
+
+void MY_FAST_CALL Aes_SetKey_Enc(UInt32 *w, const Byte *key, unsigned keySize)
+{
+  unsigned i, wSize;
+  wSize = keySize + 28;
+  keySize /= 4;
+  w[0] = ((UInt32)keySize / 2) + 3;
+  w += 4;
+
+  for (i = 0; i < keySize; i++, key += 4)
+    w[i] = GetUi32(key);
+
+  for (; i < wSize; i++)
+  {
+    UInt32 t = w[(size_t)i - 1];
+    unsigned rem = i % keySize;
+    if (rem == 0)
+      t = Ui32(Sbox[gb1(t)] ^ Rcon[i / keySize], Sbox[gb2(t)], Sbox[gb3(t)], Sbox[gb0(t)]);
+    else if (keySize > 6 && rem == 4)
+      t = Ui32(Sbox[gb0(t)], Sbox[gb1(t)], Sbox[gb2(t)], Sbox[gb3(t)]);
+    w[i] = w[i - keySize] ^ t;
+  }
+}
+
+void MY_FAST_CALL Aes_SetKey_Dec(UInt32 *w, const Byte *key, unsigned keySize)
+{
+  unsigned i, num;
+  Aes_SetKey_Enc(w, key, keySize);
+  num = keySize + 20;
+  w += 8;
+  for (i = 0; i < num; i++)
+  {
+    UInt32 r = w[i];
+    w[i] =
+      DD(0)[Sbox[gb0(r)]] ^
+      DD(1)[Sbox[gb1(r)]] ^
+      DD(2)[Sbox[gb2(r)]] ^
+      DD(3)[Sbox[gb3(r)]];
+  }
+}
+
+/* Aes_Encode and Aes_Decode functions work with little-endian words.
+  src and dest are pointers to 4 UInt32 words.
+  src and dest can point to same block */
+
+static void Aes_Encode(const UInt32 *w, UInt32 *dest, const UInt32 *src)
+{
+  UInt32 s[4];
+  UInt32 m[4];
+  UInt32 numRounds2 = w[0];
+  w += 4;
+  s[0] = src[0] ^ w[0];
+  s[1] = src[1] ^ w[1];
+  s[2] = src[2] ^ w[2];
+  s[3] = src[3] ^ w[3];
+  w += 4;
+  for (;;)
+  {
+    HT16(m, s, 0);
+    if (--numRounds2 == 0)
+      break;
+    HT16(s, m, 4);
+    w += 8;
+  }
+  w += 4;
+  FT4(0); FT4(1); FT4(2); FT4(3);
+}
+
+static void Aes_Decode(const UInt32 *w, UInt32 *dest, const UInt32 *src)
+{
+  UInt32 s[4];
+  UInt32 m[4];
+  UInt32 numRounds2 = w[0];
+  w += 4 + numRounds2 * 8;
+  s[0] = src[0] ^ w[0];
+  s[1] = src[1] ^ w[1];
+  s[2] = src[2] ^ w[2];
+  s[3] = src[3] ^ w[3];
+  for (;;)
+  {
+    w -= 8;
+    HD16(m, s, 4);
+    if (--numRounds2 == 0)
+      break;
+    HD16(s, m, 0);
+  }
+  FD4(0); FD4(1); FD4(2); FD4(3);
+}
+
+void AesCbc_Init(UInt32 *p, const Byte *iv)
+{
+  unsigned i;
+  for (i = 0; i < 4; i++)
+    p[i] = GetUi32(iv + i * 4);
+}
+
+void MY_FAST_CALL AesCbc_Encode(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  for (; numBlocks != 0; numBlocks--, data += AES_BLOCK_SIZE)
+  {
+    p[0] ^= GetUi32(data);
+    p[1] ^= GetUi32(data + 4);
+    p[2] ^= GetUi32(data + 8);
+    p[3] ^= GetUi32(data + 12);
+    
+    Aes_Encode(p + 4, p, p);
+    
+    SetUi32(data,      p[0]);
+    SetUi32(data + 4,  p[1]);
+    SetUi32(data + 8,  p[2]);
+    SetUi32(data + 12, p[3]);
+  }
+}
+
+void MY_FAST_CALL AesCbc_Decode(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  UInt32 in[4], out[4];
+  for (; numBlocks != 0; numBlocks--, data += AES_BLOCK_SIZE)
+  {
+    in[0] = GetUi32(data);
+    in[1] = GetUi32(data + 4);
+    in[2] = GetUi32(data + 8);
+    in[3] = GetUi32(data + 12);
+
+    Aes_Decode(p + 4, out, in);
+
+    SetUi32(data,      p[0] ^ out[0]);
+    SetUi32(data + 4,  p[1] ^ out[1]);
+    SetUi32(data + 8,  p[2] ^ out[2]);
+    SetUi32(data + 12, p[3] ^ out[3]);
+    
+    p[0] = in[0];
+    p[1] = in[1];
+    p[2] = in[2];
+    p[3] = in[3];
+  }
+}
+
+void MY_FAST_CALL AesCtr_Code(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  for (; numBlocks != 0; numBlocks--)
+  {
+    UInt32 temp[4];
+    unsigned i;
+
+    if (++p[0] == 0)
+      p[1]++;
+    
+    Aes_Encode(p + 4, temp, p);
+    
+    for (i = 0; i < 4; i++, data += 4)
+    {
+      UInt32 t = temp[i];
+
+      #ifdef MY_CPU_LE_UNALIGN
+        *((UInt32 *)data) ^= t;
+      #else
+        data[0] ^= (t & 0xFF);
+        data[1] ^= ((t >> 8) & 0xFF);
+        data[2] ^= ((t >> 16) & 0xFF);
+        data[3] ^= ((t >> 24));
+      #endif
+    }
+  }
+}
@@ -0,0 +1,38 @@
+/* Aes.h -- AES encryption / decryption
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __AES_H
+#define __AES_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define AES_BLOCK_SIZE 16
+
+/* Call AesGenTables one time before other AES functions */
+void AesGenTables(void);
+
+/* UInt32 pointers must be 16-byte aligned */
+
+/* 16-byte (4 * 32-bit words) blocks: 1 (IV) + 1 (keyMode) + 15 (AES-256 roundKeys) */
+#define AES_NUM_IVMRK_WORDS ((1 + 1 + 15) * 4)
+
+/* aes - 16-byte aligned pointer to keyMode+roundKeys sequence */
+/* keySize = 16 or 24 or 32 (bytes) */
+typedef void (MY_FAST_CALL *AES_SET_KEY_FUNC)(UInt32 *aes, const Byte *key, unsigned keySize);
+void MY_FAST_CALL Aes_SetKey_Enc(UInt32 *aes, const Byte *key, unsigned keySize);
+void MY_FAST_CALL Aes_SetKey_Dec(UInt32 *aes, const Byte *key, unsigned keySize);
+
+/* ivAes - 16-byte aligned pointer to iv+keyMode+roundKeys sequence: UInt32[AES_NUM_IVMRK_WORDS] */
+void AesCbc_Init(UInt32 *ivAes, const Byte *iv); /* iv size is AES_BLOCK_SIZE */
+/* data - 16-byte aligned pointer to data */
+/* numBlocks - the number of 16-byte blocks in data array */
+typedef void (MY_FAST_CALL *AES_CODE_FUNC)(UInt32 *ivAes, Byte *data, size_t numBlocks);
+extern AES_CODE_FUNC g_AesCbc_Encode;
+extern AES_CODE_FUNC g_AesCbc_Decode;
+extern AES_CODE_FUNC g_AesCtr_Code;
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,184 @@
+/* AesOpt.c -- Intel's AES
+2017-06-08 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+#if (_MSC_VER > 1500) || (_MSC_FULL_VER >= 150030729)
+#define USE_INTEL_AES
+#endif
+#endif
+
+#ifdef USE_INTEL_AES
+
+#include <wmmintrin.h>
+
+void MY_FAST_CALL AesCbc_Encode_Intel(__m128i *p, __m128i *data, size_t numBlocks)
+{
+  __m128i m = *p;
+  for (; numBlocks != 0; numBlocks--, data++)
+  {
+    UInt32 numRounds2 = *(const UInt32 *)(p + 1) - 1;
+    const __m128i *w = p + 3;
+    m = _mm_xor_si128(m, *data);
+    m = _mm_xor_si128(m, p[2]);
+    do
+    {
+      m = _mm_aesenc_si128(m, w[0]);
+      m = _mm_aesenc_si128(m, w[1]);
+      w += 2;
+    }
+    while (--numRounds2 != 0);
+    m = _mm_aesenc_si128(m, w[0]);
+    m = _mm_aesenclast_si128(m, w[1]);
+    *data = m;
+  }
+  *p = m;
+}
+
+#define NUM_WAYS 3
+
+#define AES_OP_W(op, n) { \
+    const __m128i t = w[n]; \
+    m0 = op(m0, t); \
+    m1 = op(m1, t); \
+    m2 = op(m2, t); \
+    }
+
+#define AES_DEC(n) AES_OP_W(_mm_aesdec_si128, n)
+#define AES_DEC_LAST(n) AES_OP_W(_mm_aesdeclast_si128, n)
+#define AES_ENC(n) AES_OP_W(_mm_aesenc_si128, n)
+#define AES_ENC_LAST(n) AES_OP_W(_mm_aesenclast_si128, n)
+
+void MY_FAST_CALL AesCbc_Decode_Intel(__m128i *p, __m128i *data, size_t numBlocks)
+{
+  __m128i iv = *p;
+  for (; numBlocks >= NUM_WAYS; numBlocks -= NUM_WAYS, data += NUM_WAYS)
+  {
+    UInt32 numRounds2 = *(const UInt32 *)(p + 1);
+    const __m128i *w = p + numRounds2 * 2;
+    __m128i m0, m1, m2;
+    {
+      const __m128i t = w[2];
+      m0 = _mm_xor_si128(t, data[0]);
+      m1 = _mm_xor_si128(t, data[1]);
+      m2 = _mm_xor_si128(t, data[2]);
+    }
+    numRounds2--;
+    do
+    {
+      AES_DEC(1)
+      AES_DEC(0)
+      w -= 2;
+    }
+    while (--numRounds2 != 0);
+    AES_DEC(1)
+    AES_DEC_LAST(0)
+
+    {
+      __m128i t;
+      t = _mm_xor_si128(m0, iv); iv = data[0]; data[0] = t;
+      t = _mm_xor_si128(m1, iv); iv = data[1]; data[1] = t;
+      t = _mm_xor_si128(m2, iv); iv = data[2]; data[2] = t;
+    }
+  }
+  for (; numBlocks != 0; numBlocks--, data++)
+  {
+    UInt32 numRounds2 = *(const UInt32 *)(p + 1);
+    const __m128i *w = p + numRounds2 * 2;
+    __m128i m = _mm_xor_si128(w[2], *data);
+    numRounds2--;
+    do
+    {
+      m = _mm_aesdec_si128(m, w[1]);
+      m = _mm_aesdec_si128(m, w[0]);
+      w -= 2;
+    }
+    while (--numRounds2 != 0);
+    m = _mm_aesdec_si128(m, w[1]);
+    m = _mm_aesdeclast_si128(m, w[0]);
+
+    m = _mm_xor_si128(m, iv);
+    iv = *data;
+    *data = m;
+  }
+  *p = iv;
+}
+
+void MY_FAST_CALL AesCtr_Code_Intel(__m128i *p, __m128i *data, size_t numBlocks)
+{
+  __m128i ctr = *p;
+  __m128i one;
+  one.m128i_u64[0] = 1;
+  one.m128i_u64[1] = 0;
+  for (; numBlocks >= NUM_WAYS; numBlocks -= NUM_WAYS, data += NUM_WAYS)
+  {
+    UInt32 numRounds2 = *(const UInt32 *)(p + 1) - 1;
+    const __m128i *w = p;
+    __m128i m0, m1, m2;
+    {
+      const __m128i t = w[2];
+      ctr = _mm_add_epi64(ctr, one); m0 = _mm_xor_si128(ctr, t);
+      ctr = _mm_add_epi64(ctr, one); m1 = _mm_xor_si128(ctr, t);
+      ctr = _mm_add_epi64(ctr, one); m2 = _mm_xor_si128(ctr, t);
+    }
+    w += 3;
+    do
+    {
+      AES_ENC(0)
+      AES_ENC(1)
+      w += 2;
+    }
+    while (--numRounds2 != 0);
+    AES_ENC(0)
+    AES_ENC_LAST(1)
+    data[0] = _mm_xor_si128(data[0], m0);
+    data[1] = _mm_xor_si128(data[1], m1);
+    data[2] = _mm_xor_si128(data[2], m2);
+  }
+  for (; numBlocks != 0; numBlocks--, data++)
+  {
+    UInt32 numRounds2 = *(const UInt32 *)(p + 1) - 1;
+    const __m128i *w = p;
+    __m128i m;
+    ctr = _mm_add_epi64(ctr, one);
+    m = _mm_xor_si128(ctr, p[2]);
+    w += 3;
+    do
+    {
+      m = _mm_aesenc_si128(m, w[0]);
+      m = _mm_aesenc_si128(m, w[1]);
+      w += 2;
+    }
+    while (--numRounds2 != 0);
+    m = _mm_aesenc_si128(m, w[0]);
+    m = _mm_aesenclast_si128(m, w[1]);
+    *data = _mm_xor_si128(*data, m);
+  }
+  *p = ctr;
+}
+
+#else
+
+void MY_FAST_CALL AesCbc_Encode(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCbc_Decode(UInt32 *ivAes, Byte *data, size_t numBlocks);
+void MY_FAST_CALL AesCtr_Code(UInt32 *ivAes, Byte *data, size_t numBlocks);
+
+void MY_FAST_CALL AesCbc_Encode_Intel(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  AesCbc_Encode(p, data, numBlocks);
+}
+
+void MY_FAST_CALL AesCbc_Decode_Intel(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  AesCbc_Decode(p, data, numBlocks);
+}
+
+void MY_FAST_CALL AesCtr_Code_Intel(UInt32 *p, Byte *data, size_t numBlocks)
+{
+  AesCtr_Code(p, data, numBlocks);
+}
+
+#endif
@@ -0,0 +1,455 @@
+/* Alloc.c -- Memory allocation functions
+2018-04-27 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <stdio.h>
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+#include <stdlib.h>
+
+#include "Alloc.h"
+
+/* #define _SZ_ALLOC_DEBUG */
+
+/* use _SZ_ALLOC_DEBUG to debug alloc/free operations */
+#ifdef _SZ_ALLOC_DEBUG
+
+#include <stdio.h>
+int g_allocCount = 0;
+int g_allocCountMid = 0;
+int g_allocCountBig = 0;
+
+
+#define CONVERT_INT_TO_STR(charType, tempSize) \
+  unsigned char temp[tempSize]; unsigned i = 0; \
+  while (val >= 10) { temp[i++] = (unsigned char)('0' + (unsigned)(val % 10)); val /= 10; } \
+  *s++ = (charType)('0' + (unsigned)val); \
+  while (i != 0) { i--; *s++ = temp[i]; } \
+  *s = 0;
+
+static void ConvertUInt64ToString(UInt64 val, char *s)
+{
+  CONVERT_INT_TO_STR(char, 24);
+}
+
+#define GET_HEX_CHAR(t) ((char)(((t < 10) ? ('0' + t) : ('A' + (t - 10)))))
+
+static void ConvertUInt64ToHex(UInt64 val, char *s)
+{
+  UInt64 v = val;
+  unsigned i;
+  for (i = 1;; i++)
+  {
+    v >>= 4;
+    if (v == 0)
+      break;
+  }
+  s[i] = 0;
+  do
+  {
+    unsigned t = (unsigned)(val & 0xF);
+    val >>= 4;
+    s[--i] = GET_HEX_CHAR(t);
+  }
+  while (i);
+}
+
+#define DEBUG_OUT_STREAM stderr
+
+static void Print(const char *s)
+{
+  fputs(s, DEBUG_OUT_STREAM);
+}
+
+static void PrintAligned(const char *s, size_t align)
+{
+  size_t len = strlen(s);
+  for(;;)
+  {
+    fputc(' ', DEBUG_OUT_STREAM);
+    if (len >= align)
+      break;
+    ++len;
+  }
+  Print(s);
+}
+
+static void PrintLn()
+{
+  Print("\n");
+}
+
+static void PrintHex(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToHex(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintDec(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToString(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintAddr(void *p)
+{
+  PrintHex((UInt64)(size_t)(ptrdiff_t)p, 12);
+}
+
+
+#define PRINT_ALLOC(name, cnt, size, ptr) \
+    Print(name " "); \
+    PrintDec(cnt++, 10); \
+    PrintHex(size, 10); \
+    PrintAddr(ptr); \
+    PrintLn();
+ 
+#define PRINT_FREE(name, cnt, ptr) if (ptr) { \
+    Print(name " "); \
+    PrintDec(--cnt, 10); \
+    PrintAddr(ptr); \
+    PrintLn(); }
+ 
+#else
+
+#define PRINT_ALLOC(name, cnt, size, ptr)
+#define PRINT_FREE(name, cnt, ptr)
+#define Print(s)
+#define PrintLn()
+#define PrintHex(v, align)
+#define PrintDec(v, align)
+#define PrintAddr(p)
+
+#endif
+
+
+
+void *MyAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  #ifdef _SZ_ALLOC_DEBUG
+  {
+    void *p = malloc(size);
+    PRINT_ALLOC("Alloc    ", g_allocCount, size, p);
+    return p;
+  }
+  #else
+  return malloc(size);
+  #endif
+}
+
+void MyFree(void *address)
+{
+  PRINT_FREE("Free    ", g_allocCount, address);
+  
+  free(address);
+}
+
+#ifdef _WIN32
+
+void *MidAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  
+  PRINT_ALLOC("Alloc-Mid", g_allocCountMid, size, NULL);
+  
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void MidFree(void *address)
+{
+  PRINT_FREE("Free-Mid", g_allocCountMid, address);
+
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#ifndef MEM_LARGE_PAGES
+#undef _7ZIP_LARGE_PAGES
+#endif
+
+#ifdef _7ZIP_LARGE_PAGES
+SIZE_T g_LargePageSize = 0;
+typedef SIZE_T (WINAPI *GetLargePageMinimumP)();
+#endif
+
+void SetLargePageSize()
+{
+  #ifdef _7ZIP_LARGE_PAGES
+  SIZE_T size;
+  GetLargePageMinimumP largePageMinimum = (GetLargePageMinimumP)
+        GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "GetLargePageMinimum");
+  if (!largePageMinimum)
+    return;
+  size = largePageMinimum();
+  if (size == 0 || (size & (size - 1)) != 0)
+    return;
+  g_LargePageSize = size;
+  #endif
+}
+
+
+void *BigAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+
+  PRINT_ALLOC("Alloc-Big", g_allocCountBig, size, NULL);
+  
+  #ifdef _7ZIP_LARGE_PAGES
+  {
+    SIZE_T ps = g_LargePageSize;
+    if (ps != 0 && ps <= (1 << 30) && size > (ps / 2))
+    {
+      size_t size2;
+      ps--;
+      size2 = (size + ps) & ~ps;
+      if (size2 >= size)
+      {
+        void *res = VirtualAlloc(NULL, size2, MEM_COMMIT | MEM_LARGE_PAGES, PAGE_READWRITE);
+        if (res)
+          return res;
+      }
+    }
+  }
+  #endif
+
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void BigFree(void *address)
+{
+  PRINT_FREE("Free-Big", g_allocCountBig, address);
+  
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#endif
+
+
+static void *SzAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MyAlloc(size); }
+static void SzFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MyFree(address); }
+const ISzAlloc g_Alloc = { SzAlloc, SzFree };
+
+static void *SzMidAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MidAlloc(size); }
+static void SzMidFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MidFree(address); }
+const ISzAlloc g_MidAlloc = { SzMidAlloc, SzMidFree };
+
+static void *SzBigAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return BigAlloc(size); }
+static void SzBigFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); BigFree(address); }
+const ISzAlloc g_BigAlloc = { SzBigAlloc, SzBigFree };
+
+
+/*
+  uintptr_t : <stdint.h> C99 (optional)
+            : unsupported in VS6
+*/
+
+#ifdef _WIN32
+  typedef UINT_PTR UIntPtr;
+#else
+  /*
+  typedef uintptr_t UIntPtr;
+  */
+  typedef ptrdiff_t UIntPtr;
+#endif
+
+
+#define ADJUST_ALLOC_SIZE 0
+/*
+#define ADJUST_ALLOC_SIZE (sizeof(void *) - 1)
+*/
+/*
+  Use (ADJUST_ALLOC_SIZE = (sizeof(void *) - 1)), if
+     MyAlloc() can return address that is NOT multiple of sizeof(void *).
+*/
+
+
+/*
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((char *)(p) - ((size_t)(UIntPtr)(p) & ((align) - 1))))
+*/
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((((UIntPtr)(p)) & ~((UIntPtr)(align) - 1))))
+
+#define MY_ALIGN_PTR_UP_PLUS(p, align) MY_ALIGN_PTR_DOWN(((char *)(p) + (align) + ADJUST_ALLOC_SIZE), align)
+
+
+#if (_POSIX_C_SOURCE >= 200112L) && !defined(_WIN32)
+  #define USE_posix_memalign
+#endif
+
+/*
+  This posix_memalign() is for test purposes only.
+  We also need special Free() function instead of free(),
+  if this posix_memalign() is used.
+*/
+
+/*
+static int posix_memalign(void **ptr, size_t align, size_t size)
+{
+  size_t newSize = size + align;
+  void *p;
+  void *pAligned;
+  *ptr = NULL;
+  if (newSize < size)
+    return 12; // ENOMEM
+  p = MyAlloc(newSize);
+  if (!p)
+    return 12; // ENOMEM
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, align);
+  ((void **)pAligned)[-1] = p;
+  *ptr = pAligned;
+  return 0;
+}
+*/
+
+/*
+  ALLOC_ALIGN_SIZE >= sizeof(void *)
+  ALLOC_ALIGN_SIZE >= cache_line_size
+*/
+
+#define ALLOC_ALIGN_SIZE ((size_t)1 << 7)
+
+static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
+{
+  #ifndef USE_posix_memalign
+  
+  void *p;
+  void *pAligned;
+  size_t newSize;
+  UNUSED_VAR(pp);
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+
+  newSize = size + ALLOC_ALIGN_SIZE * 1 + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  p = MyAlloc(newSize);
+  
+  if (!p)
+    return NULL;
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, ALLOC_ALIGN_SIZE);
+
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(p);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  ((void **)pAligned)[-1] = p;
+
+  return pAligned;
+
+  #else
+
+  void *p;
+  UNUSED_VAR(pp);
+  if (posix_memalign(&p, ALLOC_ALIGN_SIZE, size))
+    return NULL;
+
+  Print(" posix_memalign="); PrintAddr(p);
+  PrintLn();
+
+  return p;
+
+  #endif
+}
+
+
+static void SzAlignedFree(ISzAllocPtr pp, void *address)
+{
+  UNUSED_VAR(pp);
+  #ifndef USE_posix_memalign
+  if (address)
+    MyFree(((void **)address)[-1]);
+  #else
+  free(address);
+  #endif
+}
+
+
+const ISzAlloc g_AlignedAlloc = { SzAlignedAlloc, SzAlignedFree };
+
+
+
+#define MY_ALIGN_PTR_DOWN_1(p) MY_ALIGN_PTR_DOWN(p, sizeof(void *))
+
+/* we align ptr to support cases where CAlignOffsetAlloc::offset is not multiply of sizeof(void *) */
+#define REAL_BLOCK_PTR_VAR(p) ((void **)MY_ALIGN_PTR_DOWN_1(p))[-1]
+/*
+#define REAL_BLOCK_PTR_VAR(p) ((void **)(p))[-1]
+*/
+
+static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
+{
+  CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+  void *adr;
+  void *pAligned;
+  size_t newSize;
+  size_t extra;
+  size_t alignSize = (size_t)1 << p->numAlignBits;
+
+  if (alignSize < sizeof(void *))
+    alignSize = sizeof(void *);
+  
+  if (p->offset >= alignSize)
+    return NULL;
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+  extra = p->offset & (sizeof(void *) - 1);
+  newSize = size + alignSize + extra + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  adr = ISzAlloc_Alloc(p->baseAlloc, newSize);
+  
+  if (!adr)
+    return NULL;
+
+  pAligned = (char *)MY_ALIGN_PTR_DOWN((char *)adr +
+      alignSize - p->offset + extra + ADJUST_ALLOC_SIZE, alignSize) + p->offset;
+
+  PrintLn();
+  Print("- Aligned: ");
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(adr);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  REAL_BLOCK_PTR_VAR(pAligned) = adr;
+
+  return pAligned;
+}
+
+
+static void AlignOffsetAlloc_Free(ISzAllocPtr pp, void *address)
+{
+  if (address)
+  {
+    CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+    PrintLn();
+    Print("- Aligned Free: ");
+    PrintLn();
+    ISzAlloc_Free(p->baseAlloc, REAL_BLOCK_PTR_VAR(address));
+  }
+}
+
+
+void AlignOffsetAlloc_CreateVTable(CAlignOffsetAlloc *p)
+{
+  p->vt.Alloc = AlignOffsetAlloc_Alloc;
+  p->vt.Free = AlignOffsetAlloc_Free;
+}
@@ -0,0 +1,51 @@
+/* Alloc.h -- Memory allocation functions
+2018-02-19 : Igor Pavlov : Public domain */
+
+#ifndef __COMMON_ALLOC_H
+#define __COMMON_ALLOC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+void *MyAlloc(size_t size);
+void MyFree(void *address);
+
+#ifdef _WIN32
+
+void SetLargePageSize();
+
+void *MidAlloc(size_t size);
+void MidFree(void *address);
+void *BigAlloc(size_t size);
+void BigFree(void *address);
+
+#else
+
+#define MidAlloc(size) MyAlloc(size)
+#define MidFree(address) MyFree(address)
+#define BigAlloc(size) MyAlloc(size)
+#define BigFree(address) MyFree(address)
+
+#endif
+
+extern const ISzAlloc g_Alloc;
+extern const ISzAlloc g_BigAlloc;
+extern const ISzAlloc g_MidAlloc;
+extern const ISzAlloc g_AlignedAlloc;
+
+
+typedef struct
+{
+  ISzAlloc vt;
+  ISzAllocPtr baseAlloc;
+  unsigned numAlignBits; /* ((1 << numAlignBits) >= sizeof(void *)) */
+  size_t offset;         /* (offset == (k * sizeof(void *)) && offset < (1 << numAlignBits) */
+} CAlignOffsetAlloc;
+
+void AlignOffsetAlloc_CreateVTable(CAlignOffsetAlloc *p);
+
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,257 @@
+/* Bcj2.c -- BCJ2 Decoder (Converter for x86 code)
+2018-04-28 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bcj2.h"
+#include "CpuArch.h"
+
+#define CProb UInt16
+
+#define kTopValue ((UInt32)1 << 24)
+#define kNumModelBits 11
+#define kBitModelTotal (1 << kNumModelBits)
+#define kNumMoveBits 5
+
+#define _IF_BIT_0 ttt = *prob; bound = (p->range >> kNumModelBits) * ttt; if (p->code < bound)
+#define _UPDATE_0 p->range = bound; *prob = (CProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
+#define _UPDATE_1 p->range -= bound; p->code -= bound; *prob = (CProb)(ttt - (ttt >> kNumMoveBits));
+
+void Bcj2Dec_Init(CBcj2Dec *p)
+{
+  unsigned i;
+
+  p->state = BCJ2_DEC_STATE_OK;
+  p->ip = 0;
+  p->temp[3] = 0;
+  p->range = 0;
+  p->code = 0;
+  for (i = 0; i < sizeof(p->probs) / sizeof(p->probs[0]); i++)
+    p->probs[i] = kBitModelTotal >> 1;
+}
+
+SRes Bcj2Dec_Decode(CBcj2Dec *p)
+{
+  if (p->range <= 5)
+  {
+    p->state = BCJ2_DEC_STATE_OK;
+    for (; p->range != 5; p->range++)
+    {
+      if (p->range == 1 && p->code != 0)
+        return SZ_ERROR_DATA;
+      
+      if (p->bufs[BCJ2_STREAM_RC] == p->lims[BCJ2_STREAM_RC])
+      {
+        p->state = BCJ2_STREAM_RC;
+        return SZ_OK;
+      }
+
+      p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+    }
+    
+    if (p->code == 0xFFFFFFFF)
+      return SZ_ERROR_DATA;
+    
+    p->range = 0xFFFFFFFF;
+  }
+  else if (p->state >= BCJ2_DEC_STATE_ORIG_0)
+  {
+    while (p->state <= BCJ2_DEC_STATE_ORIG_3)
+    {
+      Byte *dest = p->dest;
+      if (dest == p->destLim)
+        return SZ_OK;
+      *dest = p->temp[(size_t)p->state - BCJ2_DEC_STATE_ORIG_0];
+      p->state++;
+      p->dest = dest + 1;
+    }
+  }
+
+  /*
+  if (BCJ2_IS_32BIT_STREAM(p->state))
+  {
+    const Byte *cur = p->bufs[p->state];
+    if (cur == p->lims[p->state])
+      return SZ_OK;
+    p->bufs[p->state] = cur + 4;
+    
+    {
+      UInt32 val;
+      Byte *dest;
+      SizeT rem;
+      
+      p->ip += 4;
+      val = GetBe32(cur) - p->ip;
+      dest = p->dest;
+      rem = p->destLim - dest;
+      if (rem < 4)
+      {
+        SizeT i;
+        SetUi32(p->temp, val);
+        for (i = 0; i < rem; i++)
+          dest[i] = p->temp[i];
+        p->dest = dest + rem;
+        p->state = BCJ2_DEC_STATE_ORIG_0 + (unsigned)rem;
+        return SZ_OK;
+      }
+      SetUi32(dest, val);
+      p->temp[3] = (Byte)(val >> 24);
+      p->dest = dest + 4;
+      p->state = BCJ2_DEC_STATE_OK;
+    }
+  }
+  */
+
+  for (;;)
+  {
+    if (BCJ2_IS_32BIT_STREAM(p->state))
+      p->state = BCJ2_DEC_STATE_OK;
+    else
+    {
+      if (p->range < kTopValue)
+      {
+        if (p->bufs[BCJ2_STREAM_RC] == p->lims[BCJ2_STREAM_RC])
+        {
+          p->state = BCJ2_STREAM_RC;
+          return SZ_OK;
+        }
+        p->range <<= 8;
+        p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+      }
+
+      {
+        const Byte *src = p->bufs[BCJ2_STREAM_MAIN];
+        const Byte *srcLim;
+        Byte *dest;
+        SizeT num = p->lims[BCJ2_STREAM_MAIN] - src;
+        
+        if (num == 0)
+        {
+          p->state = BCJ2_STREAM_MAIN;
+          return SZ_OK;
+        }
+        
+        dest = p->dest;
+        if (num > (SizeT)(p->destLim - dest))
+        {
+          num = p->destLim - dest;
+          if (num == 0)
+          {
+            p->state = BCJ2_DEC_STATE_ORIG;
+            return SZ_OK;
+          }
+        }
+       
+        srcLim = src + num;
+
+        if (p->temp[3] == 0x0F && (src[0] & 0xF0) == 0x80)
+          *dest = src[0];
+        else for (;;)
+        {
+          Byte b = *src;
+          *dest = b;
+          if (b != 0x0F)
+          {
+            if ((b & 0xFE) == 0xE8)
+              break;
+            dest++;
+            if (++src != srcLim)
+              continue;
+            break;
+          }
+          dest++;
+          if (++src == srcLim)
+            break;
+          if ((*src & 0xF0) != 0x80)
+            continue;
+          *dest = *src;
+          break;
+        }
+        
+        num = src - p->bufs[BCJ2_STREAM_MAIN];
+        
+        if (src == srcLim)
+        {
+          p->temp[3] = src[-1];
+          p->bufs[BCJ2_STREAM_MAIN] = src;
+          p->ip += (UInt32)num;
+          p->dest += num;
+          p->state =
+            p->bufs[BCJ2_STREAM_MAIN] ==
+            p->lims[BCJ2_STREAM_MAIN] ?
+              (unsigned)BCJ2_STREAM_MAIN :
+              (unsigned)BCJ2_DEC_STATE_ORIG;
+          return SZ_OK;
+        }
+        
+        {
+          UInt32 bound, ttt;
+          CProb *prob;
+          Byte b = src[0];
+          Byte prev = (Byte)(num == 0 ? p->temp[3] : src[-1]);
+          
+          p->temp[3] = b;
+          p->bufs[BCJ2_STREAM_MAIN] = src + 1;
+          num++;
+          p->ip += (UInt32)num;
+          p->dest += num;
+          
+          prob = p->probs + (unsigned)(b == 0xE8 ? 2 + (unsigned)prev : (b == 0xE9 ? 1 : 0));
+          
+          _IF_BIT_0
+          {
+            _UPDATE_0
+            continue;
+          }
+          _UPDATE_1
+            
+        }
+      }
+    }
+
+    {
+      UInt32 val;
+      unsigned cj = (p->temp[3] == 0xE8) ? BCJ2_STREAM_CALL : BCJ2_STREAM_JUMP;
+      const Byte *cur = p->bufs[cj];
+      Byte *dest;
+      SizeT rem;
+      
+      if (cur == p->lims[cj])
+      {
+        p->state = cj;
+        break;
+      }
+      
+      val = GetBe32(cur);
+      p->bufs[cj] = cur + 4;
+
+      p->ip += 4;
+      val -= p->ip;
+      dest = p->dest;
+      rem = p->destLim - dest;
+      
+      if (rem < 4)
+      {
+        p->temp[0] = (Byte)val; if (rem > 0) dest[0] = (Byte)val; val >>= 8;
+        p->temp[1] = (Byte)val; if (rem > 1) dest[1] = (Byte)val; val >>= 8;
+        p->temp[2] = (Byte)val; if (rem > 2) dest[2] = (Byte)val; val >>= 8;
+        p->temp[3] = (Byte)val;
+        p->dest = dest + rem;
+        p->state = BCJ2_DEC_STATE_ORIG_0 + (unsigned)rem;
+        break;
+      }
+      
+      SetUi32(dest, val);
+      p->temp[3] = (Byte)(val >> 24);
+      p->dest = dest + 4;
+    }
+  }
+
+  if (p->range < kTopValue && p->bufs[BCJ2_STREAM_RC] != p->lims[BCJ2_STREAM_RC])
+  {
+    p->range <<= 8;
+    p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+  }
+
+  return SZ_OK;
+}
@@ -0,0 +1,146 @@
+/* Bcj2.h -- BCJ2 Converter for x86 code
+2014-11-10 : Igor Pavlov : Public domain */
+
+#ifndef __BCJ2_H
+#define __BCJ2_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define BCJ2_NUM_STREAMS 4
+
+enum
+{
+  BCJ2_STREAM_MAIN,
+  BCJ2_STREAM_CALL,
+  BCJ2_STREAM_JUMP,
+  BCJ2_STREAM_RC
+};
+
+enum
+{
+  BCJ2_DEC_STATE_ORIG_0 = BCJ2_NUM_STREAMS,
+  BCJ2_DEC_STATE_ORIG_1,
+  BCJ2_DEC_STATE_ORIG_2,
+  BCJ2_DEC_STATE_ORIG_3,
+  
+  BCJ2_DEC_STATE_ORIG,
+  BCJ2_DEC_STATE_OK
+};
+
+enum
+{
+  BCJ2_ENC_STATE_ORIG = BCJ2_NUM_STREAMS,
+  BCJ2_ENC_STATE_OK
+};
+
+
+#define BCJ2_IS_32BIT_STREAM(s) ((s) == BCJ2_STREAM_CALL || (s) == BCJ2_STREAM_JUMP)
+
+/*
+CBcj2Dec / CBcj2Enc
+bufs sizes:
+  BUF_SIZE(n) = lims[n] - bufs[n]
+bufs sizes for BCJ2_STREAM_CALL and BCJ2_STREAM_JUMP must be mutliply of 4:
+    (BUF_SIZE(BCJ2_STREAM_CALL) & 3) == 0
+    (BUF_SIZE(BCJ2_STREAM_JUMP) & 3) == 0
+*/
+
+/*
+CBcj2Dec:
+dest is allowed to overlap with bufs[BCJ2_STREAM_MAIN], with the following conditions:
+  bufs[BCJ2_STREAM_MAIN] >= dest &&
+  bufs[BCJ2_STREAM_MAIN] - dest >= tempReserv +
+        BUF_SIZE(BCJ2_STREAM_CALL) +
+        BUF_SIZE(BCJ2_STREAM_JUMP)
+     tempReserv = 0 : for first call of Bcj2Dec_Decode
+     tempReserv = 4 : for any other calls of Bcj2Dec_Decode
+  overlap with offset = 1 is not allowed
+*/
+
+typedef struct
+{
+  const Byte *bufs[BCJ2_NUM_STREAMS];
+  const Byte *lims[BCJ2_NUM_STREAMS];
+  Byte *dest;
+  const Byte *destLim;
+
+  unsigned state; /* BCJ2_STREAM_MAIN has more priority than BCJ2_STATE_ORIG */
+
+  UInt32 ip;
+  Byte temp[4];
+  UInt32 range;
+  UInt32 code;
+  UInt16 probs[2 + 256];
+} CBcj2Dec;
+
+void Bcj2Dec_Init(CBcj2Dec *p);
+
+/* Returns: SZ_OK or SZ_ERROR_DATA */
+SRes Bcj2Dec_Decode(CBcj2Dec *p);
+
+#define Bcj2Dec_IsFinished(_p_) ((_p_)->code == 0)
+
+
+
+typedef enum
+{
+  BCJ2_ENC_FINISH_MODE_CONTINUE,
+  BCJ2_ENC_FINISH_MODE_END_BLOCK,
+  BCJ2_ENC_FINISH_MODE_END_STREAM
+} EBcj2Enc_FinishMode;
+
+typedef struct
+{
+  Byte *bufs[BCJ2_NUM_STREAMS];
+  const Byte *lims[BCJ2_NUM_STREAMS];
+  const Byte *src;
+  const Byte *srcLim;
+
+  unsigned state;
+  EBcj2Enc_FinishMode finishMode;
+
+  Byte prevByte;
+
+  Byte cache;
+  UInt32 range;
+  UInt64 low;
+  UInt64 cacheSize;
+
+  UInt32 ip;
+
+  /* 32-bit ralative offset in JUMP/CALL commands is
+       - (mod 4 GB)   in 32-bit mode
+       - signed Int32 in 64-bit mode
+     We use (mod 4 GB) check for fileSize.
+     Use fileSize up to 2 GB, if you want to support 32-bit and 64-bit code conversion. */
+  UInt32 fileIp;
+  UInt32 fileSize;    /* (fileSize <= ((UInt32)1 << 31)), 0 means no_limit */
+  UInt32 relatLimit;  /* (relatLimit <= ((UInt32)1 << 31)), 0 means desable_conversion */
+
+  UInt32 tempTarget;
+  unsigned tempPos;
+  Byte temp[4 * 2];
+
+  unsigned flushPos;
+  
+  UInt16 probs[2 + 256];
+} CBcj2Enc;
+
+void Bcj2Enc_Init(CBcj2Enc *p);
+void Bcj2Enc_Encode(CBcj2Enc *p);
+
+#define Bcj2Enc_Get_InputData_Size(p) ((SizeT)((p)->srcLim - (p)->src) + (p)->tempPos)
+#define Bcj2Enc_IsFinished(p) ((p)->flushPos == 5)
+
+
+#define BCJ2_RELAT_LIMIT_NUM_BITS 26
+#define BCJ2_RELAT_LIMIT ((UInt32)1 << BCJ2_RELAT_LIMIT_NUM_BITS)
+
+/* limit for CBcj2Enc::fileSize variable */
+#define BCJ2_FileSize_MAX ((UInt32)1 << 31)
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,311 @@
+/* Bcj2Enc.c -- BCJ2 Encoder (Converter for x86 code)
+2019-02-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+/* #define SHOW_STAT */
+
+#ifdef SHOW_STAT
+#include <stdio.h>
+#define PRF(x) x
+#else
+#define PRF(x)
+#endif
+
+#include <string.h>
+
+#include "Bcj2.h"
+#include "CpuArch.h"
+
+#define CProb UInt16
+
+#define kTopValue ((UInt32)1 << 24)
+#define kNumModelBits 11
+#define kBitModelTotal (1 << kNumModelBits)
+#define kNumMoveBits 5
+
+void Bcj2Enc_Init(CBcj2Enc *p)
+{
+  unsigned i;
+
+  p->state = BCJ2_ENC_STATE_OK;
+  p->finishMode = BCJ2_ENC_FINISH_MODE_CONTINUE;
+
+  p->prevByte = 0;
+
+  p->cache = 0;
+  p->range = 0xFFFFFFFF;
+  p->low = 0;
+  p->cacheSize = 1;
+
+  p->ip = 0;
+
+  p->fileIp = 0;
+  p->fileSize = 0;
+  p->relatLimit = BCJ2_RELAT_LIMIT;
+
+  p->tempPos = 0;
+
+  p->flushPos = 0;
+
+  for (i = 0; i < sizeof(p->probs) / sizeof(p->probs[0]); i++)
+    p->probs[i] = kBitModelTotal >> 1;
+}
+
+static BoolInt MY_FAST_CALL RangeEnc_ShiftLow(CBcj2Enc *p)
+{
+  if ((UInt32)p->low < (UInt32)0xFF000000 || (UInt32)(p->low >> 32) != 0)
+  {
+    Byte *buf = p->bufs[BCJ2_STREAM_RC];
+    do
+    {
+      if (buf == p->lims[BCJ2_STREAM_RC])
+      {
+        p->state = BCJ2_STREAM_RC;
+        p->bufs[BCJ2_STREAM_RC] = buf;
+        return True;
+      }
+      *buf++ = (Byte)(p->cache + (Byte)(p->low >> 32));
+      p->cache = 0xFF;
+    }
+    while (--p->cacheSize);
+    p->bufs[BCJ2_STREAM_RC] = buf;
+    p->cache = (Byte)((UInt32)p->low >> 24);
+  }
+  p->cacheSize++;
+  p->low = (UInt32)p->low << 8;
+  return False;
+}
+
+static void Bcj2Enc_Encode_2(CBcj2Enc *p)
+{
+  if (BCJ2_IS_32BIT_STREAM(p->state))
+  {
+    Byte *cur = p->bufs[p->state];
+    if (cur == p->lims[p->state])
+      return;
+    SetBe32(cur, p->tempTarget);
+    p->bufs[p->state] = cur + 4;
+  }
+
+  p->state = BCJ2_ENC_STATE_ORIG;
+
+  for (;;)
+  {
+    if (p->range < kTopValue)
+    {
+      if (RangeEnc_ShiftLow(p))
+        return;
+      p->range <<= 8;
+    }
+
+    {
+      {
+        const Byte *src = p->src;
+        const Byte *srcLim;
+        Byte *dest;
+        SizeT num = p->srcLim - src;
+
+        if (p->finishMode == BCJ2_ENC_FINISH_MODE_CONTINUE)
+        {
+          if (num <= 4)
+            return;
+          num -= 4;
+        }
+        else if (num == 0)
+          break;
+
+        dest = p->bufs[BCJ2_STREAM_MAIN];
+        if (num > (SizeT)(p->lims[BCJ2_STREAM_MAIN] - dest))
+        {
+          num = p->lims[BCJ2_STREAM_MAIN] - dest;
+          if (num == 0)
+          {
+            p->state = BCJ2_STREAM_MAIN;
+            return;
+          }
+        }
+       
+        srcLim = src + num;
+
+        if (p->prevByte == 0x0F && (src[0] & 0xF0) == 0x80)
+          *dest = src[0];
+        else for (;;)
+        {
+          Byte b = *src;
+          *dest = b;
+          if (b != 0x0F)
+          {
+            if ((b & 0xFE) == 0xE8)
+              break;
+            dest++;
+            if (++src != srcLim)
+              continue;
+            break;
+          }
+          dest++;
+          if (++src == srcLim)
+            break;
+          if ((*src & 0xF0) != 0x80)
+            continue;
+          *dest = *src;
+          break;
+        }
+        
+        num = src - p->src;
+        
+        if (src == srcLim)
+        {
+          p->prevByte = src[-1];
+          p->bufs[BCJ2_STREAM_MAIN] = dest;
+          p->src = src;
+          p->ip += (UInt32)num;
+          continue;
+        }
+ 
+        {
+          Byte context = (Byte)(num == 0 ? p->prevByte : src[-1]);
+          BoolInt needConvert;
+
+          p->bufs[BCJ2_STREAM_MAIN] = dest + 1;
+          p->ip += (UInt32)num + 1;
+          src++;
+          
+          needConvert = False;
+
+          if ((SizeT)(p->srcLim - src) >= 4)
+          {
+            UInt32 relatVal = GetUi32(src);
+            if ((p->fileSize == 0 || (UInt32)(p->ip + 4 + relatVal - p->fileIp) < p->fileSize)
+                && ((relatVal + p->relatLimit) >> 1) < p->relatLimit)
+              needConvert = True;
+          }
+
+          {
+            UInt32 bound;
+            unsigned ttt;
+            Byte b = src[-1];
+            CProb *prob = p->probs + (unsigned)(b == 0xE8 ? 2 + (unsigned)context : (b == 0xE9 ? 1 : 0));
+
+            ttt = *prob;
+            bound = (p->range >> kNumModelBits) * ttt;
+            
+            if (!needConvert)
+            {
+              p->range = bound;
+              *prob = (CProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
+              p->src = src;
+              p->prevByte = b;
+              continue;
+            }
+            
+            p->low += bound;
+            p->range -= bound;
+            *prob = (CProb)(ttt - (ttt >> kNumMoveBits));
+
+            {
+              UInt32 relatVal = GetUi32(src);
+              UInt32 absVal;
+              p->ip += 4;
+              absVal = p->ip + relatVal;
+              p->prevByte = src[3];
+              src += 4;
+              p->src = src;
+              {
+                unsigned cj = (b == 0xE8) ? BCJ2_STREAM_CALL : BCJ2_STREAM_JUMP;
+                Byte *cur = p->bufs[cj];
+                if (cur == p->lims[cj])
+                {
+                  p->state = cj;
+                  p->tempTarget = absVal;
+                  return;
+                }
+                SetBe32(cur, absVal);
+                p->bufs[cj] = cur + 4;
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+
+  if (p->finishMode != BCJ2_ENC_FINISH_MODE_END_STREAM)
+    return;
+
+  for (; p->flushPos < 5; p->flushPos++)
+    if (RangeEnc_ShiftLow(p))
+      return;
+  p->state = BCJ2_ENC_STATE_OK;
+}
+
+
+void Bcj2Enc_Encode(CBcj2Enc *p)
+{
+  PRF(printf("\n"));
+  PRF(printf("---- ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+  if (p->tempPos != 0)
+  {
+    unsigned extra = 0;
+   
+    for (;;)
+    {
+      const Byte *src = p->src;
+      const Byte *srcLim = p->srcLim;
+      EBcj2Enc_FinishMode finishMode = p->finishMode;
+      
+      p->src = p->temp;
+      p->srcLim = p->temp + p->tempPos;
+      if (src != srcLim)
+        p->finishMode = BCJ2_ENC_FINISH_MODE_CONTINUE;
+      
+      PRF(printf("     ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+      Bcj2Enc_Encode_2(p);
+      
+      {
+        unsigned num = (unsigned)(p->src - p->temp);
+        unsigned tempPos = p->tempPos - num;
+        unsigned i;
+        p->tempPos = tempPos;
+        for (i = 0; i < tempPos; i++)
+          p->temp[i] = p->temp[(size_t)i + num];
+      
+        p->src = src;
+        p->srcLim = srcLim;
+        p->finishMode = finishMode;
+        
+        if (p->state != BCJ2_ENC_STATE_ORIG || src == srcLim)
+          return;
+        
+        if (extra >= tempPos)
+        {
+          p->src = src - tempPos;
+          p->tempPos = 0;
+          break;
+        }
+        
+        p->temp[tempPos] = src[0];
+        p->tempPos = tempPos + 1;
+        p->src = src + 1;
+        extra++;
+      }
+    }
+  }
+
+  PRF(printf("++++ ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+  Bcj2Enc_Encode_2(p);
+  
+  if (p->state == BCJ2_ENC_STATE_ORIG)
+  {
+    const Byte *src = p->src;
+    unsigned rem = (unsigned)(p->srcLim - src);
+    unsigned i;
+    for (i = 0; i < rem; i++)
+      p->temp[i] = src[i];
+    p->tempPos = rem;
+    p->src = src + rem;
+  }
+}
@@ -0,0 +1,230 @@
+/* Bra.c -- Converters for RISC code
+2017-04-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+#include "Bra.h"
+
+SizeT ARM_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip += 4;
+  p = data;
+  lim = data + size;
+
+  if (encoding)
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return p - data;
+      p += 4;
+      if (p[-1] == 0xEB)
+        break;
+    }
+    {
+      UInt32 v = GetUi32(p - 4);
+      v <<= 2;
+        v += ip + (UInt32)(p - data);
+      v >>= 2;
+      v &= 0x00FFFFFF;
+      v |= 0xEB000000;
+      SetUi32(p - 4, v);
+    }
+  }
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return p - data;
+      p += 4;
+      if (p[-1] == 0xEB)
+        break;
+    }
+    {
+      UInt32 v = GetUi32(p - 4);
+      v <<= 2;
+        v -= ip + (UInt32)(p - data);
+      v >>= 2;
+      v &= 0x00FFFFFF;
+      v |= 0xEB000000;
+      SetUi32(p - 4, v);
+    }
+  }
+}
+
+
+SizeT ARMT_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)1;
+  p = data;
+  lim = data + size - 4;
+
+  if (encoding)
+  
+  for (;;)
+  {
+    UInt32 b1;
+    for (;;)
+    {
+      UInt32 b3;
+      if (p > lim)
+        return p - data;
+      b1 = p[1];
+      b3 = p[3];
+      p += 2;
+      b1 ^= 8;
+      if ((b3 & b1) >= 0xF8)
+        break;
+    }
+    {
+      UInt32 v =
+             ((UInt32)b1 << 19)
+          + (((UInt32)p[1] & 0x7) << 8)
+          + (((UInt32)p[-2] << 11))
+          + (p[0]);
+
+      p += 2;
+      {
+        UInt32 cur = (ip + (UInt32)(p - data)) >> 1;
+          v += cur;
+      }
+
+      p[-4] = (Byte)(v >> 11);
+      p[-3] = (Byte)(0xF0 | ((v >> 19) & 0x7));
+      p[-2] = (Byte)v;
+      p[-1] = (Byte)(0xF8 | (v >> 8));
+    }
+  }
+  
+  for (;;)
+  {
+    UInt32 b1;
+    for (;;)
+    {
+      UInt32 b3;
+      if (p > lim)
+        return p - data;
+      b1 = p[1];
+      b3 = p[3];
+      p += 2;
+      b1 ^= 8;
+      if ((b3 & b1) >= 0xF8)
+        break;
+    }
+    {
+      UInt32 v =
+             ((UInt32)b1 << 19)
+          + (((UInt32)p[1] & 0x7) << 8)
+          + (((UInt32)p[-2] << 11))
+          + (p[0]);
+
+      p += 2;
+      {
+        UInt32 cur = (ip + (UInt32)(p - data)) >> 1;
+          v -= cur;
+      }
+
+      /*
+      SetUi16(p - 4, (UInt16)(((v >> 11) & 0x7FF) | 0xF000));
+      SetUi16(p - 2, (UInt16)(v | 0xF800));
+      */
+      
+      p[-4] = (Byte)(v >> 11);
+      p[-3] = (Byte)(0xF0 | ((v >> 19) & 0x7));
+      p[-2] = (Byte)v;
+      p[-1] = (Byte)(0xF8 | (v >> 8));
+    }
+  }
+}
+
+
+SizeT PPC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip -= 4;
+  p = data;
+  lim = data + size;
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return p - data;
+      p += 4;
+      /* if ((v & 0xFC000003) == 0x48000001) */
+      if ((p[-4] & 0xFC) == 0x48 && (p[-1] & 3) == 1)
+        break;
+    }
+    {
+      UInt32 v = GetBe32(p - 4);
+      if (encoding)
+        v += ip + (UInt32)(p - data);
+      else
+        v -= ip + (UInt32)(p - data);
+      v &= 0x03FFFFFF;
+      v |= 0x48000000;
+      SetBe32(p - 4, v);
+    }
+  }
+}
+
+
+SizeT SPARC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip -= 4;
+  p = data;
+  lim = data + size;
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return p - data;
+      /*
+      v = GetBe32(p);
+      p += 4;
+      m = v + ((UInt32)5 << 29);
+      m ^= (UInt32)7 << 29;
+      m += (UInt32)1 << 22;
+      if ((m & ((UInt32)0x1FF << 23)) == 0)
+        break;
+      */
+      p += 4;
+      if ((p[-4] == 0x40 && (p[-3] & 0xC0) == 0) ||
+          (p[-4] == 0x7F && (p[-3] >= 0xC0)))
+        break;
+    }
+    {
+      UInt32 v = GetBe32(p - 4);
+      v <<= 2;
+      if (encoding)
+        v += ip + (UInt32)(p - data);
+      else
+        v -= ip + (UInt32)(p - data);
+      
+      v &= 0x01FFFFFF;
+      v -= (UInt32)1 << 24;
+      v ^= 0xFF000000;
+      v >>= 2;
+      v |= 0x40000000;
+      SetBe32(p - 4, v);
+    }
+  }
+}
@@ -0,0 +1,64 @@
+/* Bra.h -- Branch converters for executables
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __BRA_H
+#define __BRA_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/*
+These functions convert relative addresses to absolute addresses
+in CALL instructions to increase the compression ratio.
+  
+  In:
+    data     - data buffer
+    size     - size of data
+    ip       - current virtual Instruction Pinter (IP) value
+    state    - state variable for x86 converter
+    encoding - 0 (for decoding), 1 (for encoding)
+  
+  Out:
+    state    - state variable for x86 converter
+
+  Returns:
+    The number of processed bytes. If you call these functions with multiple calls,
+    you must start next call with first byte after block of processed bytes.
+  
+  Type   Endian  Alignment  LookAhead
+  
+  x86    little      1          4
+  ARMT   little      2          2
+  ARM    little      4          0
+  PPC     big        4          0
+  SPARC   big        4          0
+  IA64   little     16          0
+
+  size must be >= Alignment + LookAhead, if it's not last block.
+  If (size < Alignment + LookAhead), converter returns 0.
+
+  Example:
+
+    UInt32 ip = 0;
+    for ()
+    {
+      ; size must be >= Alignment + LookAhead, if it's not last block
+      SizeT processed = Convert(data, size, ip, 1);
+      data += processed;
+      size -= processed;
+      ip += processed;
+    }
+*/
+
+#define x86_Convert_Init(state) { state = 0; }
+SizeT x86_Convert(Byte *data, SizeT size, UInt32 ip, UInt32 *state, int encoding);
+SizeT ARM_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT ARMT_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT PPC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT SPARC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT IA64_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,82 @@
+/* Bra86.c -- Converter for x86 code (BCJ)
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bra.h"
+
+#define Test86MSByte(b) ((((b) + 1) & 0xFE) == 0)
+
+SizeT x86_Convert(Byte *data, SizeT size, UInt32 ip, UInt32 *state, int encoding)
+{
+  SizeT pos = 0;
+  UInt32 mask = *state & 7;
+  if (size < 5)
+    return 0;
+  size -= 4;
+  ip += 5;
+
+  for (;;)
+  {
+    Byte *p = data + pos;
+    const Byte *limit = data + size;
+    for (; p < limit; p++)
+      if ((*p & 0xFE) == 0xE8)
+        break;
+
+    {
+      SizeT d = (SizeT)(p - data - pos);
+      pos = (SizeT)(p - data);
+      if (p >= limit)
+      {
+        *state = (d > 2 ? 0 : mask >> (unsigned)d);
+        return pos;
+      }
+      if (d > 2)
+        mask = 0;
+      else
+      {
+        mask >>= (unsigned)d;
+        if (mask != 0 && (mask > 4 || mask == 3 || Test86MSByte(p[(size_t)(mask >> 1) + 1])))
+        {
+          mask = (mask >> 1) | 4;
+          pos++;
+          continue;
+        }
+      }
+    }
+
+    if (Test86MSByte(p[4]))
+    {
+      UInt32 v = ((UInt32)p[4] << 24) | ((UInt32)p[3] << 16) | ((UInt32)p[2] << 8) | ((UInt32)p[1]);
+      UInt32 cur = ip + (UInt32)pos;
+      pos += 5;
+      if (encoding)
+        v += cur;
+      else
+        v -= cur;
+      if (mask != 0)
+      {
+        unsigned sh = (mask & 6) << 2;
+        if (Test86MSByte((Byte)(v >> sh)))
+        {
+          v ^= (((UInt32)0x100 << sh) - 1);
+          if (encoding)
+            v += cur;
+          else
+            v -= cur;
+        }
+        mask = 0;
+      }
+      p[1] = (Byte)v;
+      p[2] = (Byte)(v >> 8);
+      p[3] = (Byte)(v >> 16);
+      p[4] = (Byte)(0 - ((v >> 24) & 1));
+    }
+    else
+    {
+      mask = (mask >> 1) | 4;
+      pos++;
+    }
+  }
+}
@@ -0,0 +1,53 @@
+/* BraIA64.c -- Converter for IA-64 code
+2017-01-26 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+#include "Bra.h"
+
+SizeT IA64_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  SizeT i;
+  if (size < 16)
+    return 0;
+  size -= 16;
+  i = 0;
+  do
+  {
+    unsigned m = ((UInt32)0x334B0000 >> (data[i] & 0x1E)) & 3;
+    if (m)
+    {
+      m++;
+      do
+      {
+        Byte *p = data + (i + (size_t)m * 5 - 8);
+        if (((p[3] >> m) & 15) == 5
+            && (((p[-1] | ((UInt32)p[0] << 8)) >> m) & 0x70) == 0)
+        {
+          unsigned raw = GetUi32(p);
+          unsigned v = raw >> m;
+          v = (v & 0xFFFFF) | ((v & (1 << 23)) >> 3);
+          
+          v <<= 4;
+          if (encoding)
+            v += ip + (UInt32)i;
+          else
+            v -= ip + (UInt32)i;
+          v >>= 4;
+          
+          v &= 0x1FFFFF;
+          v += 0x700000;
+          v &= 0x8FFFFF;
+          raw &= ~((UInt32)0x8FFFFF << m);
+          raw |= (v << m);
+          SetUi32(p, raw);
+        }
+      }
+      while (++m <= 4);
+    }
+    i += 16;
+  }
+  while (i <= size);
+  return i;
+}
@@ -0,0 +1,33 @@
+/* Compiler.h
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_COMPILER_H
+#define __7Z_COMPILER_H
+
+#ifdef _MSC_VER
+
+  #ifdef UNDER_CE
+    #define RPC_NO_WINDOWS_H
+    /* #pragma warning(disable : 4115) // '_RPC_ASYNC_STATE' : named type definition in parentheses */
+    #pragma warning(disable : 4201) // nonstandard extension used : nameless struct/union
+    #pragma warning(disable : 4214) // nonstandard extension used : bit field types other than int
+  #endif
+
+  #if _MSC_VER >= 1300
+    #pragma warning(disable : 4996) // This function or variable may be unsafe
+  #else
+    #pragma warning(disable : 4511) // copy constructor could not be generated
+    #pragma warning(disable : 4512) // assignment operator could not be generated
+    #pragma warning(disable : 4514) // unreferenced inline function has been removed
+    #pragma warning(disable : 4702) // unreachable code
+    #pragma warning(disable : 4710) // not inlined
+    #pragma warning(disable : 4714) // function marked as __forceinline not inlined
+    #pragma warning(disable : 4786) // identifier was truncated to '255' characters in the debug information
+  #endif
+
+#endif
+
+#define UNUSED_VAR(x) (void)x;
+/* #define UNUSED_VAR(x) x=x; */
+
+#endif
@@ -0,0 +1,218 @@
+/* CpuArch.c -- CPU specific code
+2018-02-18: Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+#if (defined(_MSC_VER) && !defined(MY_CPU_AMD64)) || defined(__GNUC__)
+#define USE_ASM
+#endif
+
+#if !defined(USE_ASM) && _MSC_VER >= 1500
+#include <intrin.h>
+#endif
+
+#if defined(USE_ASM) && !defined(MY_CPU_AMD64)
+static UInt32 CheckFlag(UInt32 flag)
+{
+  #ifdef _MSC_VER
+  __asm pushfd;
+  __asm pop EAX;
+  __asm mov EDX, EAX;
+  __asm xor EAX, flag;
+  __asm push EAX;
+  __asm popfd;
+  __asm pushfd;
+  __asm pop EAX;
+  __asm xor EAX, EDX;
+  __asm push EDX;
+  __asm popfd;
+  __asm and flag, EAX;
+  #else
+  __asm__ __volatile__ (
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "movl %%EAX,%%EDX\n\t"
+    "xorl %0,%%EAX\n\t"
+    "push %%EAX\n\t"
+    "popf\n\t"
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "xorl %%EDX,%%EAX\n\t"
+    "push %%EDX\n\t"
+    "popf\n\t"
+    "andl %%EAX, %0\n\t":
+    "=c" (flag) : "c" (flag) :
+    "%eax", "%edx");
+  #endif
+  return flag;
+}
+#define CHECK_CPUID_IS_SUPPORTED if (CheckFlag(1 << 18) == 0 || CheckFlag(1 << 21) == 0) return False;
+#else
+#define CHECK_CPUID_IS_SUPPORTED
+#endif
+
+void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d)
+{
+  #ifdef USE_ASM
+
+  #ifdef _MSC_VER
+
+  UInt32 a2, b2, c2, d2;
+  __asm xor EBX, EBX;
+  __asm xor ECX, ECX;
+  __asm xor EDX, EDX;
+  __asm mov EAX, function;
+  __asm cpuid;
+  __asm mov a2, EAX;
+  __asm mov b2, EBX;
+  __asm mov c2, ECX;
+  __asm mov d2, EDX;
+
+  *a = a2;
+  *b = b2;
+  *c = c2;
+  *d = d2;
+
+  #else
+
+  __asm__ __volatile__ (
+  #if defined(MY_CPU_AMD64) && defined(__PIC__)
+    "mov %%rbx, %%rdi;"
+    "cpuid;"
+    "xchg %%rbx, %%rdi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #elif defined(MY_CPU_X86) && defined(__PIC__)
+    "mov %%ebx, %%edi;"
+    "cpuid;"
+    "xchgl %%ebx, %%edi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #else
+    "cpuid"
+    : "=a" (*a) ,
+      "=b" (*b) ,
+  #endif
+      "=c" (*c) ,
+      "=d" (*d)
+    : "0" (function)) ;
+
+  #endif
+  
+  #else
+
+  int CPUInfo[4];
+  __cpuid(CPUInfo, function);
+  *a = CPUInfo[0];
+  *b = CPUInfo[1];
+  *c = CPUInfo[2];
+  *d = CPUInfo[3];
+
+  #endif
+}
+
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p)
+{
+  CHECK_CPUID_IS_SUPPORTED
+  MyCPUID(0, &p->maxFunc, &p->vendor[0], &p->vendor[2], &p->vendor[1]);
+  MyCPUID(1, &p->ver, &p->b, &p->c, &p->d);
+  return True;
+}
+
+static const UInt32 kVendors[][3] =
+{
+  { 0x756E6547, 0x49656E69, 0x6C65746E},
+  { 0x68747541, 0x69746E65, 0x444D4163},
+  { 0x746E6543, 0x48727561, 0x736C7561}
+};
+
+int x86cpuid_GetFirm(const Cx86cpuid *p)
+{
+  unsigned i;
+  for (i = 0; i < sizeof(kVendors) / sizeof(kVendors[i]); i++)
+  {
+    const UInt32 *v = kVendors[i];
+    if (v[0] == p->vendor[0] &&
+        v[1] == p->vendor[1] &&
+        v[2] == p->vendor[2])
+      return (int)i;
+  }
+  return -1;
+}
+
+BoolInt CPU_Is_InOrder()
+{
+  Cx86cpuid p;
+  int firm;
+  UInt32 family, model;
+  if (!x86cpuid_CheckAndRead(&p))
+    return True;
+
+  family = x86cpuid_GetFamily(p.ver);
+  model = x86cpuid_GetModel(p.ver);
+  
+  firm = x86cpuid_GetFirm(&p);
+
+  switch (firm)
+  {
+    case CPU_FIRM_INTEL: return (family < 6 || (family == 6 && (
+        /* In-Order Atom CPU */
+           model == 0x1C  /* 45 nm, N4xx, D4xx, N5xx, D5xx, 230, 330 */
+        || model == 0x26  /* 45 nm, Z6xx */
+        || model == 0x27  /* 32 nm, Z2460 */
+        || model == 0x35  /* 32 nm, Z2760 */
+        || model == 0x36  /* 32 nm, N2xxx, D2xxx */
+        )));
+    case CPU_FIRM_AMD: return (family < 5 || (family == 5 && (model < 6 || model == 0xA)));
+    case CPU_FIRM_VIA: return (family < 6 || (family == 6 && model < 0xF));
+  }
+  return True;
+}
+
+#if !defined(MY_CPU_AMD64) && defined(_WIN32)
+#include <windows.h>
+static BoolInt CPU_Sys_Is_SSE_Supported()
+{
+  OSVERSIONINFO vi;
+  vi.dwOSVersionInfoSize = sizeof(vi);
+  if (!GetVersionEx(&vi))
+    return False;
+  return (vi.dwMajorVersion >= 5);
+}
+#define CHECK_SYS_SSE_SUPPORT if (!CPU_Sys_Is_SSE_Supported()) return False;
+#else
+#define CHECK_SYS_SSE_SUPPORT
+#endif
+
+BoolInt CPU_Is_Aes_Supported()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_CheckAndRead(&p))
+    return False;
+  return (p.c >> 25) & 1;
+}
+
+BoolInt CPU_IsSupported_PageGB()
+{
+  Cx86cpuid cpuid;
+  if (!x86cpuid_CheckAndRead(&cpuid))
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000000, &d[0], &d[1], &d[2], &d[3]);
+    if (d[0] < 0x80000001)
+      return False;
+  }
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000001, &d[0], &d[1], &d[2], &d[3]);
+    return (d[3] >> 26) & 1;
+  }
+}
+
+#endif
@@ -0,0 +1,336 @@
+/* CpuArch.h -- CPU specific code
+2018-02-18 : Igor Pavlov : Public domain */
+
+#ifndef __CPU_ARCH_H
+#define __CPU_ARCH_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/*
+MY_CPU_LE means that CPU is LITTLE ENDIAN.
+MY_CPU_BE means that CPU is BIG ENDIAN.
+If MY_CPU_LE and MY_CPU_BE are not defined, we don't know about ENDIANNESS of platform.
+
+MY_CPU_LE_UNALIGN means that CPU is LITTLE ENDIAN and CPU supports unaligned memory accesses.
+*/
+
+#if  defined(_M_X64) \
+  || defined(_M_AMD64) \
+  || defined(__x86_64__) \
+  || defined(__AMD64__) \
+  || defined(__amd64__)
+  #define MY_CPU_AMD64
+  #ifdef __ILP32__
+    #define MY_CPU_NAME "x32"
+  #else
+    #define MY_CPU_NAME "x64"
+  #endif
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(_M_IX86) \
+  || defined(__i386__)
+  #define MY_CPU_X86
+  #define MY_CPU_NAME "x86"
+  #define MY_CPU_32BIT
+#endif
+
+
+#if  defined(_M_ARM64) \
+  || defined(__AARCH64EL__) \
+  || defined(__AARCH64EB__) \
+  || defined(__aarch64__)
+  #define MY_CPU_ARM64
+  #define MY_CPU_NAME "arm64"
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(_M_ARM) \
+  || defined(_M_ARM_NT) \
+  || defined(_M_ARMT) \
+  || defined(__arm__) \
+  || defined(__thumb__) \
+  || defined(__ARMEL__) \
+  || defined(__ARMEB__) \
+  || defined(__THUMBEL__) \
+  || defined(__THUMBEB__)
+  #define MY_CPU_ARM
+  #define MY_CPU_NAME "arm"
+  #define MY_CPU_32BIT
+#endif
+
+
+#if  defined(_M_IA64) \
+  || defined(__ia64__)
+  #define MY_CPU_IA64
+  #define MY_CPU_NAME "ia64"
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(__mips64) \
+  || defined(__mips64__) \
+  || (defined(__mips) && (__mips == 64 || __mips == 4 || __mips == 3))
+  #define MY_CPU_NAME "mips64"
+  #define MY_CPU_64BIT
+#elif defined(__mips__)
+  #define MY_CPU_NAME "mips"
+  /* #define MY_CPU_32BIT */
+#endif
+
+
+#if  defined(__ppc64__) \
+  || defined(__powerpc64__)
+  #ifdef __ILP32__
+    #define MY_CPU_NAME "ppc64-32"
+  #else
+    #define MY_CPU_NAME "ppc64"
+  #endif
+  #define MY_CPU_64BIT
+#elif defined(__ppc__) \
+  || defined(__powerpc__)
+  #define MY_CPU_NAME "ppc"
+  #define MY_CPU_32BIT
+#endif
+
+
+#if  defined(__sparc64__)
+  #define MY_CPU_NAME "sparc64"
+  #define MY_CPU_64BIT
+#elif defined(__sparc__)
+  #define MY_CPU_NAME "sparc"
+  /* #define MY_CPU_32BIT */
+#endif
+
+
+#if defined(MY_CPU_X86) || defined(MY_CPU_AMD64)
+#define MY_CPU_X86_OR_AMD64
+#endif
+
+
+#ifdef _WIN32
+
+  #ifdef MY_CPU_ARM
+  #define MY_CPU_ARM_LE
+  #endif
+
+  #ifdef MY_CPU_ARM64
+  #define MY_CPU_ARM64_LE
+  #endif
+
+  #ifdef _M_IA64
+  #define MY_CPU_IA64_LE
+  #endif
+
+#endif
+
+
+#if defined(MY_CPU_X86_OR_AMD64) \
+    || defined(MY_CPU_ARM_LE) \
+    || defined(MY_CPU_ARM64_LE) \
+    || defined(MY_CPU_IA64_LE) \
+    || defined(__LITTLE_ENDIAN__) \
+    || defined(__ARMEL__) \
+    || defined(__THUMBEL__) \
+    || defined(__AARCH64EL__) \
+    || defined(__MIPSEL__) \
+    || defined(__MIPSEL) \
+    || defined(_MIPSEL) \
+    || defined(__BFIN__) \
+    || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__))
+  #define MY_CPU_LE
+#endif
+
+#if defined(__BIG_ENDIAN__) \
+    || defined(__ARMEB__) \
+    || defined(__THUMBEB__) \
+    || defined(__AARCH64EB__) \
+    || defined(__MIPSEB__) \
+    || defined(__MIPSEB) \
+    || defined(_MIPSEB) \
+    || defined(__m68k__) \
+    || defined(__s390__) \
+    || defined(__s390x__) \
+    || defined(__zarch__) \
+    || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__))
+  #define MY_CPU_BE
+#endif
+
+
+#if defined(MY_CPU_LE) && defined(MY_CPU_BE)
+  #error Stop_Compiling_Bad_Endian
+#endif
+
+
+#if defined(MY_CPU_32BIT) && defined(MY_CPU_64BIT)
+  #error Stop_Compiling_Bad_32_64_BIT
+#endif
+
+
+#ifndef MY_CPU_NAME
+  #ifdef MY_CPU_LE
+    #define MY_CPU_NAME "LE"
+  #elif defined(MY_CPU_BE)
+    #define MY_CPU_NAME "BE"
+  #else
+    /*
+    #define MY_CPU_NAME ""
+    */
+  #endif
+#endif
+
+
+
+
+
+#ifdef MY_CPU_LE
+  #if defined(MY_CPU_X86_OR_AMD64) \
+      || defined(MY_CPU_ARM64) \
+      || defined(__ARM_FEATURE_UNALIGNED)
+    #define MY_CPU_LE_UNALIGN
+  #endif
+#endif
+
+
+#ifdef MY_CPU_LE_UNALIGN
+
+#define GetUi16(p) (*(const UInt16 *)(const void *)(p))
+#define GetUi32(p) (*(const UInt32 *)(const void *)(p))
+#define GetUi64(p) (*(const UInt64 *)(const void *)(p))
+
+#define SetUi16(p, v) { *(UInt16 *)(p) = (v); }
+#define SetUi32(p, v) { *(UInt32 *)(p) = (v); }
+#define SetUi64(p, v) { *(UInt64 *)(p) = (v); }
+
+#else
+
+#define GetUi16(p) ( (UInt16) ( \
+             ((const Byte *)(p))[0] | \
+    ((UInt16)((const Byte *)(p))[1] << 8) ))
+
+#define GetUi32(p) ( \
+             ((const Byte *)(p))[0]        | \
+    ((UInt32)((const Byte *)(p))[1] <<  8) | \
+    ((UInt32)((const Byte *)(p))[2] << 16) | \
+    ((UInt32)((const Byte *)(p))[3] << 24))
+
+#define GetUi64(p) (GetUi32(p) | ((UInt64)GetUi32(((const Byte *)(p)) + 4) << 32))
+
+#define SetUi16(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)_vvv_; \
+    _ppp_[1] = (Byte)(_vvv_ >> 8); }
+
+#define SetUi32(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)_vvv_; \
+    _ppp_[1] = (Byte)(_vvv_ >> 8); \
+    _ppp_[2] = (Byte)(_vvv_ >> 16); \
+    _ppp_[3] = (Byte)(_vvv_ >> 24); }
+
+#define SetUi64(p, v) { Byte *_ppp2_ = (Byte *)(p); UInt64 _vvv2_ = (v); \
+    SetUi32(_ppp2_    , (UInt32)_vvv2_); \
+    SetUi32(_ppp2_ + 4, (UInt32)(_vvv2_ >> 32)); }
+
+#endif
+
+#ifdef __has_builtin
+  #define MY__has_builtin(x) __has_builtin(x)
+#else
+  #define MY__has_builtin(x) 0
+#endif
+
+#if defined(MY_CPU_LE_UNALIGN) && /* defined(_WIN64) && */ (_MSC_VER >= 1300)
+
+/* Note: we use bswap instruction, that is unsupported in 386 cpu */
+
+#include <stdlib.h>
+
+#pragma intrinsic(_byteswap_ushort)
+#pragma intrinsic(_byteswap_ulong)
+#pragma intrinsic(_byteswap_uint64)
+
+/* #define GetBe16(p) _byteswap_ushort(*(const UInt16 *)(const Byte *)(p)) */
+#define GetBe32(p) _byteswap_ulong(*(const UInt32 *)(const Byte *)(p))
+#define GetBe64(p) _byteswap_uint64(*(const UInt64 *)(const Byte *)(p))
+
+#define SetBe32(p, v) (*(UInt32 *)(void *)(p)) = _byteswap_ulong(v)
+
+#elif defined(MY_CPU_LE_UNALIGN) && ( \
+       (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) \
+    || (defined(__clang__) && MY__has_builtin(__builtin_bswap16)) )
+
+/* #define GetBe16(p) __builtin_bswap16(*(const UInt16 *)(const Byte *)(p)) */
+#define GetBe32(p) __builtin_bswap32(*(const UInt32 *)(const Byte *)(p))
+#define GetBe64(p) __builtin_bswap64(*(const UInt64 *)(const Byte *)(p))
+
+#define SetBe32(p, v) (*(UInt32 *)(void *)(p)) = __builtin_bswap32(v)
+
+#else
+
+#define GetBe32(p) ( \
+    ((UInt32)((const Byte *)(p))[0] << 24) | \
+    ((UInt32)((const Byte *)(p))[1] << 16) | \
+    ((UInt32)((const Byte *)(p))[2] <<  8) | \
+             ((const Byte *)(p))[3] )
+
+#define GetBe64(p) (((UInt64)GetBe32(p) << 32) | GetBe32(((const Byte *)(p)) + 4))
+
+#define SetBe32(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)(_vvv_ >> 24); \
+    _ppp_[1] = (Byte)(_vvv_ >> 16); \
+    _ppp_[2] = (Byte)(_vvv_ >> 8); \
+    _ppp_[3] = (Byte)_vvv_; }
+
+#endif
+
+
+#ifndef GetBe16
+
+#define GetBe16(p) ( (UInt16) ( \
+    ((UInt16)((const Byte *)(p))[0] << 8) | \
+             ((const Byte *)(p))[1] ))
+
+#endif
+
+
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+typedef struct
+{
+  UInt32 maxFunc;
+  UInt32 vendor[3];
+  UInt32 ver;
+  UInt32 b;
+  UInt32 c;
+  UInt32 d;
+} Cx86cpuid;
+
+enum
+{
+  CPU_FIRM_INTEL,
+  CPU_FIRM_AMD,
+  CPU_FIRM_VIA
+};
+
+void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d);
+
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p);
+int x86cpuid_GetFirm(const Cx86cpuid *p);
+
+#define x86cpuid_GetFamily(ver) (((ver >> 16) & 0xFF0) | ((ver >> 8) & 0xF))
+#define x86cpuid_GetModel(ver)  (((ver >> 12) &  0xF0) | ((ver >> 4) & 0xF))
+#define x86cpuid_GetStepping(ver) (ver & 0xF)
+
+BoolInt CPU_Is_InOrder();
+BoolInt CPU_Is_Aes_Supported();
+BoolInt CPU_IsSupported_PageGB();
+
+#endif
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,64 @@
+/* Delta.c -- Delta converter
+2009-05-26 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Delta.h"
+
+void Delta_Init(Byte *state)
+{
+  unsigned i;
+  for (i = 0; i < DELTA_STATE_SIZE; i++)
+    state[i] = 0;
+}
+
+static void MyMemCpy(Byte *dest, const Byte *src, unsigned size)
+{
+  unsigned i;
+  for (i = 0; i < size; i++)
+    dest[i] = src[i];
+}
+
+void Delta_Encode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  Byte buf[DELTA_STATE_SIZE];
+  unsigned j = 0;
+  MyMemCpy(buf, state, delta);
+  {
+    SizeT i;
+    for (i = 0; i < size;)
+    {
+      for (j = 0; j < delta && i < size; i++, j++)
+      {
+        Byte b = data[i];
+        data[i] = (Byte)(b - buf[j]);
+        buf[j] = b;
+      }
+    }
+  }
+  if (j == delta)
+    j = 0;
+  MyMemCpy(state, buf + j, delta - j);
+  MyMemCpy(state + delta - j, buf, j);
+}
+
+void Delta_Decode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  Byte buf[DELTA_STATE_SIZE];
+  unsigned j = 0;
+  MyMemCpy(buf, state, delta);
+  {
+    SizeT i;
+    for (i = 0; i < size;)
+    {
+      for (j = 0; j < delta && i < size; i++, j++)
+      {
+        buf[j] = data[i] = (Byte)(buf[j] + data[i]);
+      }
+    }
+  }
+  if (j == delta)
+    j = 0;
+  MyMemCpy(state, buf + j, delta - j);
+  MyMemCpy(state + delta - j, buf, j);
+}
@@ -0,0 +1,19 @@
+/* Delta.h -- Delta converter
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __DELTA_H
+#define __DELTA_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define DELTA_STATE_SIZE 256
+
+void Delta_Init(Byte *state);
+void Delta_Encode(Byte *state, unsigned delta, Byte *data, SizeT size);
+void Delta_Decode(Byte *state, unsigned delta, Byte *data, SizeT size);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,108 @@
+/* DllSecur.c -- DLL loading security
+2018-02-21 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#ifdef _WIN32
+
+#include <windows.h>
+
+#include "DllSecur.h"
+
+#ifndef UNDER_CE
+
+typedef BOOL (WINAPI *Func_SetDefaultDllDirectories)(DWORD DirectoryFlags);
+
+#define MY_LOAD_LIBRARY_SEARCH_USER_DIRS 0x400
+#define MY_LOAD_LIBRARY_SEARCH_SYSTEM32  0x800
+
+static const char * const g_Dlls =
+  #ifndef _CONSOLE
+  "UXTHEME\0"
+  #endif
+  "USERENV\0"
+  "SETUPAPI\0"
+  "APPHELP\0"
+  "PROPSYS\0"
+  "DWMAPI\0"
+  "CRYPTBASE\0"
+  "OLEACC\0"
+  "CLBCATQ\0"
+  "VERSION\0"
+  ;
+
+#endif
+
+void My_SetDefaultDllDirectories()
+{
+  #ifndef UNDER_CE
+  
+    OSVERSIONINFO vi;
+    vi.dwOSVersionInfoSize = sizeof(vi);
+    GetVersionEx(&vi);
+    if (!GetVersionEx(&vi) || vi.dwMajorVersion != 6 || vi.dwMinorVersion != 0)
+    {
+      Func_SetDefaultDllDirectories setDllDirs = (Func_SetDefaultDllDirectories)
+          GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "SetDefaultDllDirectories");
+      if (setDllDirs)
+        if (setDllDirs(MY_LOAD_LIBRARY_SEARCH_SYSTEM32 | MY_LOAD_LIBRARY_SEARCH_USER_DIRS))
+          return;
+    }
+
+  #endif
+}
+
+
+void LoadSecurityDlls()
+{
+  #ifndef UNDER_CE
+  
+  wchar_t buf[MAX_PATH + 100];
+
+  {
+    // at Vista (ver 6.0) : CoCreateInstance(CLSID_ShellLink, ...) doesn't work after SetDefaultDllDirectories() : Check it ???
+    OSVERSIONINFO vi;
+    vi.dwOSVersionInfoSize = sizeof(vi);
+    if (!GetVersionEx(&vi) || vi.dwMajorVersion != 6 || vi.dwMinorVersion != 0)
+    {
+      Func_SetDefaultDllDirectories setDllDirs = (Func_SetDefaultDllDirectories)
+          GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "SetDefaultDllDirectories");
+      if (setDllDirs)
+        if (setDllDirs(MY_LOAD_LIBRARY_SEARCH_SYSTEM32 | MY_LOAD_LIBRARY_SEARCH_USER_DIRS))
+          return;
+    }
+  }
+
+  {
+    unsigned len = GetSystemDirectoryW(buf, MAX_PATH + 2);
+    if (len == 0 || len > MAX_PATH)
+      return;
+  }
+  {
+    const char *dll;
+    unsigned pos = (unsigned)lstrlenW(buf);
+
+    if (buf[pos - 1] != '\\')
+      buf[pos++] = '\\';
+    
+    for (dll = g_Dlls; dll[0] != 0;)
+    {
+      unsigned k = 0;
+      for (;;)
+      {
+        char c = *dll++;
+        buf[pos + k] = (Byte)c;
+        k++;
+        if (c == 0)
+          break;
+      }
+
+      lstrcatW(buf, L".dll");
+      LoadLibraryExW(buf, NULL, LOAD_WITH_ALTERED_SEARCH_PATH);
+    }
+  }
+  
+  #endif
+}
+
+#endif
@@ -0,0 +1,20 @@
+/* DllSecur.h -- DLL loading for security
+2018-02-19 : Igor Pavlov : Public domain */
+
+#ifndef __DLL_SECUR_H
+#define __DLL_SECUR_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#ifdef _WIN32
+
+void My_SetDefaultDllDirectories();
+void LoadSecurityDlls();
+
+#endif
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,121 @@
+/* LzFind.h -- Match finder for LZ algorithms
+2017-06-10 : Igor Pavlov : Public domain */
+
+#ifndef __LZ_FIND_H
+#define __LZ_FIND_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+typedef UInt32 CLzRef;
+
+typedef struct _CMatchFinder
+{
+  Byte *buffer;
+  UInt32 pos;
+  UInt32 posLimit;
+  UInt32 streamPos;
+  UInt32 lenLimit;
+
+  UInt32 cyclicBufferPos;
+  UInt32 cyclicBufferSize; /* it must be = (historySize + 1) */
+
+  Byte streamEndWasReached;
+  Byte btMode;
+  Byte bigHash;
+  Byte directInput;
+
+  UInt32 matchMaxLen;
+  CLzRef *hash;
+  CLzRef *son;
+  UInt32 hashMask;
+  UInt32 cutValue;
+
+  Byte *bufferBase;
+  ISeqInStream *stream;
+  
+  UInt32 blockSize;
+  UInt32 keepSizeBefore;
+  UInt32 keepSizeAfter;
+
+  UInt32 numHashBytes;
+  size_t directInputRem;
+  UInt32 historySize;
+  UInt32 fixedHashSize;
+  UInt32 hashSizeSum;
+  SRes result;
+  UInt32 crc[256];
+  size_t numRefs;
+
+  UInt64 expectedDataSize;
+} CMatchFinder;
+
+#define Inline_MatchFinder_GetPointerToCurrentPos(p) ((p)->buffer)
+
+#define Inline_MatchFinder_GetNumAvailableBytes(p) ((p)->streamPos - (p)->pos)
+
+#define Inline_MatchFinder_IsFinishedOK(p) \
+    ((p)->streamEndWasReached \
+        && (p)->streamPos == (p)->pos \
+        && (!(p)->directInput || (p)->directInputRem == 0))
+      
+int MatchFinder_NeedMove(CMatchFinder *p);
+Byte *MatchFinder_GetPointerToCurrentPos(CMatchFinder *p);
+void MatchFinder_MoveBlock(CMatchFinder *p);
+void MatchFinder_ReadIfRequired(CMatchFinder *p);
+
+void MatchFinder_Construct(CMatchFinder *p);
+
+/* Conditions:
+     historySize <= 3 GB
+     keepAddBufferBefore + matchMaxLen + keepAddBufferAfter < 511MB
+*/
+int MatchFinder_Create(CMatchFinder *p, UInt32 historySize,
+    UInt32 keepAddBufferBefore, UInt32 matchMaxLen, UInt32 keepAddBufferAfter,
+    ISzAllocPtr alloc);
+void MatchFinder_Free(CMatchFinder *p, ISzAllocPtr alloc);
+void MatchFinder_Normalize3(UInt32 subValue, CLzRef *items, size_t numItems);
+void MatchFinder_ReduceOffsets(CMatchFinder *p, UInt32 subValue);
+
+UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *buffer, CLzRef *son,
+    UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 _cutValue,
+    UInt32 *distances, UInt32 maxLen);
+
+/*
+Conditions:
+  Mf_GetNumAvailableBytes_Func must be called before each Mf_GetMatchLen_Func.
+  Mf_GetPointerToCurrentPos_Func's result must be used only before any other function
+*/
+
+typedef void (*Mf_Init_Func)(void *object);
+typedef UInt32 (*Mf_GetNumAvailableBytes_Func)(void *object);
+typedef const Byte * (*Mf_GetPointerToCurrentPos_Func)(void *object);
+typedef UInt32 (*Mf_GetMatches_Func)(void *object, UInt32 *distances);
+typedef void (*Mf_Skip_Func)(void *object, UInt32);
+
+typedef struct _IMatchFinder
+{
+  Mf_Init_Func Init;
+  Mf_GetNumAvailableBytes_Func GetNumAvailableBytes;
+  Mf_GetPointerToCurrentPos_Func GetPointerToCurrentPos;
+  Mf_GetMatches_Func GetMatches;
+  Mf_Skip_Func Skip;
+} IMatchFinder;
+
+void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder *vTable);
+
+void MatchFinder_Init_LowHash(CMatchFinder *p);
+void MatchFinder_Init_HighHash(CMatchFinder *p);
+void MatchFinder_Init_3(CMatchFinder *p, int readData);
+void MatchFinder_Init(CMatchFinder *p);
+
+UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances);
+UInt32 Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances);
+
+void Bt3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num);
+void Hc3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,853 @@
+/* LzFindMt.c -- multithreaded Match finder for LZ algorithms
+2018-12-29 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "LzHash.h"
+
+#include "LzFindMt.h"
+
+static void MtSync_Construct(CMtSync *p)
+{
+  p->wasCreated = False;
+  p->csWasInitialized = False;
+  p->csWasEntered = False;
+  Thread_Construct(&p->thread);
+  Event_Construct(&p->canStart);
+  Event_Construct(&p->wasStarted);
+  Event_Construct(&p->wasStopped);
+  Semaphore_Construct(&p->freeSemaphore);
+  Semaphore_Construct(&p->filledSemaphore);
+}
+
+static void MtSync_GetNextBlock(CMtSync *p)
+{
+  if (p->needStart)
+  {
+    p->numProcessedBlocks = 1;
+    p->needStart = False;
+    p->stopWriting = False;
+    p->exit = False;
+    Event_Reset(&p->wasStarted);
+    Event_Reset(&p->wasStopped);
+
+    Event_Set(&p->canStart);
+    Event_Wait(&p->wasStarted);
+
+    // if (mt) MatchFinder_Init_LowHash(mt->MatchFinder);
+  }
+  else
+  {
+    CriticalSection_Leave(&p->cs);
+    p->csWasEntered = False;
+    p->numProcessedBlocks++;
+    Semaphore_Release1(&p->freeSemaphore);
+  }
+  Semaphore_Wait(&p->filledSemaphore);
+  CriticalSection_Enter(&p->cs);
+  p->csWasEntered = True;
+}
+
+/* MtSync_StopWriting must be called if Writing was started */
+
+static void MtSync_StopWriting(CMtSync *p)
+{
+  UInt32 myNumBlocks = p->numProcessedBlocks;
+  if (!Thread_WasCreated(&p->thread) || p->needStart)
+    return;
+  p->stopWriting = True;
+  if (p->csWasEntered)
+  {
+    CriticalSection_Leave(&p->cs);
+    p->csWasEntered = False;
+  }
+  Semaphore_Release1(&p->freeSemaphore);
+ 
+  Event_Wait(&p->wasStopped);
+
+  while (myNumBlocks++ != p->numProcessedBlocks)
+  {
+    Semaphore_Wait(&p->filledSemaphore);
+    Semaphore_Release1(&p->freeSemaphore);
+  }
+  p->needStart = True;
+}
+
+static void MtSync_Destruct(CMtSync *p)
+{
+  if (Thread_WasCreated(&p->thread))
+  {
+    MtSync_StopWriting(p);
+    p->exit = True;
+    if (p->needStart)
+      Event_Set(&p->canStart);
+    Thread_Wait(&p->thread);
+    Thread_Close(&p->thread);
+  }
+  if (p->csWasInitialized)
+  {
+    CriticalSection_Delete(&p->cs);
+    p->csWasInitialized = False;
+  }
+
+  Event_Close(&p->canStart);
+  Event_Close(&p->wasStarted);
+  Event_Close(&p->wasStopped);
+  Semaphore_Close(&p->freeSemaphore);
+  Semaphore_Close(&p->filledSemaphore);
+
+  p->wasCreated = False;
+}
+
+#define RINOK_THREAD(x) { if ((x) != 0) return SZ_ERROR_THREAD; }
+
+static SRes MtSync_Create2(CMtSync *p, THREAD_FUNC_TYPE startAddress, void *obj, UInt32 numBlocks)
+{
+  if (p->wasCreated)
+    return SZ_OK;
+
+  RINOK_THREAD(CriticalSection_Init(&p->cs));
+  p->csWasInitialized = True;
+
+  RINOK_THREAD(AutoResetEvent_CreateNotSignaled(&p->canStart));
+  RINOK_THREAD(AutoResetEvent_CreateNotSignaled(&p->wasStarted));
+  RINOK_THREAD(AutoResetEvent_CreateNotSignaled(&p->wasStopped));
+  
+  RINOK_THREAD(Semaphore_Create(&p->freeSemaphore, numBlocks, numBlocks));
+  RINOK_THREAD(Semaphore_Create(&p->filledSemaphore, 0, numBlocks));
+
+  p->needStart = True;
+  
+  RINOK_THREAD(Thread_Create(&p->thread, startAddress, obj));
+  p->wasCreated = True;
+  return SZ_OK;
+}
+
+static SRes MtSync_Create(CMtSync *p, THREAD_FUNC_TYPE startAddress, void *obj, UInt32 numBlocks)
+{
+  SRes res = MtSync_Create2(p, startAddress, obj, numBlocks);
+  if (res != SZ_OK)
+    MtSync_Destruct(p);
+  return res;
+}
+
+void MtSync_Init(CMtSync *p) { p->needStart = True; }
+
+#define kMtMaxValForNormalize 0xFFFFFFFF
+
+#define DEF_GetHeads2(name, v, action) \
+  static void GetHeads ## name(const Byte *p, UInt32 pos, \
+      UInt32 *hash, UInt32 hashMask, UInt32 *heads, UInt32 numHeads, const UInt32 *crc) \
+    { action; for (; numHeads != 0; numHeads--) { \
+      const UInt32 value = (v); p++; *heads++ = pos - hash[value]; hash[value] = pos++;  } }
+
+#define DEF_GetHeads(name, v) DEF_GetHeads2(name, v, ;)
+
+DEF_GetHeads2(2,  (p[0] | ((UInt32)p[1] << 8)), UNUSED_VAR(hashMask); UNUSED_VAR(crc); )
+DEF_GetHeads(3,  (crc[p[0]] ^ p[1] ^ ((UInt32)p[2] << 8)) & hashMask)
+DEF_GetHeads(4,  (crc[p[0]] ^ p[1] ^ ((UInt32)p[2] << 8) ^ (crc[p[3]] << 5)) & hashMask)
+DEF_GetHeads(4b, (crc[p[0]] ^ p[1] ^ ((UInt32)p[2] << 8) ^ ((UInt32)p[3] << 16)) & hashMask)
+/* DEF_GetHeads(5,  (crc[p[0]] ^ p[1] ^ ((UInt32)p[2] << 8) ^ (crc[p[3]] << 5) ^ (crc[p[4]] << 3)) & hashMask) */
+
+static void HashThreadFunc(CMatchFinderMt *mt)
+{
+  CMtSync *p = &mt->hashSync;
+  for (;;)
+  {
+    UInt32 numProcessedBlocks = 0;
+    Event_Wait(&p->canStart);
+    Event_Set(&p->wasStarted);
+
+    MatchFinder_Init_HighHash(mt->MatchFinder);
+
+    for (;;)
+    {
+      if (p->exit)
+        return;
+      if (p->stopWriting)
+      {
+        p->numProcessedBlocks = numProcessedBlocks;
+        Event_Set(&p->wasStopped);
+        break;
+      }
+
+      {
+        CMatchFinder *mf = mt->MatchFinder;
+        if (MatchFinder_NeedMove(mf))
+        {
+          CriticalSection_Enter(&mt->btSync.cs);
+          CriticalSection_Enter(&mt->hashSync.cs);
+          {
+            const Byte *beforePtr = Inline_MatchFinder_GetPointerToCurrentPos(mf);
+            ptrdiff_t offset;
+            MatchFinder_MoveBlock(mf);
+            offset = beforePtr - Inline_MatchFinder_GetPointerToCurrentPos(mf);
+            mt->pointerToCurPos -= offset;
+            mt->buffer -= offset;
+          }
+          CriticalSection_Leave(&mt->btSync.cs);
+          CriticalSection_Leave(&mt->hashSync.cs);
+          continue;
+        }
+
+        Semaphore_Wait(&p->freeSemaphore);
+
+        MatchFinder_ReadIfRequired(mf);
+        if (mf->pos > (kMtMaxValForNormalize - kMtHashBlockSize))
+        {
+          UInt32 subValue = (mf->pos - mf->historySize - 1);
+          MatchFinder_ReduceOffsets(mf, subValue);
+          MatchFinder_Normalize3(subValue, mf->hash + mf->fixedHashSize, (size_t)mf->hashMask + 1);
+        }
+        {
+          UInt32 *heads = mt->hashBuf + ((numProcessedBlocks++) & kMtHashNumBlocksMask) * kMtHashBlockSize;
+          UInt32 num = mf->streamPos - mf->pos;
+          heads[0] = 2;
+          heads[1] = num;
+          if (num >= mf->numHashBytes)
+          {
+            num = num - mf->numHashBytes + 1;
+            if (num > kMtHashBlockSize - 2)
+              num = kMtHashBlockSize - 2;
+            mt->GetHeadsFunc(mf->buffer, mf->pos, mf->hash + mf->fixedHashSize, mf->hashMask, heads + 2, num, mf->crc);
+            heads[0] = 2 + num;
+          }
+          mf->pos += num;
+          mf->buffer += num;
+        }
+      }
+
+      Semaphore_Release1(&p->filledSemaphore);
+    }
+  }
+}
+
+static void MatchFinderMt_GetNextBlock_Hash(CMatchFinderMt *p)
+{
+  MtSync_GetNextBlock(&p->hashSync);
+  p->hashBufPosLimit = p->hashBufPos = ((p->hashSync.numProcessedBlocks - 1) & kMtHashNumBlocksMask) * kMtHashBlockSize;
+  p->hashBufPosLimit += p->hashBuf[p->hashBufPos++];
+  p->hashNumAvail = p->hashBuf[p->hashBufPos++];
+}
+
+#define kEmptyHashValue 0
+
+#define MFMT_GM_INLINE
+
+#ifdef MFMT_GM_INLINE
+
+/*
+  we use size_t for _cyclicBufferPos instead of UInt32
+  to eliminate "movsx" BUG in old MSVC x64 compiler.
+*/
+
+MY_NO_INLINE
+static UInt32 *GetMatchesSpecN(UInt32 lenLimit, UInt32 pos, const Byte *cur, CLzRef *son,
+    size_t _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 _cutValue,
+    UInt32 *distances, UInt32 _maxLen, const UInt32 *hash, const UInt32 *limit, UInt32 size, UInt32 *posRes)
+{
+  do
+  {
+  UInt32 *_distances = ++distances;
+  UInt32 delta = *hash++;
+
+  CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+  CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+  unsigned len0 = 0, len1 = 0;
+  UInt32 cutValue = _cutValue;
+  unsigned maxLen = (unsigned)_maxLen;
+
+  /*
+  if (size > 1)
+  {
+    UInt32 delta = *hash;
+    if (delta < _cyclicBufferSize)
+    {
+      UInt32 cyc1 = _cyclicBufferPos + 1;
+      CLzRef *pair = son + ((size_t)(cyc1 - delta + ((delta > cyc1) ? _cyclicBufferSize : 0)) << 1);
+      Byte b = *(cur + 1 - delta);
+      _distances[0] = pair[0];
+      _distances[1] = b;
+    }
+  }
+  */
+  if (cutValue == 0 || delta >= _cyclicBufferSize)
+  {
+    *ptr0 = *ptr1 = kEmptyHashValue;
+  }
+  else
+  for(;;)
+  {
+    {
+      CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((_cyclicBufferPos < delta) ? _cyclicBufferSize : 0)) << 1);
+      const Byte *pb = cur - delta;
+      unsigned len = (len0 < len1 ? len0 : len1);
+      UInt32 pair0 = *pair;
+      if (pb[len] == cur[len])
+      {
+        if (++len != lenLimit && pb[len] == cur[len])
+          while (++len != lenLimit)
+            if (pb[len] != cur[len])
+              break;
+        if (maxLen < len)
+        {
+          maxLen = len;
+          *distances++ = (UInt32)len;
+          *distances++ = delta - 1;
+          if (len == lenLimit)
+          {
+            UInt32 pair1 = pair[1];
+            *ptr1 = pair0;
+            *ptr0 = pair1;
+            break;
+          }
+        }
+      }
+      {
+        UInt32 curMatch = pos - delta;
+        // delta = pos - *pair;
+        // delta = pos - pair[((UInt32)pb[len] - (UInt32)cur[len]) >> 31];
+        if (pb[len] < cur[len])
+        {
+          delta = pos - pair[1];
+          *ptr1 = curMatch;
+          ptr1 = pair + 1;
+          len1 = len;
+        }
+        else
+        {
+          delta = pos - *pair;
+          *ptr0 = curMatch;
+          ptr0 = pair;
+          len0 = len;
+        }
+      }
+    }
+    if (--cutValue == 0 || delta >= _cyclicBufferSize)
+    {
+      *ptr0 = *ptr1 = kEmptyHashValue;
+      break;
+    }
+  }
+  pos++;
+  _cyclicBufferPos++;
+  cur++;
+  {
+    UInt32 num = (UInt32)(distances - _distances);
+    _distances[-1] = num;
+  }
+  }
+  while (distances < limit && --size != 0);
+  *posRes = pos;
+  return distances;
+}
+
+#endif
+
+
+
+static void BtGetMatches(CMatchFinderMt *p, UInt32 *distances)
+{
+  UInt32 numProcessed = 0;
+  UInt32 curPos = 2;
+  UInt32 limit = kMtBtBlockSize - (p->matchMaxLen * 2); //  * 2
+  
+  distances[1] = p->hashNumAvail;
+  
+  while (curPos < limit)
+  {
+    if (p->hashBufPos == p->hashBufPosLimit)
+    {
+      MatchFinderMt_GetNextBlock_Hash(p);
+      distances[1] = numProcessed + p->hashNumAvail;
+      if (p->hashNumAvail >= p->numHashBytes)
+        continue;
+      distances[0] = curPos + p->hashNumAvail;
+      distances += curPos;
+      for (; p->hashNumAvail != 0; p->hashNumAvail--)
+        *distances++ = 0;
+      return;
+    }
+    {
+      UInt32 size = p->hashBufPosLimit - p->hashBufPos;
+      UInt32 lenLimit = p->matchMaxLen;
+      UInt32 pos = p->pos;
+      UInt32 cyclicBufferPos = p->cyclicBufferPos;
+      if (lenLimit >= p->hashNumAvail)
+        lenLimit = p->hashNumAvail;
+      {
+        UInt32 size2 = p->hashNumAvail - lenLimit + 1;
+        if (size2 < size)
+          size = size2;
+        size2 = p->cyclicBufferSize - cyclicBufferPos;
+        if (size2 < size)
+          size = size2;
+      }
+      
+      #ifndef MFMT_GM_INLINE
+      while (curPos < limit && size-- != 0)
+      {
+        UInt32 *startDistances = distances + curPos;
+        UInt32 num = (UInt32)(GetMatchesSpec1(lenLimit, pos - p->hashBuf[p->hashBufPos++],
+            pos, p->buffer, p->son, cyclicBufferPos, p->cyclicBufferSize, p->cutValue,
+            startDistances + 1, p->numHashBytes - 1) - startDistances);
+        *startDistances = num - 1;
+        curPos += num;
+        cyclicBufferPos++;
+        pos++;
+        p->buffer++;
+      }
+      #else
+      {
+        UInt32 posRes;
+        curPos = (UInt32)(GetMatchesSpecN(lenLimit, pos, p->buffer, p->son, cyclicBufferPos, p->cyclicBufferSize, p->cutValue,
+            distances + curPos, p->numHashBytes - 1, p->hashBuf + p->hashBufPos,
+            distances + limit,
+            size, &posRes) - distances);
+        p->hashBufPos += posRes - pos;
+        cyclicBufferPos += posRes - pos;
+        p->buffer += posRes - pos;
+        pos = posRes;
+      }
+      #endif
+
+      numProcessed += pos - p->pos;
+      p->hashNumAvail -= pos - p->pos;
+      p->pos = pos;
+      if (cyclicBufferPos == p->cyclicBufferSize)
+        cyclicBufferPos = 0;
+      p->cyclicBufferPos = cyclicBufferPos;
+    }
+  }
+  
+  distances[0] = curPos;
+}
+
+static void BtFillBlock(CMatchFinderMt *p, UInt32 globalBlockIndex)
+{
+  CMtSync *sync = &p->hashSync;
+  if (!sync->needStart)
+  {
+    CriticalSection_Enter(&sync->cs);
+    sync->csWasEntered = True;
+  }
+  
+  BtGetMatches(p, p->btBuf + (globalBlockIndex & kMtBtNumBlocksMask) * kMtBtBlockSize);
+
+  if (p->pos > kMtMaxValForNormalize - kMtBtBlockSize)
+  {
+    UInt32 subValue = p->pos - p->cyclicBufferSize;
+    MatchFinder_Normalize3(subValue, p->son, (size_t)p->cyclicBufferSize * 2);
+    p->pos -= subValue;
+  }
+
+  if (!sync->needStart)
+  {
+    CriticalSection_Leave(&sync->cs);
+    sync->csWasEntered = False;
+  }
+}
+
+void BtThreadFunc(CMatchFinderMt *mt)
+{
+  CMtSync *p = &mt->btSync;
+  for (;;)
+  {
+    UInt32 blockIndex = 0;
+    Event_Wait(&p->canStart);
+    Event_Set(&p->wasStarted);
+    for (;;)
+    {
+      if (p->exit)
+        return;
+      if (p->stopWriting)
+      {
+        p->numProcessedBlocks = blockIndex;
+        MtSync_StopWriting(&mt->hashSync);
+        Event_Set(&p->wasStopped);
+        break;
+      }
+      Semaphore_Wait(&p->freeSemaphore);
+      BtFillBlock(mt, blockIndex++);
+      Semaphore_Release1(&p->filledSemaphore);
+    }
+  }
+}
+
+void MatchFinderMt_Construct(CMatchFinderMt *p)
+{
+  p->hashBuf = NULL;
+  MtSync_Construct(&p->hashSync);
+  MtSync_Construct(&p->btSync);
+}
+
+static void MatchFinderMt_FreeMem(CMatchFinderMt *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->hashBuf);
+  p->hashBuf = NULL;
+}
+
+void MatchFinderMt_Destruct(CMatchFinderMt *p, ISzAllocPtr alloc)
+{
+  MtSync_Destruct(&p->hashSync);
+  MtSync_Destruct(&p->btSync);
+  MatchFinderMt_FreeMem(p, alloc);
+}
+
+#define kHashBufferSize (kMtHashBlockSize * kMtHashNumBlocks)
+#define kBtBufferSize (kMtBtBlockSize * kMtBtNumBlocks)
+
+static THREAD_FUNC_RET_TYPE THREAD_FUNC_CALL_TYPE HashThreadFunc2(void *p) { HashThreadFunc((CMatchFinderMt *)p);  return 0; }
+static THREAD_FUNC_RET_TYPE THREAD_FUNC_CALL_TYPE BtThreadFunc2(void *p)
+{
+  Byte allocaDummy[0x180];
+  unsigned i = 0;
+  for (i = 0; i < 16; i++)
+    allocaDummy[i] = (Byte)0;
+  if (allocaDummy[0] == 0)
+    BtThreadFunc((CMatchFinderMt *)p);
+  return 0;
+}
+
+SRes MatchFinderMt_Create(CMatchFinderMt *p, UInt32 historySize, UInt32 keepAddBufferBefore,
+    UInt32 matchMaxLen, UInt32 keepAddBufferAfter, ISzAllocPtr alloc)
+{
+  CMatchFinder *mf = p->MatchFinder;
+  p->historySize = historySize;
+  if (kMtBtBlockSize <= matchMaxLen * 4)
+    return SZ_ERROR_PARAM;
+  if (!p->hashBuf)
+  {
+    p->hashBuf = (UInt32 *)ISzAlloc_Alloc(alloc, (kHashBufferSize + kBtBufferSize) * sizeof(UInt32));
+    if (!p->hashBuf)
+      return SZ_ERROR_MEM;
+    p->btBuf = p->hashBuf + kHashBufferSize;
+  }
+  keepAddBufferBefore += (kHashBufferSize + kBtBufferSize);
+  keepAddBufferAfter += kMtHashBlockSize;
+  if (!MatchFinder_Create(mf, historySize, keepAddBufferBefore, matchMaxLen, keepAddBufferAfter, alloc))
+    return SZ_ERROR_MEM;
+
+  RINOK(MtSync_Create(&p->hashSync, HashThreadFunc2, p, kMtHashNumBlocks));
+  RINOK(MtSync_Create(&p->btSync, BtThreadFunc2, p, kMtBtNumBlocks));
+  return SZ_OK;
+}
+
+/* Call it after ReleaseStream / SetStream */
+static void MatchFinderMt_Init(CMatchFinderMt *p)
+{
+  CMatchFinder *mf = p->MatchFinder;
+  
+  p->btBufPos =
+  p->btBufPosLimit = 0;
+  p->hashBufPos =
+  p->hashBufPosLimit = 0;
+
+  /* Init without data reading. We don't want to read data in this thread */
+  MatchFinder_Init_3(mf, False);
+  MatchFinder_Init_LowHash(mf);
+  
+  p->pointerToCurPos = Inline_MatchFinder_GetPointerToCurrentPos(mf);
+  p->btNumAvailBytes = 0;
+  p->lzPos = p->historySize + 1;
+
+  p->hash = mf->hash;
+  p->fixedHashSize = mf->fixedHashSize;
+  p->crc = mf->crc;
+
+  p->son = mf->son;
+  p->matchMaxLen = mf->matchMaxLen;
+  p->numHashBytes = mf->numHashBytes;
+  p->pos = mf->pos;
+  p->buffer = mf->buffer;
+  p->cyclicBufferPos = mf->cyclicBufferPos;
+  p->cyclicBufferSize = mf->cyclicBufferSize;
+  p->cutValue = mf->cutValue;
+}
+
+/* ReleaseStream is required to finish multithreading */
+void MatchFinderMt_ReleaseStream(CMatchFinderMt *p)
+{
+  MtSync_StopWriting(&p->btSync);
+  /* p->MatchFinder->ReleaseStream(); */
+}
+
+static void MatchFinderMt_Normalize(CMatchFinderMt *p)
+{
+  MatchFinder_Normalize3(p->lzPos - p->historySize - 1, p->hash, p->fixedHashSize);
+  p->lzPos = p->historySize + 1;
+}
+
+static void MatchFinderMt_GetNextBlock_Bt(CMatchFinderMt *p)
+{
+  UInt32 blockIndex;
+  MtSync_GetNextBlock(&p->btSync);
+  blockIndex = ((p->btSync.numProcessedBlocks - 1) & kMtBtNumBlocksMask);
+  p->btBufPosLimit = p->btBufPos = blockIndex * kMtBtBlockSize;
+  p->btBufPosLimit += p->btBuf[p->btBufPos++];
+  p->btNumAvailBytes = p->btBuf[p->btBufPos++];
+  if (p->lzPos >= kMtMaxValForNormalize - kMtBtBlockSize)
+    MatchFinderMt_Normalize(p);
+}
+
+static const Byte * MatchFinderMt_GetPointerToCurrentPos(CMatchFinderMt *p)
+{
+  return p->pointerToCurPos;
+}
+
+#define GET_NEXT_BLOCK_IF_REQUIRED if (p->btBufPos == p->btBufPosLimit) MatchFinderMt_GetNextBlock_Bt(p);
+
+static UInt32 MatchFinderMt_GetNumAvailableBytes(CMatchFinderMt *p)
+{
+  GET_NEXT_BLOCK_IF_REQUIRED;
+  return p->btNumAvailBytes;
+}
+
+static UInt32 * MixMatches2(CMatchFinderMt *p, UInt32 matchMinPos, UInt32 *distances)
+{
+  UInt32 h2, curMatch2;
+  UInt32 *hash = p->hash;
+  const Byte *cur = p->pointerToCurPos;
+  UInt32 lzPos = p->lzPos;
+  MT_HASH2_CALC
+      
+  curMatch2 = hash[h2];
+  hash[h2] = lzPos;
+
+  if (curMatch2 >= matchMinPos)
+    if (cur[(ptrdiff_t)curMatch2 - lzPos] == cur[0])
+    {
+      *distances++ = 2;
+      *distances++ = lzPos - curMatch2 - 1;
+    }
+  
+  return distances;
+}
+
+static UInt32 * MixMatches3(CMatchFinderMt *p, UInt32 matchMinPos, UInt32 *distances)
+{
+  UInt32 h2, h3, curMatch2, curMatch3;
+  UInt32 *hash = p->hash;
+  const Byte *cur = p->pointerToCurPos;
+  UInt32 lzPos = p->lzPos;
+  MT_HASH3_CALC
+
+  curMatch2 = hash[                h2];
+  curMatch3 = (hash + kFix3HashSize)[h3];
+  
+  hash[                h2] = lzPos;
+  (hash + kFix3HashSize)[h3] = lzPos;
+
+  if (curMatch2 >= matchMinPos && cur[(ptrdiff_t)curMatch2 - lzPos] == cur[0])
+  {
+    distances[1] = lzPos - curMatch2 - 1;
+    if (cur[(ptrdiff_t)curMatch2 - lzPos + 2] == cur[2])
+    {
+      distances[0] = 3;
+      return distances + 2;
+    }
+    distances[0] = 2;
+    distances += 2;
+  }
+  
+  if (curMatch3 >= matchMinPos && cur[(ptrdiff_t)curMatch3 - lzPos] == cur[0])
+  {
+    *distances++ = 3;
+    *distances++ = lzPos - curMatch3 - 1;
+  }
+  
+  return distances;
+}
+
+/*
+static UInt32 *MixMatches4(CMatchFinderMt *p, UInt32 matchMinPos, UInt32 *distances)
+{
+  UInt32 h2, h3, h4, curMatch2, curMatch3, curMatch4;
+  UInt32 *hash = p->hash;
+  const Byte *cur = p->pointerToCurPos;
+  UInt32 lzPos = p->lzPos;
+  MT_HASH4_CALC
+      
+  curMatch2 = hash[                h2];
+  curMatch3 = (hash + kFix3HashSize)[h3];
+  curMatch4 = (hash + kFix4HashSize)[h4];
+  
+  hash[                h2] = lzPos;
+  (hash + kFix3HashSize)[h3] = lzPos;
+  (hash + kFix4HashSize)[h4] = lzPos;
+
+  if (curMatch2 >= matchMinPos && cur[(ptrdiff_t)curMatch2 - lzPos] == cur[0])
+  {
+    distances[1] = lzPos - curMatch2 - 1;
+    if (cur[(ptrdiff_t)curMatch2 - lzPos + 2] == cur[2])
+    {
+      distances[0] = (cur[(ptrdiff_t)curMatch2 - lzPos + 3] == cur[3]) ? 4 : 3;
+      return distances + 2;
+    }
+    distances[0] = 2;
+    distances += 2;
+  }
+  
+  if (curMatch3 >= matchMinPos && cur[(ptrdiff_t)curMatch3 - lzPos] == cur[0])
+  {
+    distances[1] = lzPos - curMatch3 - 1;
+    if (cur[(ptrdiff_t)curMatch3 - lzPos + 3] == cur[3])
+    {
+      distances[0] = 4;
+      return distances + 2;
+    }
+    distances[0] = 3;
+    distances += 2;
+  }
+
+  if (curMatch4 >= matchMinPos)
+    if (
+      cur[(ptrdiff_t)curMatch4 - lzPos] == cur[0] &&
+      cur[(ptrdiff_t)curMatch4 - lzPos + 3] == cur[3]
+      )
+    {
+      *distances++ = 4;
+      *distances++ = lzPos - curMatch4 - 1;
+    }
+  
+  return distances;
+}
+*/
+
+#define INCREASE_LZ_POS p->lzPos++; p->pointerToCurPos++;
+
+static UInt32 MatchFinderMt2_GetMatches(CMatchFinderMt *p, UInt32 *distances)
+{
+  const UInt32 *btBuf = p->btBuf + p->btBufPos;
+  UInt32 len = *btBuf++;
+  p->btBufPos += 1 + len;
+  p->btNumAvailBytes--;
+  {
+    UInt32 i;
+    for (i = 0; i < len; i += 2)
+    {
+      UInt32 v0 = btBuf[0];
+      UInt32 v1 = btBuf[1];
+      btBuf += 2;
+      distances[0] = v0;
+      distances[1] = v1;
+      distances += 2;
+    }
+  }
+  INCREASE_LZ_POS
+  return len;
+}
+
+static UInt32 MatchFinderMt_GetMatches(CMatchFinderMt *p, UInt32 *distances)
+{
+  const UInt32 *btBuf = p->btBuf + p->btBufPos;
+  UInt32 len = *btBuf++;
+  p->btBufPos += 1 + len;
+
+  if (len == 0)
+  {
+    /* change for bt5 ! */
+    if (p->btNumAvailBytes-- >= 4)
+      len = (UInt32)(p->MixMatchesFunc(p, p->lzPos - p->historySize, distances) - (distances));
+  }
+  else
+  {
+    /* Condition: there are matches in btBuf with length < p->numHashBytes */
+    UInt32 *distances2;
+    p->btNumAvailBytes--;
+    distances2 = p->MixMatchesFunc(p, p->lzPos - btBuf[1], distances);
+    do
+    {
+      UInt32 v0 = btBuf[0];
+      UInt32 v1 = btBuf[1];
+      btBuf += 2;
+      distances2[0] = v0;
+      distances2[1] = v1;
+      distances2 += 2;
+    }
+    while ((len -= 2) != 0);
+    len = (UInt32)(distances2 - (distances));
+  }
+  INCREASE_LZ_POS
+  return len;
+}
+
+#define SKIP_HEADER2_MT  do { GET_NEXT_BLOCK_IF_REQUIRED
+#define SKIP_HEADER_MT(n) SKIP_HEADER2_MT if (p->btNumAvailBytes-- >= (n)) { const Byte *cur = p->pointerToCurPos; UInt32 *hash = p->hash;
+#define SKIP_FOOTER_MT } INCREASE_LZ_POS p->btBufPos += p->btBuf[p->btBufPos] + 1; } while (--num != 0);
+
+static void MatchFinderMt0_Skip(CMatchFinderMt *p, UInt32 num)
+{
+  SKIP_HEADER2_MT { p->btNumAvailBytes--;
+  SKIP_FOOTER_MT
+}
+
+static void MatchFinderMt2_Skip(CMatchFinderMt *p, UInt32 num)
+{
+  SKIP_HEADER_MT(2)
+      UInt32 h2;
+      MT_HASH2_CALC
+      hash[h2] = p->lzPos;
+  SKIP_FOOTER_MT
+}
+
+static void MatchFinderMt3_Skip(CMatchFinderMt *p, UInt32 num)
+{
+  SKIP_HEADER_MT(3)
+      UInt32 h2, h3;
+      MT_HASH3_CALC
+      (hash + kFix3HashSize)[h3] =
+      hash[                h2] =
+        p->lzPos;
+  SKIP_FOOTER_MT
+}
+
+/*
+static void MatchFinderMt4_Skip(CMatchFinderMt *p, UInt32 num)
+{
+  SKIP_HEADER_MT(4)
+      UInt32 h2, h3, h4;
+      MT_HASH4_CALC
+      (hash + kFix4HashSize)[h4] =
+      (hash + kFix3HashSize)[h3] =
+      hash[                h2] =
+        p->lzPos;
+  SKIP_FOOTER_MT
+}
+*/
+
+void MatchFinderMt_CreateVTable(CMatchFinderMt *p, IMatchFinder *vTable)
+{
+  vTable->Init = (Mf_Init_Func)MatchFinderMt_Init;
+  vTable->GetNumAvailableBytes = (Mf_GetNumAvailableBytes_Func)MatchFinderMt_GetNumAvailableBytes;
+  vTable->GetPointerToCurrentPos = (Mf_GetPointerToCurrentPos_Func)MatchFinderMt_GetPointerToCurrentPos;
+  vTable->GetMatches = (Mf_GetMatches_Func)MatchFinderMt_GetMatches;
+  
+  switch (p->MatchFinder->numHashBytes)
+  {
+    case 2:
+      p->GetHeadsFunc = GetHeads2;
+      p->MixMatchesFunc = (Mf_Mix_Matches)NULL;
+      vTable->Skip = (Mf_Skip_Func)MatchFinderMt0_Skip;
+      vTable->GetMatches = (Mf_GetMatches_Func)MatchFinderMt2_GetMatches;
+      break;
+    case 3:
+      p->GetHeadsFunc = GetHeads3;
+      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches2;
+      vTable->Skip = (Mf_Skip_Func)MatchFinderMt2_Skip;
+      break;
+    default:
+    /* case 4: */
+      p->GetHeadsFunc = p->MatchFinder->bigHash ? GetHeads4b : GetHeads4;
+      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches3;
+      vTable->Skip = (Mf_Skip_Func)MatchFinderMt3_Skip;
+      break;
+    /*
+    default:
+      p->GetHeadsFunc = GetHeads5;
+      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches4;
+      vTable->Skip = (Mf_Skip_Func)MatchFinderMt4_Skip;
+      break;
+    */
+  }
+}
@@ -0,0 +1,101 @@
+/* LzFindMt.h -- multithreaded Match finder for LZ algorithms
+2018-07-04 : Igor Pavlov : Public domain */
+
+#ifndef __LZ_FIND_MT_H
+#define __LZ_FIND_MT_H
+
+#include "LzFind.h"
+#include "Threads.h"
+
+EXTERN_C_BEGIN
+
+#define kMtHashBlockSize (1 << 13)
+#define kMtHashNumBlocks (1 << 3)
+#define kMtHashNumBlocksMask (kMtHashNumBlocks - 1)
+
+#define kMtBtBlockSize (1 << 14)
+#define kMtBtNumBlocks (1 << 6)
+#define kMtBtNumBlocksMask (kMtBtNumBlocks - 1)
+
+typedef struct _CMtSync
+{
+  BoolInt wasCreated;
+  BoolInt needStart;
+  BoolInt exit;
+  BoolInt stopWriting;
+
+  CThread thread;
+  CAutoResetEvent canStart;
+  CAutoResetEvent wasStarted;
+  CAutoResetEvent wasStopped;
+  CSemaphore freeSemaphore;
+  CSemaphore filledSemaphore;
+  BoolInt csWasInitialized;
+  BoolInt csWasEntered;
+  CCriticalSection cs;
+  UInt32 numProcessedBlocks;
+} CMtSync;
+
+typedef UInt32 * (*Mf_Mix_Matches)(void *p, UInt32 matchMinPos, UInt32 *distances);
+
+/* kMtCacheLineDummy must be >= size_of_CPU_cache_line */
+#define kMtCacheLineDummy 128
+
+typedef void (*Mf_GetHeads)(const Byte *buffer, UInt32 pos,
+  UInt32 *hash, UInt32 hashMask, UInt32 *heads, UInt32 numHeads, const UInt32 *crc);
+
+typedef struct _CMatchFinderMt
+{
+  /* LZ */
+  const Byte *pointerToCurPos;
+  UInt32 *btBuf;
+  UInt32 btBufPos;
+  UInt32 btBufPosLimit;
+  UInt32 lzPos;
+  UInt32 btNumAvailBytes;
+
+  UInt32 *hash;
+  UInt32 fixedHashSize;
+  UInt32 historySize;
+  const UInt32 *crc;
+
+  Mf_Mix_Matches MixMatchesFunc;
+  
+  /* LZ + BT */
+  CMtSync btSync;
+  Byte btDummy[kMtCacheLineDummy];
+
+  /* BT */
+  UInt32 *hashBuf;
+  UInt32 hashBufPos;
+  UInt32 hashBufPosLimit;
+  UInt32 hashNumAvail;
+
+  CLzRef *son;
+  UInt32 matchMaxLen;
+  UInt32 numHashBytes;
+  UInt32 pos;
+  const Byte *buffer;
+  UInt32 cyclicBufferPos;
+  UInt32 cyclicBufferSize; /* it must be historySize + 1 */
+  UInt32 cutValue;
+
+  /* BT + Hash */
+  CMtSync hashSync;
+  /* Byte hashDummy[kMtCacheLineDummy]; */
+  
+  /* Hash */
+  Mf_GetHeads GetHeadsFunc;
+  CMatchFinder *MatchFinder;
+} CMatchFinderMt;
+
+void MatchFinderMt_Construct(CMatchFinderMt *p);
+void MatchFinderMt_Destruct(CMatchFinderMt *p, ISzAllocPtr alloc);
+SRes MatchFinderMt_Create(CMatchFinderMt *p, UInt32 historySize, UInt32 keepAddBufferBefore,
+    UInt32 matchMaxLen, UInt32 keepAddBufferAfter, ISzAllocPtr alloc);
+void MatchFinderMt_CreateVTable(CMatchFinderMt *p, IMatchFinder *vTable);
+void MatchFinderMt_ReleaseStream(CMatchFinderMt *p);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,57 @@
+/* LzHash.h -- HASH functions for LZ algorithms
+2015-04-12 : Igor Pavlov : Public domain */
+
+#ifndef __LZ_HASH_H
+#define __LZ_HASH_H
+
+#define kHash2Size (1 << 10)
+#define kHash3Size (1 << 16)
+#define kHash4Size (1 << 20)
+
+#define kFix3HashSize (kHash2Size)
+#define kFix4HashSize (kHash2Size + kHash3Size)
+#define kFix5HashSize (kHash2Size + kHash3Size + kHash4Size)
+
+#define HASH2_CALC hv = cur[0] | ((UInt32)cur[1] << 8);
+
+#define HASH3_CALC { \
+  UInt32 temp = p->crc[cur[0]] ^ cur[1]; \
+  h2 = temp & (kHash2Size - 1); \
+  hv = (temp ^ ((UInt32)cur[2] << 8)) & p->hashMask; }
+
+#define HASH4_CALC { \
+  UInt32 temp = p->crc[cur[0]] ^ cur[1]; \
+  h2 = temp & (kHash2Size - 1); \
+  temp ^= ((UInt32)cur[2] << 8); \
+  h3 = temp & (kHash3Size - 1); \
+  hv = (temp ^ (p->crc[cur[3]] << 5)) & p->hashMask; }
+
+#define HASH5_CALC { \
+  UInt32 temp = p->crc[cur[0]] ^ cur[1]; \
+  h2 = temp & (kHash2Size - 1); \
+  temp ^= ((UInt32)cur[2] << 8); \
+  h3 = temp & (kHash3Size - 1); \
+  temp ^= (p->crc[cur[3]] << 5); \
+  h4 = temp & (kHash4Size - 1); \
+  hv = (temp ^ (p->crc[cur[4]] << 3)) & p->hashMask; }
+
+/* #define HASH_ZIP_CALC hv = ((cur[0] | ((UInt32)cur[1] << 8)) ^ p->crc[cur[2]]) & 0xFFFF; */
+#define HASH_ZIP_CALC hv = ((cur[2] | ((UInt32)cur[0] << 8)) ^ p->crc[cur[1]]) & 0xFFFF;
+
+
+#define MT_HASH2_CALC \
+  h2 = (p->crc[cur[0]] ^ cur[1]) & (kHash2Size - 1);
+
+#define MT_HASH3_CALC { \
+  UInt32 temp = p->crc[cur[0]] ^ cur[1]; \
+  h2 = temp & (kHash2Size - 1); \
+  h3 = (temp ^ ((UInt32)cur[2] << 8)) & (kHash3Size - 1); }
+
+#define MT_HASH4_CALC { \
+  UInt32 temp = p->crc[cur[0]] ^ cur[1]; \
+  h2 = temp & (kHash2Size - 1); \
+  temp ^= ((UInt32)cur[2] << 8); \
+  h3 = temp & (kHash3Size - 1); \
+  h4 = (temp ^ (p->crc[cur[3]] << 5)) & (kHash4Size - 1); }
+
+#endif
@@ -0,0 +1,488 @@
+/* Lzma2Dec.c -- LZMA2 Decoder
+2019-02-02 : Igor Pavlov : Public domain */
+
+/* #define SHOW_DEBUG_INFO */
+
+#include "Precomp.h"
+
+#ifdef SHOW_DEBUG_INFO
+#include <stdio.h>
+#endif
+
+#include <string.h>
+
+#include "Lzma2Dec.h"
+
+/*
+00000000  -  End of data
+00000001 U U  -  Uncompressed, reset dic, need reset state and set new prop
+00000010 U U  -  Uncompressed, no reset
+100uuuuu U U P P  -  LZMA, no reset
+101uuuuu U U P P  -  LZMA, reset state
+110uuuuu U U P P S  -  LZMA, reset state + set new prop
+111uuuuu U U P P S  -  LZMA, reset state + set new prop, reset dic
+
+  u, U - Unpack Size
+  P - Pack Size
+  S - Props
+*/
+
+#define LZMA2_CONTROL_COPY_RESET_DIC 1
+
+#define LZMA2_IS_UNCOMPRESSED_STATE(p) (((p)->control & (1 << 7)) == 0)
+
+#define LZMA2_LCLP_MAX 4
+#define LZMA2_DIC_SIZE_FROM_PROP(p) (((UInt32)2 | ((p) & 1)) << ((p) / 2 + 11))
+
+#ifdef SHOW_DEBUG_INFO
+#define PRF(x) x
+#else
+#define PRF(x)
+#endif
+
+typedef enum
+{
+  LZMA2_STATE_CONTROL,
+  LZMA2_STATE_UNPACK0,
+  LZMA2_STATE_UNPACK1,
+  LZMA2_STATE_PACK0,
+  LZMA2_STATE_PACK1,
+  LZMA2_STATE_PROP,
+  LZMA2_STATE_DATA,
+  LZMA2_STATE_DATA_CONT,
+  LZMA2_STATE_FINISHED,
+  LZMA2_STATE_ERROR
+} ELzma2State;
+
+static SRes Lzma2Dec_GetOldProps(Byte prop, Byte *props)
+{
+  UInt32 dicSize;
+  if (prop > 40)
+    return SZ_ERROR_UNSUPPORTED;
+  dicSize = (prop == 40) ? 0xFFFFFFFF : LZMA2_DIC_SIZE_FROM_PROP(prop);
+  props[0] = (Byte)LZMA2_LCLP_MAX;
+  props[1] = (Byte)(dicSize);
+  props[2] = (Byte)(dicSize >> 8);
+  props[3] = (Byte)(dicSize >> 16);
+  props[4] = (Byte)(dicSize >> 24);
+  return SZ_OK;
+}
+
+SRes Lzma2Dec_AllocateProbs(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc)
+{
+  Byte props[LZMA_PROPS_SIZE];
+  RINOK(Lzma2Dec_GetOldProps(prop, props));
+  return LzmaDec_AllocateProbs(&p->decoder, props, LZMA_PROPS_SIZE, alloc);
+}
+
+SRes Lzma2Dec_Allocate(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc)
+{
+  Byte props[LZMA_PROPS_SIZE];
+  RINOK(Lzma2Dec_GetOldProps(prop, props));
+  return LzmaDec_Allocate(&p->decoder, props, LZMA_PROPS_SIZE, alloc);
+}
+
+void Lzma2Dec_Init(CLzma2Dec *p)
+{
+  p->state = LZMA2_STATE_CONTROL;
+  p->needInitLevel = 0xE0;
+  p->isExtraMode = False;
+  p->unpackSize = 0;
+  
+  // p->decoder.dicPos = 0; // we can use it instead of full init
+  LzmaDec_Init(&p->decoder);
+}
+
+static ELzma2State Lzma2Dec_UpdateState(CLzma2Dec *p, Byte b)
+{
+  switch (p->state)
+  {
+    case LZMA2_STATE_CONTROL:
+      p->isExtraMode = False;
+      p->control = b;
+      PRF(printf("\n %8X", (unsigned)p->decoder.dicPos));
+      PRF(printf(" %02X", (unsigned)b));
+      if (b == 0)
+        return LZMA2_STATE_FINISHED;
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (b == LZMA2_CONTROL_COPY_RESET_DIC)
+          p->needInitLevel = 0xC0;
+        else if (b > 2 || p->needInitLevel == 0xE0)
+          return LZMA2_STATE_ERROR;
+      }
+      else
+      {
+        if (b < p->needInitLevel)
+          return LZMA2_STATE_ERROR;
+        p->needInitLevel = 0;
+        p->unpackSize = (UInt32)(b & 0x1F) << 16;
+      }
+      return LZMA2_STATE_UNPACK0;
+    
+    case LZMA2_STATE_UNPACK0:
+      p->unpackSize |= (UInt32)b << 8;
+      return LZMA2_STATE_UNPACK1;
+    
+    case LZMA2_STATE_UNPACK1:
+      p->unpackSize |= (UInt32)b;
+      p->unpackSize++;
+      PRF(printf(" %7u", (unsigned)p->unpackSize));
+      return LZMA2_IS_UNCOMPRESSED_STATE(p) ? LZMA2_STATE_DATA : LZMA2_STATE_PACK0;
+    
+    case LZMA2_STATE_PACK0:
+      p->packSize = (UInt32)b << 8;
+      return LZMA2_STATE_PACK1;
+
+    case LZMA2_STATE_PACK1:
+      p->packSize |= (UInt32)b;
+      p->packSize++;
+      // if (p->packSize < 5) return LZMA2_STATE_ERROR;
+      PRF(printf(" %5u", (unsigned)p->packSize));
+      return (p->control & 0x40) ? LZMA2_STATE_PROP : LZMA2_STATE_DATA;
+
+    case LZMA2_STATE_PROP:
+    {
+      unsigned lc, lp;
+      if (b >= (9 * 5 * 5))
+        return LZMA2_STATE_ERROR;
+      lc = b % 9;
+      b /= 9;
+      p->decoder.prop.pb = (Byte)(b / 5);
+      lp = b % 5;
+      if (lc + lp > LZMA2_LCLP_MAX)
+        return LZMA2_STATE_ERROR;
+      p->decoder.prop.lc = (Byte)lc;
+      p->decoder.prop.lp = (Byte)lp;
+      return LZMA2_STATE_DATA;
+    }
+  }
+  return LZMA2_STATE_ERROR;
+}
+
+static void LzmaDec_UpdateWithUncompressed(CLzmaDec *p, const Byte *src, SizeT size)
+{
+  memcpy(p->dic + p->dicPos, src, size);
+  p->dicPos += size;
+  if (p->checkDicSize == 0 && p->prop.dicSize - p->processedPos <= size)
+    p->checkDicSize = p->prop.dicSize;
+  p->processedPos += (UInt32)size;
+}
+
+void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState);
+
+
+SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status)
+{
+  SizeT inSize = *srcLen;
+  *srcLen = 0;
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+
+  while (p->state != LZMA2_STATE_ERROR)
+  {
+    SizeT dicPos;
+
+    if (p->state == LZMA2_STATE_FINISHED)
+    {
+      *status = LZMA_STATUS_FINISHED_WITH_MARK;
+      return SZ_OK;
+    }
+    
+    dicPos = p->decoder.dicPos;
+    
+    if (dicPos == dicLimit && finishMode == LZMA_FINISH_ANY)
+    {
+      *status = LZMA_STATUS_NOT_FINISHED;
+      return SZ_OK;
+    }
+
+    if (p->state != LZMA2_STATE_DATA && p->state != LZMA2_STATE_DATA_CONT)
+    {
+      if (*srcLen == inSize)
+      {
+        *status = LZMA_STATUS_NEEDS_MORE_INPUT;
+        return SZ_OK;
+      }
+      (*srcLen)++;
+      p->state = Lzma2Dec_UpdateState(p, *src++);
+      if (dicPos == dicLimit && p->state != LZMA2_STATE_FINISHED)
+        break;
+      continue;
+    }
+    
+    {
+      SizeT inCur = inSize - *srcLen;
+      SizeT outCur = dicLimit - dicPos;
+      ELzmaFinishMode curFinishMode = LZMA_FINISH_ANY;
+      
+      if (outCur >= p->unpackSize)
+      {
+        outCur = (SizeT)p->unpackSize;
+        curFinishMode = LZMA_FINISH_END;
+      }
+
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (inCur == 0)
+        {
+          *status = LZMA_STATUS_NEEDS_MORE_INPUT;
+          return SZ_OK;
+        }
+
+        if (p->state == LZMA2_STATE_DATA)
+        {
+          BoolInt initDic = (p->control == LZMA2_CONTROL_COPY_RESET_DIC);
+          LzmaDec_InitDicAndState(&p->decoder, initDic, False);
+        }
+
+        if (inCur > outCur)
+          inCur = outCur;
+        if (inCur == 0)
+          break;
+
+        LzmaDec_UpdateWithUncompressed(&p->decoder, src, inCur);
+
+        src += inCur;
+        *srcLen += inCur;
+        p->unpackSize -= (UInt32)inCur;
+        p->state = (p->unpackSize == 0) ? LZMA2_STATE_CONTROL : LZMA2_STATE_DATA_CONT;
+      }
+      else
+      {
+        SRes res;
+
+        if (p->state == LZMA2_STATE_DATA)
+        {
+          BoolInt initDic = (p->control >= 0xE0);
+          BoolInt initState = (p->control >= 0xA0);
+          LzmaDec_InitDicAndState(&p->decoder, initDic, initState);
+          p->state = LZMA2_STATE_DATA_CONT;
+        }
+  
+        if (inCur > p->packSize)
+          inCur = (SizeT)p->packSize;
+        
+        res = LzmaDec_DecodeToDic(&p->decoder, dicPos + outCur, src, &inCur, curFinishMode, status);
+
+        src += inCur;
+        *srcLen += inCur;
+        p->packSize -= (UInt32)inCur;
+        outCur = p->decoder.dicPos - dicPos;
+        p->unpackSize -= (UInt32)outCur;
+
+        if (res != 0)
+          break;
+        
+        if (*status == LZMA_STATUS_NEEDS_MORE_INPUT)
+        {
+          if (p->packSize == 0)
+            break;
+          return SZ_OK;
+        }
+
+        if (inCur == 0 && outCur == 0)
+        {
+          if (*status != LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK
+              || p->unpackSize != 0
+              || p->packSize != 0)
+            break;
+          p->state = LZMA2_STATE_CONTROL;
+        }
+        
+        *status = LZMA_STATUS_NOT_SPECIFIED;
+      }
+    }
+  }
+  
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+  p->state = LZMA2_STATE_ERROR;
+  return SZ_ERROR_DATA;
+}
+
+
+
+
+ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
+    SizeT outSize,
+    const Byte *src, SizeT *srcLen,
+    int checkFinishBlock)
+{
+  SizeT inSize = *srcLen;
+  *srcLen = 0;
+
+  while (p->state != LZMA2_STATE_ERROR)
+  {
+    if (p->state == LZMA2_STATE_FINISHED)
+      return (ELzma2ParseStatus)LZMA_STATUS_FINISHED_WITH_MARK;
+
+    if (outSize == 0 && !checkFinishBlock)
+      return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+    
+    if (p->state != LZMA2_STATE_DATA && p->state != LZMA2_STATE_DATA_CONT)
+    {
+      if (*srcLen == inSize)
+        return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+      (*srcLen)++;
+
+      p->state = Lzma2Dec_UpdateState(p, *src++);
+
+      if (p->state == LZMA2_STATE_UNPACK0)
+      {
+        // if (p->decoder.dicPos != 0)
+        if (p->control == LZMA2_CONTROL_COPY_RESET_DIC || p->control >= 0xE0)
+          return LZMA2_PARSE_STATUS_NEW_BLOCK;
+        // if (outSize == 0) return LZMA_STATUS_NOT_FINISHED;
+      }
+
+      // The following code can be commented.
+      // It's not big problem, if we read additional input bytes.
+      // It will be stopped later in LZMA2_STATE_DATA / LZMA2_STATE_DATA_CONT state.
+
+      if (outSize == 0 && p->state != LZMA2_STATE_FINISHED)
+      {
+        // checkFinishBlock is true. So we expect that block must be finished,
+        // We can return LZMA_STATUS_NOT_SPECIFIED or LZMA_STATUS_NOT_FINISHED here
+        // break;
+        return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+      }
+
+      if (p->state == LZMA2_STATE_DATA)
+        return LZMA2_PARSE_STATUS_NEW_CHUNK;
+
+      continue;
+    }
+
+    if (outSize == 0)
+      return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+
+    {
+      SizeT inCur = inSize - *srcLen;
+
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (inCur == 0)
+          return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+        if (inCur > p->unpackSize)
+          inCur = p->unpackSize;
+        if (inCur > outSize)
+          inCur = outSize;
+        p->decoder.dicPos += inCur;
+        src += inCur;
+        *srcLen += inCur;
+        outSize -= inCur;
+        p->unpackSize -= (UInt32)inCur;
+        p->state = (p->unpackSize == 0) ? LZMA2_STATE_CONTROL : LZMA2_STATE_DATA_CONT;
+      }
+      else
+      {
+        p->isExtraMode = True;
+
+        if (inCur == 0)
+        {
+          if (p->packSize != 0)
+            return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+        }
+        else if (p->state == LZMA2_STATE_DATA)
+        {
+          p->state = LZMA2_STATE_DATA_CONT;
+          if (*src != 0)
+          {
+            // first byte of lzma chunk must be Zero
+            *srcLen += 1;
+            p->packSize--;
+            break;
+          }
+        }
+  
+        if (inCur > p->packSize)
+          inCur = (SizeT)p->packSize;
+
+        src += inCur;
+        *srcLen += inCur;
+        p->packSize -= (UInt32)inCur;
+
+        if (p->packSize == 0)
+        {
+          SizeT rem = outSize;
+          if (rem > p->unpackSize)
+            rem = p->unpackSize;
+          p->decoder.dicPos += rem;
+          p->unpackSize -= (UInt32)rem;
+          outSize -= rem;
+          if (p->unpackSize == 0)
+            p->state = LZMA2_STATE_CONTROL;
+        }
+      }
+    }
+  }
+  
+  p->state = LZMA2_STATE_ERROR;
+  return (ELzma2ParseStatus)LZMA_STATUS_NOT_SPECIFIED;
+}
+
+
+
+
+SRes Lzma2Dec_DecodeToBuf(CLzma2Dec *p, Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status)
+{
+  SizeT outSize = *destLen, inSize = *srcLen;
+  *srcLen = *destLen = 0;
+  
+  for (;;)
+  {
+    SizeT inCur = inSize, outCur, dicPos;
+    ELzmaFinishMode curFinishMode;
+    SRes res;
+    
+    if (p->decoder.dicPos == p->decoder.dicBufSize)
+      p->decoder.dicPos = 0;
+    dicPos = p->decoder.dicPos;
+    curFinishMode = LZMA_FINISH_ANY;
+    outCur = p->decoder.dicBufSize - dicPos;
+    
+    if (outCur >= outSize)
+    {
+      outCur = outSize;
+      curFinishMode = finishMode;
+    }
+
+    res = Lzma2Dec_DecodeToDic(p, dicPos + outCur, src, &inCur, curFinishMode, status);
+    
+    src += inCur;
+    inSize -= inCur;
+    *srcLen += inCur;
+    outCur = p->decoder.dicPos - dicPos;
+    memcpy(dest, p->decoder.dic + dicPos, outCur);
+    dest += outCur;
+    outSize -= outCur;
+    *destLen += outCur;
+    if (res != 0)
+      return res;
+    if (outCur == 0 || outSize == 0)
+      return SZ_OK;
+  }
+}
+
+
+SRes Lzma2Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+    Byte prop, ELzmaFinishMode finishMode, ELzmaStatus *status, ISzAllocPtr alloc)
+{
+  CLzma2Dec p;
+  SRes res;
+  SizeT outSize = *destLen, inSize = *srcLen;
+  *destLen = *srcLen = 0;
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+  Lzma2Dec_Construct(&p);
+  RINOK(Lzma2Dec_AllocateProbs(&p, prop, alloc));
+  p.decoder.dic = dest;
+  p.decoder.dicBufSize = outSize;
+  Lzma2Dec_Init(&p);
+  *srcLen = inSize;
+  res = Lzma2Dec_DecodeToDic(&p, outSize, src, srcLen, finishMode, status);
+  *destLen = p.decoder.dicPos;
+  if (res == SZ_OK && *status == LZMA_STATUS_NEEDS_MORE_INPUT)
+    res = SZ_ERROR_INPUT_EOF;
+  Lzma2Dec_FreeProbs(&p, alloc);
+  return res;
+}
@@ -0,0 +1,120 @@
+/* Lzma2Dec.h -- LZMA2 Decoder
+2018-02-19 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_DEC_H
+#define __LZMA2_DEC_H
+
+#include "LzmaDec.h"
+
+EXTERN_C_BEGIN
+
+/* ---------- State Interface ---------- */
+
+typedef struct
+{
+  unsigned state;
+  Byte control;
+  Byte needInitLevel;
+  Byte isExtraMode;
+  Byte _pad_;
+  UInt32 packSize;
+  UInt32 unpackSize;
+  CLzmaDec decoder;
+} CLzma2Dec;
+
+#define Lzma2Dec_Construct(p) LzmaDec_Construct(&(p)->decoder)
+#define Lzma2Dec_FreeProbs(p, alloc) LzmaDec_FreeProbs(&(p)->decoder, alloc)
+#define Lzma2Dec_Free(p, alloc) LzmaDec_Free(&(p)->decoder, alloc)
+
+SRes Lzma2Dec_AllocateProbs(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc);
+SRes Lzma2Dec_Allocate(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc);
+void Lzma2Dec_Init(CLzma2Dec *p);
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen or dicLimit).
+  LZMA_FINISH_ANY - use smallest number of input bytes
+  LZMA_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+      LZMA_STATUS_NEEDS_MORE_INPUT
+  SZ_ERROR_DATA - Data error
+*/
+
+SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+SRes Lzma2Dec_DecodeToBuf(CLzma2Dec *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+
+/* ---------- LZMA2 block and chunk parsing ---------- */
+
+/*
+Lzma2Dec_Parse() parses compressed data stream up to next independent block or next chunk data.
+It can return LZMA_STATUS_* code or LZMA2_PARSE_STATUS_* code:
+  - LZMA2_PARSE_STATUS_NEW_BLOCK - there is new block, and 1 additional byte (control byte of next block header) was read from input.
+  - LZMA2_PARSE_STATUS_NEW_CHUNK - there is new chunk, and only lzma2 header of new chunk was read.
+                                   CLzma2Dec::unpackSize contains unpack size of that chunk
+*/
+
+typedef enum
+{
+/*
+  LZMA_STATUS_NOT_SPECIFIED                 // data error
+  LZMA_STATUS_FINISHED_WITH_MARK
+  LZMA_STATUS_NOT_FINISHED                  //
+  LZMA_STATUS_NEEDS_MORE_INPUT
+  LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK   // unused
+*/
+  LZMA2_PARSE_STATUS_NEW_BLOCK = LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK + 1,
+  LZMA2_PARSE_STATUS_NEW_CHUNK
+} ELzma2ParseStatus;
+
+ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
+    SizeT outSize,   // output size
+    const Byte *src, SizeT *srcLen,
+    int checkFinishBlock   // set (checkFinishBlock = 1), if it must read full input data, if decoder.dicPos reaches blockMax position.
+    );
+
+/*
+LZMA2 parser doesn't decode LZMA chunks, so we must read
+  full input LZMA chunk to decode some part of LZMA chunk.
+
+Lzma2Dec_GetUnpackExtra() returns the value that shows
+    max possible number of output bytes that can be output by decoder
+    at current input positon.
+*/
+
+#define Lzma2Dec_GetUnpackExtra(p) ((p)->isExtraMode ? (p)->unpackSize : 0);
+
+
+/* ---------- One Call Interface ---------- */
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  LZMA_FINISH_ANY - use smallest number of input bytes
+  LZMA_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+  SZ_ERROR_DATA - Data error
+  SZ_ERROR_MEM  - Memory allocation error
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+  SZ_ERROR_INPUT_EOF - It needs more bytes in input buffer (src).
+*/
+
+SRes Lzma2Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+    Byte prop, ELzmaFinishMode finishMode, ELzmaStatus *status, ISzAllocPtr alloc);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,79 @@
+/* Lzma2DecMt.h -- LZMA2 Decoder Multi-thread
+2018-02-17 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_DEC_MT_H
+#define __LZMA2_DEC_MT_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+typedef struct
+{
+  size_t inBufSize_ST;
+  size_t outStep_ST;
+  
+  #ifndef _7ZIP_ST
+  unsigned numThreads;
+  size_t inBufSize_MT;
+  size_t outBlockMax;
+  size_t inBlockMax;
+  #endif
+} CLzma2DecMtProps;
+
+/* init to single-thread mode */
+void Lzma2DecMtProps_Init(CLzma2DecMtProps *p);
+
+
+/* ---------- CLzma2DecMtHandle Interface ---------- */
+
+/* Lzma2DecMt_ * functions can return the following exit codes:
+SRes:
+  SZ_OK           - OK
+  SZ_ERROR_MEM    - Memory allocation error
+  SZ_ERROR_PARAM  - Incorrect paramater in props
+  SZ_ERROR_WRITE  - ISeqOutStream write callback error
+  // SZ_ERROR_OUTPUT_EOF - output buffer overflow - version with (Byte *) output
+  SZ_ERROR_PROGRESS - some break from progress callback
+  SZ_ERROR_THREAD - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzma2DecMtHandle;
+
+CLzma2DecMtHandle Lzma2DecMt_Create(ISzAllocPtr alloc, ISzAllocPtr allocMid);
+void Lzma2DecMt_Destroy(CLzma2DecMtHandle p);
+
+SRes Lzma2DecMt_Decode(CLzma2DecMtHandle p,
+    Byte prop,
+    const CLzma2DecMtProps *props,
+    ISeqOutStream *outStream,
+    const UInt64 *outDataSize, // NULL means undefined
+    int finishMode,            // 0 - partial unpacking is allowed, 1 - if lzma2 stream must be finished
+    // Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    // const Byte *inData, size_t inDataSize,
+    
+    // out variables:
+    UInt64 *inProcessed,
+    int *isMT,  /* out: (*isMT == 0), if single thread decoding was used */
+
+    // UInt64 *outProcessed,
+    ICompressProgress *progress);
+
+
+/* ---------- Read from CLzma2DecMtHandle Interface ---------- */
+
+SRes Lzma2DecMt_Init(CLzma2DecMtHandle pp,
+    Byte prop,
+    const CLzma2DecMtProps *props,
+    const UInt64 *outDataSize, int finishMode,
+    ISeqInStream *inStream);
+
+SRes Lzma2DecMt_Read(CLzma2DecMtHandle pp,
+    Byte *data, size_t *outSize,
+    UInt64 *inStreamProcessed);
+
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,803 @@
+/* Lzma2Enc.c -- LZMA2 Encoder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+/* #define _7ZIP_ST */
+
+#include "Lzma2Enc.h"
+
+#ifndef _7ZIP_ST
+#include "MtCoder.h"
+#else
+#define MTCODER__THREADS_MAX 1
+#endif
+
+#define LZMA2_CONTROL_LZMA (1 << 7)
+#define LZMA2_CONTROL_COPY_NO_RESET 2
+#define LZMA2_CONTROL_COPY_RESET_DIC 1
+#define LZMA2_CONTROL_EOF 0
+
+#define LZMA2_LCLP_MAX 4
+
+#define LZMA2_DIC_SIZE_FROM_PROP(p) (((UInt32)2 | ((p) & 1)) << ((p) / 2 + 11))
+
+#define LZMA2_PACK_SIZE_MAX (1 << 16)
+#define LZMA2_COPY_CHUNK_SIZE LZMA2_PACK_SIZE_MAX
+#define LZMA2_UNPACK_SIZE_MAX (1 << 21)
+#define LZMA2_KEEP_WINDOW_SIZE LZMA2_UNPACK_SIZE_MAX
+
+#define LZMA2_CHUNK_SIZE_COMPRESSED_MAX ((1 << 16) + 16)
+
+
+#define PRF(x) /* x */
+
+
+/* ---------- CLimitedSeqInStream ---------- */
+
+typedef struct
+{
+  ISeqInStream vt;
+  ISeqInStream *realStream;
+  UInt64 limit;
+  UInt64 processed;
+  int finished;
+} CLimitedSeqInStream;
+
+static void LimitedSeqInStream_Init(CLimitedSeqInStream *p)
+{
+  p->limit = (UInt64)(Int64)-1;
+  p->processed = 0;
+  p->finished = 0;
+}
+
+static SRes LimitedSeqInStream_Read(const ISeqInStream *pp, void *data, size_t *size)
+{
+  CLimitedSeqInStream *p = CONTAINER_FROM_VTBL(pp, CLimitedSeqInStream, vt);
+  size_t size2 = *size;
+  SRes res = SZ_OK;
+  
+  if (p->limit != (UInt64)(Int64)-1)
+  {
+    UInt64 rem = p->limit - p->processed;
+    if (size2 > rem)
+      size2 = (size_t)rem;
+  }
+  if (size2 != 0)
+  {
+    res = ISeqInStream_Read(p->realStream, data, &size2);
+    p->finished = (size2 == 0 ? 1 : 0);
+    p->processed += size2;
+  }
+  *size = size2;
+  return res;
+}
+
+
+/* ---------- CLzma2EncInt ---------- */
+
+typedef struct
+{
+  CLzmaEncHandle enc;
+  Byte propsAreSet;
+  Byte propsByte;
+  Byte needInitState;
+  Byte needInitProp;
+  UInt64 srcPos;
+} CLzma2EncInt;
+
+
+static SRes Lzma2EncInt_InitStream(CLzma2EncInt *p, const CLzma2EncProps *props)
+{
+  if (!p->propsAreSet)
+  {
+    SizeT propsSize = LZMA_PROPS_SIZE;
+    Byte propsEncoded[LZMA_PROPS_SIZE];
+    RINOK(LzmaEnc_SetProps(p->enc, &props->lzmaProps));
+    RINOK(LzmaEnc_WriteProperties(p->enc, propsEncoded, &propsSize));
+    p->propsByte = propsEncoded[0];
+    p->propsAreSet = True;
+  }
+  return SZ_OK;
+}
+
+static void Lzma2EncInt_InitBlock(CLzma2EncInt *p)
+{
+  p->srcPos = 0;
+  p->needInitState = True;
+  p->needInitProp = True;
+}
+
+
+SRes LzmaEnc_PrepareForLzma2(CLzmaEncHandle pp, ISeqInStream *inStream, UInt32 keepWindowSize,
+    ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_MemPrepare(CLzmaEncHandle pp, const Byte *src, SizeT srcLen,
+    UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, BoolInt reInit,
+    Byte *dest, size_t *destLen, UInt32 desiredPackSize, UInt32 *unpackSize);
+const Byte *LzmaEnc_GetCurBuf(CLzmaEncHandle pp);
+void LzmaEnc_Finish(CLzmaEncHandle pp);
+void LzmaEnc_SaveState(CLzmaEncHandle pp);
+void LzmaEnc_RestoreState(CLzmaEncHandle pp);
+
+/*
+UInt32 LzmaEnc_GetNumAvailableBytes(CLzmaEncHandle pp);
+*/
+
+static SRes Lzma2EncInt_EncodeSubblock(CLzma2EncInt *p, Byte *outBuf,
+    size_t *packSizeRes, ISeqOutStream *outStream)
+{
+  size_t packSizeLimit = *packSizeRes;
+  size_t packSize = packSizeLimit;
+  UInt32 unpackSize = LZMA2_UNPACK_SIZE_MAX;
+  unsigned lzHeaderSize = 5 + (p->needInitProp ? 1 : 0);
+  BoolInt useCopyBlock;
+  SRes res;
+
+  *packSizeRes = 0;
+  if (packSize < lzHeaderSize)
+    return SZ_ERROR_OUTPUT_EOF;
+  packSize -= lzHeaderSize;
+  
+  LzmaEnc_SaveState(p->enc);
+  res = LzmaEnc_CodeOneMemBlock(p->enc, p->needInitState,
+      outBuf + lzHeaderSize, &packSize, LZMA2_PACK_SIZE_MAX, &unpackSize);
+  
+  PRF(printf("\npackSize = %7d unpackSize = %7d  ", packSize, unpackSize));
+
+  if (unpackSize == 0)
+    return res;
+
+  if (res == SZ_OK)
+    useCopyBlock = (packSize + 2 >= unpackSize || packSize > (1 << 16));
+  else
+  {
+    if (res != SZ_ERROR_OUTPUT_EOF)
+      return res;
+    res = SZ_OK;
+    useCopyBlock = True;
+  }
+
+  if (useCopyBlock)
+  {
+    size_t destPos = 0;
+    PRF(printf("################# COPY           "));
+
+    while (unpackSize > 0)
+    {
+      UInt32 u = (unpackSize < LZMA2_COPY_CHUNK_SIZE) ? unpackSize : LZMA2_COPY_CHUNK_SIZE;
+      if (packSizeLimit - destPos < u + 3)
+        return SZ_ERROR_OUTPUT_EOF;
+      outBuf[destPos++] = (Byte)(p->srcPos == 0 ? LZMA2_CONTROL_COPY_RESET_DIC : LZMA2_CONTROL_COPY_NO_RESET);
+      outBuf[destPos++] = (Byte)((u - 1) >> 8);
+      outBuf[destPos++] = (Byte)(u - 1);
+      memcpy(outBuf + destPos, LzmaEnc_GetCurBuf(p->enc) - unpackSize, u);
+      unpackSize -= u;
+      destPos += u;
+      p->srcPos += u;
+      
+      if (outStream)
+      {
+        *packSizeRes += destPos;
+        if (ISeqOutStream_Write(outStream, outBuf, destPos) != destPos)
+          return SZ_ERROR_WRITE;
+        destPos = 0;
+      }
+      else
+        *packSizeRes = destPos;
+      /* needInitState = True; */
+    }
+    
+    LzmaEnc_RestoreState(p->enc);
+    return SZ_OK;
+  }
+
+  {
+    size_t destPos = 0;
+    UInt32 u = unpackSize - 1;
+    UInt32 pm = (UInt32)(packSize - 1);
+    unsigned mode = (p->srcPos == 0) ? 3 : (p->needInitState ? (p->needInitProp ? 2 : 1) : 0);
+
+    PRF(printf("               "));
+
+    outBuf[destPos++] = (Byte)(LZMA2_CONTROL_LZMA | (mode << 5) | ((u >> 16) & 0x1F));
+    outBuf[destPos++] = (Byte)(u >> 8);
+    outBuf[destPos++] = (Byte)u;
+    outBuf[destPos++] = (Byte)(pm >> 8);
+    outBuf[destPos++] = (Byte)pm;
+    
+    if (p->needInitProp)
+      outBuf[destPos++] = p->propsByte;
+    
+    p->needInitProp = False;
+    p->needInitState = False;
+    destPos += packSize;
+    p->srcPos += unpackSize;
+
+    if (outStream)
+      if (ISeqOutStream_Write(outStream, outBuf, destPos) != destPos)
+        return SZ_ERROR_WRITE;
+    
+    *packSizeRes = destPos;
+    return SZ_OK;
+  }
+}
+
+
+/* ---------- Lzma2 Props ---------- */
+
+void Lzma2EncProps_Init(CLzma2EncProps *p)
+{
+  LzmaEncProps_Init(&p->lzmaProps);
+  p->blockSize = LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO;
+  p->numBlockThreads_Reduced = -1;
+  p->numBlockThreads_Max = -1;
+  p->numTotalThreads = -1;
+}
+
+void Lzma2EncProps_Normalize(CLzma2EncProps *p)
+{
+  UInt64 fileSize;
+  int t1, t1n, t2, t2r, t3;
+  {
+    CLzmaEncProps lzmaProps = p->lzmaProps;
+    LzmaEncProps_Normalize(&lzmaProps);
+    t1n = lzmaProps.numThreads;
+  }
+
+  t1 = p->lzmaProps.numThreads;
+  t2 = p->numBlockThreads_Max;
+  t3 = p->numTotalThreads;
+
+  if (t2 > MTCODER__THREADS_MAX)
+    t2 = MTCODER__THREADS_MAX;
+
+  if (t3 <= 0)
+  {
+    if (t2 <= 0)
+      t2 = 1;
+    t3 = t1n * t2;
+  }
+  else if (t2 <= 0)
+  {
+    t2 = t3 / t1n;
+    if (t2 == 0)
+    {
+      t1 = 1;
+      t2 = t3;
+    }
+    if (t2 > MTCODER__THREADS_MAX)
+      t2 = MTCODER__THREADS_MAX;
+  }
+  else if (t1 <= 0)
+  {
+    t1 = t3 / t2;
+    if (t1 == 0)
+      t1 = 1;
+  }
+  else
+    t3 = t1n * t2;
+
+  p->lzmaProps.numThreads = t1;
+
+  t2r = t2;
+
+  fileSize = p->lzmaProps.reduceSize;
+
+  if (   p->blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+      && p->blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO
+      && (p->blockSize < fileSize || fileSize == (UInt64)(Int64)-1))
+    p->lzmaProps.reduceSize = p->blockSize;
+
+  LzmaEncProps_Normalize(&p->lzmaProps);
+
+  p->lzmaProps.reduceSize = fileSize;
+
+  t1 = p->lzmaProps.numThreads;
+
+  if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID)
+  {
+    t2r = t2 = 1;
+    t3 = t1;
+  }
+  else if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO && t2 <= 1)
+  {
+    /* if there is no block multi-threading, we use SOLID block */
+    p->blockSize = LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID;
+  }
+  else
+  {
+    if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO)
+    {
+      const UInt32 kMinSize = (UInt32)1 << 20;
+      const UInt32 kMaxSize = (UInt32)1 << 28;
+      const UInt32 dictSize = p->lzmaProps.dictSize;
+      UInt64 blockSize = (UInt64)dictSize << 2;
+      if (blockSize < kMinSize) blockSize = kMinSize;
+      if (blockSize > kMaxSize) blockSize = kMaxSize;
+      if (blockSize < dictSize) blockSize = dictSize;
+      blockSize += (kMinSize - 1);
+      blockSize &= ~(UInt64)(kMinSize - 1);
+      p->blockSize = blockSize;
+    }
+    
+    if (t2 > 1 && fileSize != (UInt64)(Int64)-1)
+    {
+      UInt64 numBlocks = fileSize / p->blockSize;
+      if (numBlocks * p->blockSize != fileSize)
+        numBlocks++;
+      if (numBlocks < (unsigned)t2)
+      {
+        t2r = (unsigned)numBlocks;
+        if (t2r == 0)
+          t2r = 1;
+        t3 = t1 * t2r;
+      }
+    }
+  }
+  
+  p->numBlockThreads_Max = t2;
+  p->numBlockThreads_Reduced = t2r;
+  p->numTotalThreads = t3;
+}
+
+
+static SRes Progress(ICompressProgress *p, UInt64 inSize, UInt64 outSize)
+{
+  return (p && ICompressProgress_Progress(p, inSize, outSize) != SZ_OK) ? SZ_ERROR_PROGRESS : SZ_OK;
+}
+
+
+/* ---------- Lzma2 ---------- */
+
+typedef struct
+{
+  Byte propEncoded;
+  CLzma2EncProps props;
+  UInt64 expectedDataSize;
+  
+  Byte *tempBufLzma;
+
+  ISzAllocPtr alloc;
+  ISzAllocPtr allocBig;
+
+  CLzma2EncInt coders[MTCODER__THREADS_MAX];
+
+  #ifndef _7ZIP_ST
+  
+  ISeqOutStream *outStream;
+  Byte *outBuf;
+  size_t outBuf_Rem;   /* remainder in outBuf */
+
+  size_t outBufSize;   /* size of allocated outBufs[i] */
+  size_t outBufsDataSizes[MTCODER__BLOCKS_MAX];
+  BoolInt mtCoder_WasConstructed;
+  CMtCoder mtCoder;
+  Byte *outBufs[MTCODER__BLOCKS_MAX];
+
+  #endif
+
+} CLzma2Enc;
+
+
+
+CLzma2EncHandle Lzma2Enc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig)
+{
+  CLzma2Enc *p = (CLzma2Enc *)ISzAlloc_Alloc(alloc, sizeof(CLzma2Enc));
+  if (!p)
+    return NULL;
+  Lzma2EncProps_Init(&p->props);
+  Lzma2EncProps_Normalize(&p->props);
+  p->expectedDataSize = (UInt64)(Int64)-1;
+  p->tempBufLzma = NULL;
+  p->alloc = alloc;
+  p->allocBig = allocBig;
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__THREADS_MAX; i++)
+      p->coders[i].enc = NULL;
+  }
+  
+  #ifndef _7ZIP_ST
+  p->mtCoder_WasConstructed = False;
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+      p->outBufs[i] = NULL;
+    p->outBufSize = 0;
+  }
+  #endif
+
+  return p;
+}
+
+
+#ifndef _7ZIP_ST
+
+static void Lzma2Enc_FreeOutBufs(CLzma2Enc *p)
+{
+  unsigned i;
+  for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+    if (p->outBufs[i])
+    {
+      ISzAlloc_Free(p->alloc, p->outBufs[i]);
+      p->outBufs[i] = NULL;
+    }
+  p->outBufSize = 0;
+}
+
+#endif
+
+
+void Lzma2Enc_Destroy(CLzma2EncHandle pp)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  unsigned i;
+  for (i = 0; i < MTCODER__THREADS_MAX; i++)
+  {
+    CLzma2EncInt *t = &p->coders[i];
+    if (t->enc)
+    {
+      LzmaEnc_Destroy(t->enc, p->alloc, p->allocBig);
+      t->enc = NULL;
+    }
+  }
+
+
+  #ifndef _7ZIP_ST
+  if (p->mtCoder_WasConstructed)
+  {
+    MtCoder_Destruct(&p->mtCoder);
+    p->mtCoder_WasConstructed = False;
+  }
+  Lzma2Enc_FreeOutBufs(p);
+  #endif
+
+  ISzAlloc_Free(p->alloc, p->tempBufLzma);
+  p->tempBufLzma = NULL;
+
+  ISzAlloc_Free(p->alloc, pp);
+}
+
+
+SRes Lzma2Enc_SetProps(CLzma2EncHandle pp, const CLzma2EncProps *props)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  CLzmaEncProps lzmaProps = props->lzmaProps;
+  LzmaEncProps_Normalize(&lzmaProps);
+  if (lzmaProps.lc + lzmaProps.lp > LZMA2_LCLP_MAX)
+    return SZ_ERROR_PARAM;
+  p->props = *props;
+  Lzma2EncProps_Normalize(&p->props);
+  return SZ_OK;
+}
+
+
+void Lzma2Enc_SetDataSize(CLzmaEncHandle pp, UInt64 expectedDataSiize)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  p->expectedDataSize = expectedDataSiize;
+}
+
+
+Byte Lzma2Enc_WriteProperties(CLzma2EncHandle pp)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  unsigned i;
+  UInt32 dicSize = LzmaEncProps_GetDictSize(&p->props.lzmaProps);
+  for (i = 0; i < 40; i++)
+    if (dicSize <= LZMA2_DIC_SIZE_FROM_PROP(i))
+      break;
+  return (Byte)i;
+}
+
+
+static SRes Lzma2Enc_EncodeMt1(
+    CLzma2Enc *me,
+    CLzma2EncInt *p,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    int finished,
+    ICompressProgress *progress)
+{
+  UInt64 unpackTotal = 0;
+  UInt64 packTotal = 0;
+  size_t outLim = 0;
+  CLimitedSeqInStream limitedInStream;
+
+  if (outBuf)
+  {
+    outLim = *outBufSize;
+    *outBufSize = 0;
+  }
+
+  if (!p->enc)
+  {
+    p->propsAreSet = False;
+    p->enc = LzmaEnc_Create(me->alloc);
+    if (!p->enc)
+      return SZ_ERROR_MEM;
+  }
+
+  limitedInStream.realStream = inStream;
+  if (inStream)
+  {
+    limitedInStream.vt.Read = LimitedSeqInStream_Read;
+  }
+  
+  if (!outBuf)
+  {
+    // outStream version works only in one thread. So we use CLzma2Enc::tempBufLzma
+    if (!me->tempBufLzma)
+    {
+      me->tempBufLzma = (Byte *)ISzAlloc_Alloc(me->alloc, LZMA2_CHUNK_SIZE_COMPRESSED_MAX);
+      if (!me->tempBufLzma)
+        return SZ_ERROR_MEM;
+    }
+  }
+
+  RINOK(Lzma2EncInt_InitStream(p, &me->props));
+
+  for (;;)
+  {
+    SRes res = SZ_OK;
+    size_t inSizeCur = 0;
+
+    Lzma2EncInt_InitBlock(p);
+    
+    LimitedSeqInStream_Init(&limitedInStream);
+    limitedInStream.limit = me->props.blockSize;
+
+    if (inStream)
+    {
+      UInt64 expected = (UInt64)(Int64)-1;
+      // inStream version works only in one thread. So we use CLzma2Enc::expectedDataSize
+      if (me->expectedDataSize != (UInt64)(Int64)-1
+          && me->expectedDataSize >= unpackTotal)
+        expected = me->expectedDataSize - unpackTotal;
+      if (me->props.blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+          && expected > me->props.blockSize)
+        expected = (size_t)me->props.blockSize;
+
+      LzmaEnc_SetDataSize(p->enc, expected);
+
+      RINOK(LzmaEnc_PrepareForLzma2(p->enc,
+          &limitedInStream.vt,
+          LZMA2_KEEP_WINDOW_SIZE,
+          me->alloc,
+          me->allocBig));
+    }
+    else
+    {
+      inSizeCur = inDataSize - (size_t)unpackTotal;
+      if (me->props.blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+          && inSizeCur > me->props.blockSize)
+        inSizeCur = (size_t)me->props.blockSize;
+    
+      // LzmaEnc_SetDataSize(p->enc, inSizeCur);
+      
+      RINOK(LzmaEnc_MemPrepare(p->enc,
+          inData + (size_t)unpackTotal, inSizeCur,
+          LZMA2_KEEP_WINDOW_SIZE,
+          me->alloc,
+          me->allocBig));
+    }
+
+    for (;;)
+    {
+      size_t packSize = LZMA2_CHUNK_SIZE_COMPRESSED_MAX;
+      if (outBuf)
+        packSize = outLim - (size_t)packTotal;
+      
+      res = Lzma2EncInt_EncodeSubblock(p,
+          outBuf ? outBuf + (size_t)packTotal : me->tempBufLzma, &packSize,
+          outBuf ? NULL : outStream);
+      
+      if (res != SZ_OK)
+        break;
+
+      packTotal += packSize;
+      if (outBuf)
+        *outBufSize = (size_t)packTotal;
+      
+      res = Progress(progress, unpackTotal + p->srcPos, packTotal);
+      if (res != SZ_OK)
+        break;
+
+      /*
+      if (LzmaEnc_GetNumAvailableBytes(p->enc) == 0)
+        break;
+      */
+
+      if (packSize == 0)
+        break;
+    }
+    
+    LzmaEnc_Finish(p->enc);
+    
+    unpackTotal += p->srcPos;
+    
+    RINOK(res);
+
+    if (p->srcPos != (inStream ? limitedInStream.processed : inSizeCur))
+      return SZ_ERROR_FAIL;
+    
+    if (inStream ? limitedInStream.finished : (unpackTotal == inDataSize))
+    {
+      if (finished)
+      {
+        if (outBuf)
+        {
+          size_t destPos = *outBufSize;
+          if (destPos >= outLim)
+            return SZ_ERROR_OUTPUT_EOF;
+          outBuf[destPos] = 0;
+          *outBufSize = destPos + 1;
+        }
+        else
+        {
+          Byte b = 0;
+          if (ISeqOutStream_Write(outStream, &b, 1) != 1)
+            return SZ_ERROR_WRITE;
+        }
+      }
+      return SZ_OK;
+    }
+  }
+}
+
+
+
+#ifndef _7ZIP_ST
+
+static SRes Lzma2Enc_MtCallback_Code(void *pp, unsigned coderIndex, unsigned outBufIndex,
+    const Byte *src, size_t srcSize, int finished)
+{
+  CLzma2Enc *me = (CLzma2Enc *)pp;
+  size_t destSize = me->outBufSize;
+  SRes res;
+  CMtProgressThunk progressThunk;
+
+  Byte *dest = me->outBufs[outBufIndex];
+
+  me->outBufsDataSizes[outBufIndex] = 0;
+
+  if (!dest)
+  {
+    dest = (Byte *)ISzAlloc_Alloc(me->alloc, me->outBufSize);
+    if (!dest)
+      return SZ_ERROR_MEM;
+    me->outBufs[outBufIndex] = dest;
+  }
+
+  MtProgressThunk_CreateVTable(&progressThunk);
+  progressThunk.mtProgress = &me->mtCoder.mtProgress;
+  progressThunk.inSize = 0;
+  progressThunk.outSize = 0;
+
+  res = Lzma2Enc_EncodeMt1(me,
+      &me->coders[coderIndex],
+      NULL, dest, &destSize,
+      NULL, src, srcSize,
+      finished,
+      &progressThunk.vt);
+
+  me->outBufsDataSizes[outBufIndex] = destSize;
+
+  return res;
+}
+
+
+static SRes Lzma2Enc_MtCallback_Write(void *pp, unsigned outBufIndex)
+{
+  CLzma2Enc *me = (CLzma2Enc *)pp;
+  size_t size = me->outBufsDataSizes[outBufIndex];
+  const Byte *data = me->outBufs[outBufIndex];
+  
+  if (me->outStream)
+    return ISeqOutStream_Write(me->outStream, data, size) == size ? SZ_OK : SZ_ERROR_WRITE;
+  
+  if (size > me->outBuf_Rem)
+    return SZ_ERROR_OUTPUT_EOF;
+  memcpy(me->outBuf, data, size);
+  me->outBuf_Rem -= size;
+  me->outBuf += size;
+  return SZ_OK;
+}
+
+#endif
+
+
+
+SRes Lzma2Enc_Encode2(CLzma2EncHandle pp,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    ICompressProgress *progress)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+
+  if (inStream && inData)
+    return SZ_ERROR_PARAM;
+
+  if (outStream && outBuf)
+    return SZ_ERROR_PARAM;
+
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__THREADS_MAX; i++)
+      p->coders[i].propsAreSet = False;
+  }
+
+  #ifndef _7ZIP_ST
+  
+  if (p->props.numBlockThreads_Reduced > 1)
+  {
+    IMtCoderCallback2 vt;
+
+    if (!p->mtCoder_WasConstructed)
+    {
+      p->mtCoder_WasConstructed = True;
+      MtCoder_Construct(&p->mtCoder);
+    }
+
+    vt.Code = Lzma2Enc_MtCallback_Code;
+    vt.Write = Lzma2Enc_MtCallback_Write;
+
+    p->outStream = outStream;
+    p->outBuf = NULL;
+    p->outBuf_Rem = 0;
+    if (!outStream)
+    {
+      p->outBuf = outBuf;
+      p->outBuf_Rem = *outBufSize;
+      *outBufSize = 0;
+    }
+
+    p->mtCoder.allocBig = p->allocBig;
+    p->mtCoder.progress = progress;
+    p->mtCoder.inStream = inStream;
+    p->mtCoder.inData = inData;
+    p->mtCoder.inDataSize = inDataSize;
+    p->mtCoder.mtCallback = &vt;
+    p->mtCoder.mtCallbackObject = p;
+
+    p->mtCoder.blockSize = (size_t)p->props.blockSize;
+    if (p->mtCoder.blockSize != p->props.blockSize)
+      return SZ_ERROR_PARAM; /* SZ_ERROR_MEM */
+
+    {
+      size_t destBlockSize = p->mtCoder.blockSize + (p->mtCoder.blockSize >> 10) + 16;
+      if (destBlockSize < p->mtCoder.blockSize)
+        return SZ_ERROR_PARAM;
+      if (p->outBufSize != destBlockSize)
+        Lzma2Enc_FreeOutBufs(p);
+      p->outBufSize = destBlockSize;
+    }
+
+    p->mtCoder.numThreadsMax = p->props.numBlockThreads_Max;
+    p->mtCoder.expectedDataSize = p->expectedDataSize;
+    
+    {
+      SRes res = MtCoder_Code(&p->mtCoder);
+      if (!outStream)
+        *outBufSize = p->outBuf - outBuf;
+      return res;
+    }
+  }
+
+  #endif
+
+
+  return Lzma2Enc_EncodeMt1(p,
+      &p->coders[0],
+      outStream, outBuf, outBufSize,
+      inStream, inData, inDataSize,
+      True, /* finished */
+      progress);
+}
@@ -0,0 +1,55 @@
+/* Lzma2Enc.h -- LZMA2 Encoder
+2017-07-27 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_ENC_H
+#define __LZMA2_ENC_H
+
+#include "LzmaEnc.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO 0
+#define LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID ((UInt64)(Int64)-1)
+
+typedef struct
+{
+  CLzmaEncProps lzmaProps;
+  UInt64 blockSize;
+  int numBlockThreads_Reduced;
+  int numBlockThreads_Max;
+  int numTotalThreads;
+} CLzma2EncProps;
+
+void Lzma2EncProps_Init(CLzma2EncProps *p);
+void Lzma2EncProps_Normalize(CLzma2EncProps *p);
+
+/* ---------- CLzmaEnc2Handle Interface ---------- */
+
+/* Lzma2Enc_* functions can return the following exit codes:
+SRes:
+  SZ_OK           - OK
+  SZ_ERROR_MEM    - Memory allocation error
+  SZ_ERROR_PARAM  - Incorrect paramater in props
+  SZ_ERROR_WRITE  - ISeqOutStream write callback error
+  SZ_ERROR_OUTPUT_EOF - output buffer overflow - version with (Byte *) output
+  SZ_ERROR_PROGRESS - some break from progress callback
+  SZ_ERROR_THREAD - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzma2EncHandle;
+
+CLzma2EncHandle Lzma2Enc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig);
+void Lzma2Enc_Destroy(CLzma2EncHandle p);
+SRes Lzma2Enc_SetProps(CLzma2EncHandle p, const CLzma2EncProps *props);
+void Lzma2Enc_SetDataSize(CLzma2EncHandle p, UInt64 expectedDataSiize);
+Byte Lzma2Enc_WriteProperties(CLzma2EncHandle p);
+SRes Lzma2Enc_Encode2(CLzma2EncHandle p,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    ICompressProgress *progress);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,111 @@
+/* Lzma86.h -- LZMA + x86 (BCJ) Filter
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA86_H
+#define __LZMA86_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA86_SIZE_OFFSET (1 + 5)
+#define LZMA86_HEADER_SIZE (LZMA86_SIZE_OFFSET + 8)
+
+/*
+It's an example for LZMA + x86 Filter use.
+You can use .lzma86 extension, if you write that stream to file.
+.lzma86 header adds one additional byte to standard .lzma header.
+.lzma86 header (14 bytes):
+  Offset Size  Description
+    0     1    = 0 - no filter, pure LZMA
+               = 1 - x86 filter + LZMA
+    1     1    lc, lp and pb in encoded form
+    2     4    dictSize (little endian)
+    6     8    uncompressed size (little endian)
+
+
+Lzma86_Encode
+-------------
+level - compression level: 0 <= level <= 9, the default value for "level" is 5.
+
+dictSize - The dictionary size in bytes. The maximum value is
+        128 MB = (1 << 27) bytes for 32-bit version
+          1 GB = (1 << 30) bytes for 64-bit version
+     The default value is 16 MB = (1 << 24) bytes, for level = 5.
+     It's recommended to use the dictionary that is larger than 4 KB and
+     that can be calculated as (1 << N) or (3 << N) sizes.
+     For better compression ratio dictSize must be >= inSize.
+
+filterMode:
+    SZ_FILTER_NO   - no Filter
+    SZ_FILTER_YES  - x86 Filter
+    SZ_FILTER_AUTO - it tries both alternatives to select best.
+              Encoder will use 2 or 3 passes:
+              2 passes when FILTER_NO provides better compression.
+              3 passes when FILTER_YES provides better compression.
+
+Lzma86Encode allocates Data with MyAlloc functions.
+RAM Requirements for compressing:
+  RamSize = dictionarySize * 11.5 + 6MB + FilterBlockSize
+      filterMode     FilterBlockSize
+     SZ_FILTER_NO         0
+     SZ_FILTER_YES      inSize
+     SZ_FILTER_AUTO     inSize
+
+
+Return code:
+  SZ_OK               - OK
+  SZ_ERROR_MEM        - Memory allocation error
+  SZ_ERROR_PARAM      - Incorrect paramater
+  SZ_ERROR_OUTPUT_EOF - output buffer overflow
+  SZ_ERROR_THREAD     - errors in multithreading functions (only for Mt version)
+*/
+
+enum ESzFilterMode
+{
+  SZ_FILTER_NO,
+  SZ_FILTER_YES,
+  SZ_FILTER_AUTO
+};
+
+SRes Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
+    int level, UInt32 dictSize, int filterMode);
+
+
+/*
+Lzma86_GetUnpackSize:
+  In:
+    src      - input data
+    srcLen   - input data size
+  Out:
+    unpackSize - size of uncompressed stream
+  Return code:
+    SZ_OK               - OK
+    SZ_ERROR_INPUT_EOF  - Error in headers
+*/
+
+SRes Lzma86_GetUnpackSize(const Byte *src, SizeT srcLen, UInt64 *unpackSize);
+
+/*
+Lzma86_Decode:
+  In:
+    dest     - output data
+    destLen  - output data size
+    src      - input data
+    srcLen   - input data size
+  Out:
+    destLen  - processed output size
+    srcLen   - processed input size
+  Return code:
+    SZ_OK           - OK
+    SZ_ERROR_DATA  - Data error
+    SZ_ERROR_MEM   - Memory allocation error
+    SZ_ERROR_UNSUPPORTED - unsupported file
+    SZ_ERROR_INPUT_EOF - it needs more bytes in input buffer
+*/
+
+SRes Lzma86_Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,54 @@
+/* Lzma86Dec.c -- LZMA + x86 (BCJ) Filter Decoder
+2016-05-16 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Lzma86.h"
+
+#include "Alloc.h"
+#include "Bra.h"
+#include "LzmaDec.h"
+
+SRes Lzma86_GetUnpackSize(const Byte *src, SizeT srcLen, UInt64 *unpackSize)
+{
+  unsigned i;
+  if (srcLen < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_INPUT_EOF;
+  *unpackSize = 0;
+  for (i = 0; i < sizeof(UInt64); i++)
+    *unpackSize += ((UInt64)src[LZMA86_SIZE_OFFSET + i]) << (8 * i);
+  return SZ_OK;
+}
+
+SRes Lzma86_Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen)
+{
+  SRes res;
+  int useFilter;
+  SizeT inSizePure;
+  ELzmaStatus status;
+
+  if (*srcLen < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_INPUT_EOF;
+
+  useFilter = src[0];
+
+  if (useFilter > 1)
+  {
+    *destLen = 0;
+    return SZ_ERROR_UNSUPPORTED;
+  }
+
+  inSizePure = *srcLen - LZMA86_HEADER_SIZE;
+  res = LzmaDecode(dest, destLen, src + LZMA86_HEADER_SIZE, &inSizePure,
+      src + 1, LZMA_PROPS_SIZE, LZMA_FINISH_ANY, &status, &g_Alloc);
+  *srcLen = inSizePure + LZMA86_HEADER_SIZE;
+  if (res != SZ_OK)
+    return res;
+  if (useFilter == 1)
+  {
+    UInt32 x86State;
+    x86_Convert_Init(x86State);
+    x86_Convert(dest, *destLen, 0, &x86State, 0);
+  }
+  return SZ_OK;
+}
@@ -0,0 +1,106 @@
+/* Lzma86Enc.c -- LZMA + x86 (BCJ) Filter Encoder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "Lzma86.h"
+
+#include "Alloc.h"
+#include "Bra.h"
+#include "LzmaEnc.h"
+
+#define SZE_OUT_OVERFLOW SZE_DATA_ERROR
+
+int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
+    int level, UInt32 dictSize, int filterMode)
+{
+  size_t outSize2 = *destLen;
+  Byte *filteredStream;
+  BoolInt useFilter;
+  int mainResult = SZ_ERROR_OUTPUT_EOF;
+  CLzmaEncProps props;
+  LzmaEncProps_Init(&props);
+  props.level = level;
+  props.dictSize = dictSize;
+  
+  *destLen = 0;
+  if (outSize2 < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_OUTPUT_EOF;
+
+  {
+    int i;
+    UInt64 t = srcLen;
+    for (i = 0; i < 8; i++, t >>= 8)
+      dest[LZMA86_SIZE_OFFSET + i] = (Byte)t;
+  }
+
+  filteredStream = 0;
+  useFilter = (filterMode != SZ_FILTER_NO);
+  if (useFilter)
+  {
+    if (srcLen != 0)
+    {
+      filteredStream = (Byte *)MyAlloc(srcLen);
+      if (filteredStream == 0)
+        return SZ_ERROR_MEM;
+      memcpy(filteredStream, src, srcLen);
+    }
+    {
+      UInt32 x86State;
+      x86_Convert_Init(x86State);
+      x86_Convert(filteredStream, srcLen, 0, &x86State, 1);
+    }
+  }
+
+  {
+    size_t minSize = 0;
+    BoolInt bestIsFiltered = False;
+
+    /* passes for SZ_FILTER_AUTO:
+        0 - BCJ + LZMA
+        1 - LZMA
+        2 - BCJ + LZMA agaian, if pass 0 (BCJ + LZMA) is better.
+    */
+    int numPasses = (filterMode == SZ_FILTER_AUTO) ? 3 : 1;
+
+    int i;
+    for (i = 0; i < numPasses; i++)
+    {
+      size_t outSizeProcessed = outSize2 - LZMA86_HEADER_SIZE;
+      size_t outPropsSize = 5;
+      SRes curRes;
+      BoolInt curModeIsFiltered = (numPasses > 1 && i == numPasses - 1);
+      if (curModeIsFiltered && !bestIsFiltered)
+        break;
+      if (useFilter && i == 0)
+        curModeIsFiltered = True;
+      
+      curRes = LzmaEncode(dest + LZMA86_HEADER_SIZE, &outSizeProcessed,
+          curModeIsFiltered ? filteredStream : src, srcLen,
+          &props, dest + 1, &outPropsSize, 0,
+          NULL, &g_Alloc, &g_Alloc);
+      
+      if (curRes != SZ_ERROR_OUTPUT_EOF)
+      {
+        if (curRes != SZ_OK)
+        {
+          mainResult = curRes;
+          break;
+        }
+        if (outSizeProcessed <= minSize || mainResult != SZ_OK)
+        {
+          minSize = outSizeProcessed;
+          bestIsFiltered = curModeIsFiltered;
+          mainResult = SZ_OK;
+        }
+      }
+    }
+    dest[0] = (Byte)(bestIsFiltered ? 1 : 0);
+    *destLen = LZMA86_HEADER_SIZE + minSize;
+  }
+  if (useFilter)
+    MyFree(filteredStream);
+  return mainResult;
+}
@@ -0,0 +1,234 @@
+/* LzmaDec.h -- LZMA Decoder
+2018-04-21 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA_DEC_H
+#define __LZMA_DEC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/* #define _LZMA_PROB32 */
+/* _LZMA_PROB32 can increase the speed on some CPUs,
+   but memory usage for CLzmaDec::probs will be doubled in that case */
+
+typedef
+#ifdef _LZMA_PROB32
+  UInt32
+#else
+  UInt16
+#endif
+  CLzmaProb;
+
+
+/* ---------- LZMA Properties ---------- */
+
+#define LZMA_PROPS_SIZE 5
+
+typedef struct _CLzmaProps
+{
+  Byte lc;
+  Byte lp;
+  Byte pb;
+  Byte _pad_;
+  UInt32 dicSize;
+} CLzmaProps;
+
+/* LzmaProps_Decode - decodes properties
+Returns:
+  SZ_OK
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+*/
+
+SRes LzmaProps_Decode(CLzmaProps *p, const Byte *data, unsigned size);
+
+
+/* ---------- LZMA Decoder state ---------- */
+
+/* LZMA_REQUIRED_INPUT_MAX = number of required input bytes for worst case.
+   Num bits = log2((2^11 / 31) ^ 22) + 26 < 134 + 26 = 160; */
+
+#define LZMA_REQUIRED_INPUT_MAX 20
+
+typedef struct
+{
+  /* Don't change this structure. ASM code can use it. */
+  CLzmaProps prop;
+  CLzmaProb *probs;
+  CLzmaProb *probs_1664;
+  Byte *dic;
+  SizeT dicBufSize;
+  SizeT dicPos;
+  const Byte *buf;
+  UInt32 range;
+  UInt32 code;
+  UInt32 processedPos;
+  UInt32 checkDicSize;
+  UInt32 reps[4];
+  UInt32 state;
+  UInt32 remainLen;
+
+  UInt32 numProbs;
+  unsigned tempBufSize;
+  Byte tempBuf[LZMA_REQUIRED_INPUT_MAX];
+} CLzmaDec;
+
+#define LzmaDec_Construct(p) { (p)->dic = NULL; (p)->probs = NULL; }
+
+void LzmaDec_Init(CLzmaDec *p);
+
+/* There are two types of LZMA streams:
+     - Stream with end mark. That end mark adds about 6 bytes to compressed size.
+     - Stream without end mark. You must know exact uncompressed size to decompress such stream. */
+
+typedef enum
+{
+  LZMA_FINISH_ANY,   /* finish at any point */
+  LZMA_FINISH_END    /* block must be finished at the end */
+} ELzmaFinishMode;
+
+/* ELzmaFinishMode has meaning only if the decoding reaches output limit !!!
+
+   You must use LZMA_FINISH_END, when you know that current output buffer
+   covers last bytes of block. In other cases you must use LZMA_FINISH_ANY.
+
+   If LZMA decoder sees end marker before reaching output limit, it returns SZ_OK,
+   and output value of destLen will be less than output buffer size limit.
+   You can check status result also.
+
+   You can use multiple checks to test data integrity after full decompression:
+     1) Check Result and "status" variable.
+     2) Check that output(destLen) = uncompressedSize, if you know real uncompressedSize.
+     3) Check that output(srcLen) = compressedSize, if you know real compressedSize.
+        You must use correct finish mode in that case. */
+
+typedef enum
+{
+  LZMA_STATUS_NOT_SPECIFIED,               /* use main error code instead */
+  LZMA_STATUS_FINISHED_WITH_MARK,          /* stream was finished with end mark. */
+  LZMA_STATUS_NOT_FINISHED,                /* stream was not finished */
+  LZMA_STATUS_NEEDS_MORE_INPUT,            /* you must provide more input bytes */
+  LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK  /* there is probability that stream was finished without end mark */
+} ELzmaStatus;
+
+/* ELzmaStatus is used only as output value for function call */
+
+
+/* ---------- Interfaces ---------- */
+
+/* There are 3 levels of interfaces:
+     1) Dictionary Interface
+     2) Buffer Interface
+     3) One Call Interface
+   You can select any of these interfaces, but don't mix functions from different
+   groups for same object. */
+
+
+/* There are two variants to allocate state for Dictionary Interface:
+     1) LzmaDec_Allocate / LzmaDec_Free
+     2) LzmaDec_AllocateProbs / LzmaDec_FreeProbs
+   You can use variant 2, if you set dictionary buffer manually.
+   For Buffer Interface you must always use variant 1.
+
+LzmaDec_Allocate* can return:
+  SZ_OK
+  SZ_ERROR_MEM         - Memory allocation error
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+*/
+   
+SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc);
+void LzmaDec_FreeProbs(CLzmaDec *p, ISzAllocPtr alloc);
+
+SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc);
+void LzmaDec_Free(CLzmaDec *p, ISzAllocPtr alloc);
+
+/* ---------- Dictionary Interface ---------- */
+
+/* You can use it, if you want to eliminate the overhead for data copying from
+   dictionary to some other external buffer.
+   You must work with CLzmaDec variables directly in this interface.
+
+   STEPS:
+     LzmaDec_Construct()
+     LzmaDec_Allocate()
+     for (each new stream)
+     {
+       LzmaDec_Init()
+       while (it needs more decompression)
+       {
+         LzmaDec_DecodeToDic()
+         use data from CLzmaDec::dic and update CLzmaDec::dicPos
+       }
+     }
+     LzmaDec_Free()
+*/
+
+/* LzmaDec_DecodeToDic
+   
+   The decoding to internal dictionary buffer (CLzmaDec::dic).
+   You must manually update CLzmaDec::dicPos, if it reaches CLzmaDec::dicBufSize !!!
+
+finishMode:
+  It has meaning only if the decoding reaches output limit (dicLimit).
+  LZMA_FINISH_ANY - Decode just dicLimit bytes.
+  LZMA_FINISH_END - Stream must be finished after dicLimit.
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+      LZMA_STATUS_NEEDS_MORE_INPUT
+      LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK
+  SZ_ERROR_DATA - Data error
+*/
+
+SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+
+/* ---------- Buffer Interface ---------- */
+
+/* It's zlib-like interface.
+   See LzmaDec_DecodeToDic description for information about STEPS and return results,
+   but you must use LzmaDec_DecodeToBuf instead of LzmaDec_DecodeToDic and you don't need
+   to work with CLzmaDec variables manually.
+
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  LZMA_FINISH_ANY - Decode just destLen bytes.
+  LZMA_FINISH_END - Stream must be finished after (*destLen).
+*/
+
+SRes LzmaDec_DecodeToBuf(CLzmaDec *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+
+/* ---------- One Call Interface ---------- */
+
+/* LzmaDecode
+
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  LZMA_FINISH_ANY - Decode just destLen bytes.
+  LZMA_FINISH_END - Stream must be finished after (*destLen).
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+      LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK
+  SZ_ERROR_DATA - Data error
+  SZ_ERROR_MEM  - Memory allocation error
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+  SZ_ERROR_INPUT_EOF - It needs more bytes in input buffer (src).
+*/
+
+SRes LzmaDecode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+    const Byte *propData, unsigned propSize, ELzmaFinishMode finishMode,
+    ELzmaStatus *status, ISzAllocPtr alloc);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,76 @@
+/*  LzmaEnc.h -- LZMA Encoder
+2017-07-27 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA_ENC_H
+#define __LZMA_ENC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA_PROPS_SIZE 5
+
+typedef struct _CLzmaEncProps
+{
+  int level;       /* 0 <= level <= 9 */
+  UInt32 dictSize; /* (1 << 12) <= dictSize <= (1 << 27) for 32-bit version
+                      (1 << 12) <= dictSize <= (3 << 29) for 64-bit version
+                      default = (1 << 24) */
+  int lc;          /* 0 <= lc <= 8, default = 3 */
+  int lp;          /* 0 <= lp <= 4, default = 0 */
+  int pb;          /* 0 <= pb <= 4, default = 2 */
+  int algo;        /* 0 - fast, 1 - normal, default = 1 */
+  int fb;          /* 5 <= fb <= 273, default = 32 */
+  int btMode;      /* 0 - hashChain Mode, 1 - binTree mode - normal, default = 1 */
+  int numHashBytes; /* 2, 3 or 4, default = 4 */
+  UInt32 mc;       /* 1 <= mc <= (1 << 30), default = 32 */
+  unsigned writeEndMark;  /* 0 - do not write EOPM, 1 - write EOPM, default = 0 */
+  int numThreads;  /* 1 or 2, default = 2 */
+
+  UInt64 reduceSize; /* estimated size of data that will be compressed. default = (UInt64)(Int64)-1.
+                        Encoder uses this value to reduce dictionary size */
+} CLzmaEncProps;
+
+void LzmaEncProps_Init(CLzmaEncProps *p);
+void LzmaEncProps_Normalize(CLzmaEncProps *p);
+UInt32 LzmaEncProps_GetDictSize(const CLzmaEncProps *props2);
+
+
+/* ---------- CLzmaEncHandle Interface ---------- */
+
+/* LzmaEnc* functions can return the following exit codes:
+SRes:
+  SZ_OK           - OK
+  SZ_ERROR_MEM    - Memory allocation error
+  SZ_ERROR_PARAM  - Incorrect paramater in props
+  SZ_ERROR_WRITE  - ISeqOutStream write callback error
+  SZ_ERROR_OUTPUT_EOF - output buffer overflow - version with (Byte *) output
+  SZ_ERROR_PROGRESS - some break from progress callback
+  SZ_ERROR_THREAD - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzmaEncHandle;
+
+CLzmaEncHandle LzmaEnc_Create(ISzAllocPtr alloc);
+void LzmaEnc_Destroy(CLzmaEncHandle p, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+
+SRes LzmaEnc_SetProps(CLzmaEncHandle p, const CLzmaEncProps *props);
+void LzmaEnc_SetDataSize(CLzmaEncHandle p, UInt64 expectedDataSiize);
+SRes LzmaEnc_WriteProperties(CLzmaEncHandle p, Byte *properties, SizeT *size);
+unsigned LzmaEnc_IsWriteEndMark(CLzmaEncHandle p);
+
+SRes LzmaEnc_Encode(CLzmaEncHandle p, ISeqOutStream *outStream, ISeqInStream *inStream,
+    ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_MemEncode(CLzmaEncHandle p, Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen,
+    int writeEndMark, ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+
+
+/* ---------- One Call Interface ---------- */
+
+SRes LzmaEncode(Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen,
+    const CLzmaEncProps *props, Byte *propsEncoded, SizeT *propsSize, int writeEndMark,
+    ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,40 @@
+/* LzmaLib.c -- LZMA library wrapper
+2015-06-13 : Igor Pavlov : Public domain */
+
+#include "Alloc.h"
+#include "LzmaDec.h"
+#include "LzmaEnc.h"
+#include "LzmaLib.h"
+
+MY_STDAPI LzmaCompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t srcLen,
+  unsigned char *outProps, size_t *outPropsSize,
+  int level, /* 0 <= level <= 9, default = 5 */
+  unsigned dictSize, /* use (1 << N) or (3 << N). 4 KB < dictSize <= 128 MB */
+  int lc, /* 0 <= lc <= 8, default = 3  */
+  int lp, /* 0 <= lp <= 4, default = 0  */
+  int pb, /* 0 <= pb <= 4, default = 2  */
+  int fb,  /* 5 <= fb <= 273, default = 32 */
+  int numThreads /* 1 or 2, default = 2 */
+)
+{
+  CLzmaEncProps props;
+  LzmaEncProps_Init(&props);
+  props.level = level;
+  props.dictSize = dictSize;
+  props.lc = lc;
+  props.lp = lp;
+  props.pb = pb;
+  props.fb = fb;
+  props.numThreads = numThreads;
+
+  return LzmaEncode(dest, destLen, src, srcLen, &props, outProps, outPropsSize, 0,
+      NULL, &g_Alloc, &g_Alloc);
+}
+
+
+MY_STDAPI LzmaUncompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t *srcLen,
+  const unsigned char *props, size_t propsSize)
+{
+  ELzmaStatus status;
+  return LzmaDecode(dest, destLen, src, srcLen, props, (unsigned)propsSize, LZMA_FINISH_ANY, &status, &g_Alloc);
+}
@@ -0,0 +1,131 @@
+/* LzmaLib.h -- LZMA library interface
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA_LIB_H
+#define __LZMA_LIB_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define MY_STDAPI int MY_STD_CALL
+
+#define LZMA_PROPS_SIZE 5
+
+/*
+RAM requirements for LZMA:
+  for compression:   (dictSize * 11.5 + 6 MB) + state_size
+  for decompression: dictSize + state_size
+    state_size = (4 + (1.5 << (lc + lp))) KB
+    by default (lc=3, lp=0), state_size = 16 KB.
+
+LZMA properties (5 bytes) format
+    Offset Size  Description
+      0     1    lc, lp and pb in encoded form.
+      1     4    dictSize (little endian).
+*/
+
+/*
+LzmaCompress
+------------
+
+outPropsSize -
+     In:  the pointer to the size of outProps buffer; *outPropsSize = LZMA_PROPS_SIZE = 5.
+     Out: the pointer to the size of written properties in outProps buffer; *outPropsSize = LZMA_PROPS_SIZE = 5.
+
+  LZMA Encoder will use defult values for any parameter, if it is
+  -1  for any from: level, loc, lp, pb, fb, numThreads
+   0  for dictSize
+  
+level - compression level: 0 <= level <= 9;
+
+  level dictSize algo  fb
+    0:    16 KB   0    32
+    1:    64 KB   0    32
+    2:   256 KB   0    32
+    3:     1 MB   0    32
+    4:     4 MB   0    32
+    5:    16 MB   1    32
+    6:    32 MB   1    32
+    7+:   64 MB   1    64
+ 
+  The default value for "level" is 5.
+
+  algo = 0 means fast method
+  algo = 1 means normal method
+
+dictSize - The dictionary size in bytes. The maximum value is
+        128 MB = (1 << 27) bytes for 32-bit version
+          1 GB = (1 << 30) bytes for 64-bit version
+     The default value is 16 MB = (1 << 24) bytes.
+     It's recommended to use the dictionary that is larger than 4 KB and
+     that can be calculated as (1 << N) or (3 << N) sizes.
+
+lc - The number of literal context bits (high bits of previous literal).
+     It can be in the range from 0 to 8. The default value is 3.
+     Sometimes lc=4 gives the gain for big files.
+
+lp - The number of literal pos bits (low bits of current position for literals).
+     It can be in the range from 0 to 4. The default value is 0.
+     The lp switch is intended for periodical data when the period is equal to 2^lp.
+     For example, for 32-bit (4 bytes) periodical data you can use lp=2. Often it's
+     better to set lc=0, if you change lp switch.
+
+pb - The number of pos bits (low bits of current position).
+     It can be in the range from 0 to 4. The default value is 2.
+     The pb switch is intended for periodical data when the period is equal 2^pb.
+
+fb - Word size (the number of fast bytes).
+     It can be in the range from 5 to 273. The default value is 32.
+     Usually, a big number gives a little bit better compression ratio and
+     slower compression process.
+
+numThreads - The number of thereads. 1 or 2. The default value is 2.
+     Fast mode (algo = 0) can use only 1 thread.
+
+Out:
+  destLen  - processed output size
+Returns:
+  SZ_OK               - OK
+  SZ_ERROR_MEM        - Memory allocation error
+  SZ_ERROR_PARAM      - Incorrect paramater
+  SZ_ERROR_OUTPUT_EOF - output buffer overflow
+  SZ_ERROR_THREAD     - errors in multithreading functions (only for Mt version)
+*/
+
+MY_STDAPI LzmaCompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t srcLen,
+  unsigned char *outProps, size_t *outPropsSize, /* *outPropsSize must be = 5 */
+  int level,      /* 0 <= level <= 9, default = 5 */
+  unsigned dictSize,  /* default = (1 << 24) */
+  int lc,        /* 0 <= lc <= 8, default = 3  */
+  int lp,        /* 0 <= lp <= 4, default = 0  */
+  int pb,        /* 0 <= pb <= 4, default = 2  */
+  int fb,        /* 5 <= fb <= 273, default = 32 */
+  int numThreads /* 1 or 2, default = 2 */
+  );
+
+/*
+LzmaUncompress
+--------------
+In:
+  dest     - output data
+  destLen  - output data size
+  src      - input data
+  srcLen   - input data size
+Out:
+  destLen  - processed output size
+  srcLen   - processed input size
+Returns:
+  SZ_OK                - OK
+  SZ_ERROR_DATA        - Data error
+  SZ_ERROR_MEM         - Memory allocation arror
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+  SZ_ERROR_INPUT_EOF   - it needs more bytes in input buffer (src)
+*/
+
+MY_STDAPI LzmaUncompress(unsigned char *dest, size_t *destLen, const unsigned char *src, SizeT *srcLen,
+  const unsigned char *props, size_t propsSize);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,601 @@
+/* MtCoder.c -- Multi-thread Coder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "MtCoder.h"
+
+#ifndef _7ZIP_ST
+
+SRes MtProgressThunk_Progress(const ICompressProgress *pp, UInt64 inSize, UInt64 outSize)
+{
+  CMtProgressThunk *thunk = CONTAINER_FROM_VTBL(pp, CMtProgressThunk, vt);
+  UInt64 inSize2 = 0;
+  UInt64 outSize2 = 0;
+  if (inSize != (UInt64)(Int64)-1)
+  {
+    inSize2 = inSize - thunk->inSize;
+    thunk->inSize = inSize;
+  }
+  if (outSize != (UInt64)(Int64)-1)
+  {
+    outSize2 = outSize - thunk->outSize;
+    thunk->outSize = outSize;
+  }
+  return MtProgress_ProgressAdd(thunk->mtProgress, inSize2, outSize2);
+}
+
+
+void MtProgressThunk_CreateVTable(CMtProgressThunk *p)
+{
+  p->vt.Progress = MtProgressThunk_Progress;
+}
+
+
+
+#define RINOK_THREAD(x) { if ((x) != 0) return SZ_ERROR_THREAD; }
+
+
+static WRes ArEvent_OptCreate_And_Reset(CEvent *p)
+{
+  if (Event_IsCreated(p))
+    return Event_Reset(p);
+  return AutoResetEvent_CreateNotSignaled(p);
+}
+
+
+static THREAD_FUNC_RET_TYPE THREAD_FUNC_CALL_TYPE ThreadFunc(void *pp);
+
+
+static SRes MtCoderThread_CreateAndStart(CMtCoderThread *t)
+{
+  WRes wres = ArEvent_OptCreate_And_Reset(&t->startEvent);
+  if (wres == 0)
+  {
+    t->stop = False;
+    if (!Thread_WasCreated(&t->thread))
+      wres = Thread_Create(&t->thread, ThreadFunc, t);
+    if (wres == 0)
+      wres = Event_Set(&t->startEvent);
+  }
+  if (wres == 0)
+    return SZ_OK;
+  return MY_SRes_HRESULT_FROM_WRes(wres);
+}
+
+
+static void MtCoderThread_Destruct(CMtCoderThread *t)
+{
+  if (Thread_WasCreated(&t->thread))
+  {
+    t->stop = 1;
+    Event_Set(&t->startEvent);
+    Thread_Wait(&t->thread);
+    Thread_Close(&t->thread);
+  }
+
+  Event_Close(&t->startEvent);
+
+  if (t->inBuf)
+  {
+    ISzAlloc_Free(t->mtCoder->allocBig, t->inBuf);
+    t->inBuf = NULL;
+  }
+}
+
+
+
+static SRes FullRead(ISeqInStream *stream, Byte *data, size_t *processedSize)
+{
+  size_t size = *processedSize;
+  *processedSize = 0;
+  while (size != 0)
+  {
+    size_t cur = size;
+    SRes res = ISeqInStream_Read(stream, data, &cur);
+    *processedSize += cur;
+    data += cur;
+    size -= cur;
+    RINOK(res);
+    if (cur == 0)
+      return SZ_OK;
+  }
+  return SZ_OK;
+}
+
+
+/*
+  ThreadFunc2() returns:
+  SZ_OK           - in all normal cases (even for stream error or memory allocation error)
+  SZ_ERROR_THREAD - in case of failure in system synch function
+*/
+
+static SRes ThreadFunc2(CMtCoderThread *t)
+{
+  CMtCoder *mtc = t->mtCoder;
+
+  for (;;)
+  {
+    unsigned bi;
+    SRes res;
+    SRes res2;
+    BoolInt finished;
+    unsigned bufIndex;
+    size_t size;
+    const Byte *inData;
+    UInt64 readProcessed = 0;
+    
+    RINOK_THREAD(Event_Wait(&mtc->readEvent))
+
+    /* after Event_Wait(&mtc->readEvent) we must call Event_Set(&mtc->readEvent) in any case to unlock another threads */
+
+    if (mtc->stopReading)
+    {
+      return Event_Set(&mtc->readEvent) == 0 ? SZ_OK : SZ_ERROR_THREAD;
+    }
+
+    res = MtProgress_GetError(&mtc->mtProgress);
+    
+    size = 0;
+    inData = NULL;
+    finished = True;
+
+    if (res == SZ_OK)
+    {
+      size = mtc->blockSize;
+      if (mtc->inStream)
+      {
+        if (!t->inBuf)
+        {
+          t->inBuf = (Byte *)ISzAlloc_Alloc(mtc->allocBig, mtc->blockSize);
+          if (!t->inBuf)
+            res = SZ_ERROR_MEM;
+        }
+        if (res == SZ_OK)
+        {
+          res = FullRead(mtc->inStream, t->inBuf, &size);
+          readProcessed = mtc->readProcessed + size;
+          mtc->readProcessed = readProcessed;
+        }
+        if (res != SZ_OK)
+        {
+          mtc->readRes = res;
+          /* after reading error - we can stop encoding of previous blocks */
+          MtProgress_SetError(&mtc->mtProgress, res);
+        }
+        else
+          finished = (size != mtc->blockSize);
+      }
+      else
+      {
+        size_t rem;
+        readProcessed = mtc->readProcessed;
+        rem = mtc->inDataSize - (size_t)readProcessed;
+        if (size > rem)
+          size = rem;
+        inData = mtc->inData + (size_t)readProcessed;
+        readProcessed += size;
+        mtc->readProcessed = readProcessed;
+        finished = (mtc->inDataSize == (size_t)readProcessed);
+      }
+    }
+
+    /* we must get some block from blocksSemaphore before Event_Set(&mtc->readEvent) */
+
+    res2 = SZ_OK;
+
+    if (Semaphore_Wait(&mtc->blocksSemaphore) != 0)
+    {
+      res2 = SZ_ERROR_THREAD;
+      if (res == SZ_OK)
+      {
+        res = res2;
+        // MtProgress_SetError(&mtc->mtProgress, res);
+      }
+    }
+
+    bi = mtc->blockIndex;
+
+    if (++mtc->blockIndex >= mtc->numBlocksMax)
+      mtc->blockIndex = 0;
+
+    bufIndex = (unsigned)(int)-1;
+
+    if (res == SZ_OK)
+      res = MtProgress_GetError(&mtc->mtProgress);
+
+    if (res != SZ_OK)
+      finished = True;
+
+    if (!finished)
+    {
+      if (mtc->numStartedThreads < mtc->numStartedThreadsLimit
+          && mtc->expectedDataSize != readProcessed)
+      {
+        res = MtCoderThread_CreateAndStart(&mtc->threads[mtc->numStartedThreads]);
+        if (res == SZ_OK)
+          mtc->numStartedThreads++;
+        else
+        {
+          MtProgress_SetError(&mtc->mtProgress, res);
+          finished = True;
+        }
+      }
+    }
+
+    if (finished)
+      mtc->stopReading = True;
+
+    RINOK_THREAD(Event_Set(&mtc->readEvent))
+
+    if (res2 != SZ_OK)
+      return res2;
+
+    if (res == SZ_OK)
+    {
+      CriticalSection_Enter(&mtc->cs);
+      bufIndex = mtc->freeBlockHead;
+      mtc->freeBlockHead = mtc->freeBlockList[bufIndex];
+      CriticalSection_Leave(&mtc->cs);
+      
+      res = mtc->mtCallback->Code(mtc->mtCallbackObject, t->index, bufIndex,
+          mtc->inStream ? t->inBuf : inData, size, finished);
+      
+      // MtProgress_Reinit(&mtc->mtProgress, t->index);
+
+      if (res != SZ_OK)
+        MtProgress_SetError(&mtc->mtProgress, res);
+    }
+
+    {
+      CMtCoderBlock *block = &mtc->blocks[bi];
+      block->res = res;
+      block->bufIndex = bufIndex;
+      block->finished = finished;
+    }
+    
+    #ifdef MTCODER__USE_WRITE_THREAD
+      RINOK_THREAD(Event_Set(&mtc->writeEvents[bi]))
+    #else
+    {
+      unsigned wi;
+      {
+        CriticalSection_Enter(&mtc->cs);
+        wi = mtc->writeIndex;
+        if (wi == bi)
+          mtc->writeIndex = (unsigned)(int)-1;
+        else
+          mtc->ReadyBlocks[bi] = True;
+        CriticalSection_Leave(&mtc->cs);
+      }
+
+      if (wi != bi)
+      {
+        if (res != SZ_OK || finished)
+          return 0;
+        continue;
+      }
+
+      if (mtc->writeRes != SZ_OK)
+        res = mtc->writeRes;
+
+      for (;;)
+      {
+        if (res == SZ_OK && bufIndex != (unsigned)(int)-1)
+        {
+          res = mtc->mtCallback->Write(mtc->mtCallbackObject, bufIndex);
+          if (res != SZ_OK)
+          {
+            mtc->writeRes = res;
+            MtProgress_SetError(&mtc->mtProgress, res);
+          }
+        }
+
+        if (++wi >= mtc->numBlocksMax)
+          wi = 0;
+        {
+          BoolInt isReady;
+
+          CriticalSection_Enter(&mtc->cs);
+          
+          if (bufIndex != (unsigned)(int)-1)
+          {
+            mtc->freeBlockList[bufIndex] = mtc->freeBlockHead;
+            mtc->freeBlockHead = bufIndex;
+          }
+          
+          isReady = mtc->ReadyBlocks[wi];
+          
+          if (isReady)
+            mtc->ReadyBlocks[wi] = False;
+          else
+            mtc->writeIndex = wi;
+          
+          CriticalSection_Leave(&mtc->cs);
+
+          RINOK_THREAD(Semaphore_Release1(&mtc->blocksSemaphore))
+
+          if (!isReady)
+            break;
+        }
+
+        {
+          CMtCoderBlock *block = &mtc->blocks[wi];
+          if (res == SZ_OK && block->res != SZ_OK)
+            res = block->res;
+          bufIndex = block->bufIndex;
+          finished = block->finished;
+        }
+      }
+    }
+    #endif
+      
+    if (finished || res != SZ_OK)
+      return 0;
+  }
+}
+
+
+static THREAD_FUNC_RET_TYPE THREAD_FUNC_CALL_TYPE ThreadFunc(void *pp)
+{
+  CMtCoderThread *t = (CMtCoderThread *)pp;
+  for (;;)
+  {
+    if (Event_Wait(&t->startEvent) != 0)
+      return SZ_ERROR_THREAD;
+    if (t->stop)
+      return 0;
+    {
+      SRes res = ThreadFunc2(t);
+      CMtCoder *mtc = t->mtCoder;
+      if (res != SZ_OK)
+      {
+        MtProgress_SetError(&mtc->mtProgress, res);
+      }
+      
+      #ifndef MTCODER__USE_WRITE_THREAD
+      {
+        unsigned numFinished = (unsigned)InterlockedIncrement(&mtc->numFinishedThreads);
+        if (numFinished == mtc->numStartedThreads)
+          if (Event_Set(&mtc->finishedEvent) != 0)
+            return SZ_ERROR_THREAD;
+      }
+      #endif
+    }
+  }
+}
+
+
+
+void MtCoder_Construct(CMtCoder *p)
+{
+  unsigned i;
+  
+  p->blockSize = 0;
+  p->numThreadsMax = 0;
+  p->expectedDataSize = (UInt64)(Int64)-1;
+
+  p->inStream = NULL;
+  p->inData = NULL;
+  p->inDataSize = 0;
+
+  p->progress = NULL;
+  p->allocBig = NULL;
+
+  p->mtCallback = NULL;
+  p->mtCallbackObject = NULL;
+
+  p->allocatedBufsSize = 0;
+
+  Event_Construct(&p->readEvent);
+  Semaphore_Construct(&p->blocksSemaphore);
+
+  for (i = 0; i < MTCODER__THREADS_MAX; i++)
+  {
+    CMtCoderThread *t = &p->threads[i];
+    t->mtCoder = p;
+    t->index = i;
+    t->inBuf = NULL;
+    t->stop = False;
+    Event_Construct(&t->startEvent);
+    Thread_Construct(&t->thread);
+  }
+
+  #ifdef MTCODER__USE_WRITE_THREAD
+    for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+      Event_Construct(&p->writeEvents[i]);
+  #else
+    Event_Construct(&p->finishedEvent);
+  #endif
+
+  CriticalSection_Init(&p->cs);
+  CriticalSection_Init(&p->mtProgress.cs);
+}
+
+
+
+
+static void MtCoder_Free(CMtCoder *p)
+{
+  unsigned i;
+
+  /*
+  p->stopReading = True;
+  if (Event_IsCreated(&p->readEvent))
+    Event_Set(&p->readEvent);
+  */
+
+  for (i = 0; i < MTCODER__THREADS_MAX; i++)
+    MtCoderThread_Destruct(&p->threads[i]);
+
+  Event_Close(&p->readEvent);
+  Semaphore_Close(&p->blocksSemaphore);
+
+  #ifdef MTCODER__USE_WRITE_THREAD
+    for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+      Event_Close(&p->writeEvents[i]);
+  #else
+    Event_Close(&p->finishedEvent);
+  #endif
+}
+
+
+void MtCoder_Destruct(CMtCoder *p)
+{
+  MtCoder_Free(p);
+
+  CriticalSection_Delete(&p->cs);
+  CriticalSection_Delete(&p->mtProgress.cs);
+}
+
+
+SRes MtCoder_Code(CMtCoder *p)
+{
+  unsigned numThreads = p->numThreadsMax;
+  unsigned numBlocksMax;
+  unsigned i;
+  SRes res = SZ_OK;
+
+  if (numThreads > MTCODER__THREADS_MAX)
+    numThreads = MTCODER__THREADS_MAX;
+  numBlocksMax = MTCODER__GET_NUM_BLOCKS_FROM_THREADS(numThreads);
+  
+  if (p->blockSize < ((UInt32)1 << 26)) numBlocksMax++;
+  if (p->blockSize < ((UInt32)1 << 24)) numBlocksMax++;
+  if (p->blockSize < ((UInt32)1 << 22)) numBlocksMax++;
+
+  if (numBlocksMax > MTCODER__BLOCKS_MAX)
+    numBlocksMax = MTCODER__BLOCKS_MAX;
+
+  if (p->blockSize != p->allocatedBufsSize)
+  {
+    for (i = 0; i < MTCODER__THREADS_MAX; i++)
+    {
+      CMtCoderThread *t = &p->threads[i];
+      if (t->inBuf)
+      {
+        ISzAlloc_Free(p->allocBig, t->inBuf);
+        t->inBuf = NULL;
+      }
+    }
+    p->allocatedBufsSize = p->blockSize;
+  }
+
+  p->readRes = SZ_OK;
+
+  MtProgress_Init(&p->mtProgress, p->progress);
+
+  #ifdef MTCODER__USE_WRITE_THREAD
+    for (i = 0; i < numBlocksMax; i++)
+    {
+      RINOK_THREAD(ArEvent_OptCreate_And_Reset(&p->writeEvents[i]));
+    }
+  #else
+    RINOK_THREAD(ArEvent_OptCreate_And_Reset(&p->finishedEvent));
+  #endif
+
+  {
+    RINOK_THREAD(ArEvent_OptCreate_And_Reset(&p->readEvent));
+
+    if (Semaphore_IsCreated(&p->blocksSemaphore))
+    {
+      RINOK_THREAD(Semaphore_Close(&p->blocksSemaphore));
+    }
+    RINOK_THREAD(Semaphore_Create(&p->blocksSemaphore, numBlocksMax, numBlocksMax));
+  }
+
+  for (i = 0; i < MTCODER__BLOCKS_MAX - 1; i++)
+    p->freeBlockList[i] = i + 1;
+  p->freeBlockList[MTCODER__BLOCKS_MAX - 1] = (unsigned)(int)-1;
+  p->freeBlockHead = 0;
+
+  p->readProcessed = 0;
+  p->blockIndex = 0;
+  p->numBlocksMax = numBlocksMax;
+  p->stopReading = False;
+
+  #ifndef MTCODER__USE_WRITE_THREAD
+    p->writeIndex = 0;
+    p->writeRes = SZ_OK;
+    for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+      p->ReadyBlocks[i] = False;
+    p->numFinishedThreads = 0;
+  #endif
+
+  p->numStartedThreadsLimit = numThreads;
+  p->numStartedThreads = 0;
+
+  // for (i = 0; i < numThreads; i++)
+  {
+    CMtCoderThread *nextThread = &p->threads[p->numStartedThreads++];
+    RINOK(MtCoderThread_CreateAndStart(nextThread));
+  }
+
+  RINOK_THREAD(Event_Set(&p->readEvent))
+
+  #ifdef MTCODER__USE_WRITE_THREAD
+  {
+    unsigned bi = 0;
+
+    for (;; bi++)
+    {
+      if (bi >= numBlocksMax)
+        bi = 0;
+
+      RINOK_THREAD(Event_Wait(&p->writeEvents[bi]))
+
+      {
+        const CMtCoderBlock *block = &p->blocks[bi];
+        unsigned bufIndex = block->bufIndex;
+        BoolInt finished = block->finished;
+        if (res == SZ_OK && block->res != SZ_OK)
+          res = block->res;
+
+        if (bufIndex != (unsigned)(int)-1)
+        {
+          if (res == SZ_OK)
+          {
+            res = p->mtCallback->Write(p->mtCallbackObject, bufIndex);
+            if (res != SZ_OK)
+              MtProgress_SetError(&p->mtProgress, res);
+          }
+          
+          CriticalSection_Enter(&p->cs);
+          {
+            p->freeBlockList[bufIndex] = p->freeBlockHead;
+            p->freeBlockHead = bufIndex;
+          }
+          CriticalSection_Leave(&p->cs);
+        }
+        
+        RINOK_THREAD(Semaphore_Release1(&p->blocksSemaphore))
+
+        if (finished)
+          break;
+      }
+    }
+  }
+  #else
+  {
+    WRes wres = Event_Wait(&p->finishedEvent);
+    res = MY_SRes_HRESULT_FROM_WRes(wres);
+  }
+  #endif
+
+  if (res == SZ_OK)
+    res = p->readRes;
+
+  if (res == SZ_OK)
+    res = p->mtProgress.res;
+
+  #ifndef MTCODER__USE_WRITE_THREAD
+    if (res == SZ_OK)
+      res = p->writeRes;
+  #endif
+
+  if (res != SZ_OK)
+    MtCoder_Free(p);
+  return res;
+}
+
+#endif
@@ -0,0 +1,141 @@
+/* MtCoder.h -- Multi-thread Coder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#ifndef __MT_CODER_H
+#define __MT_CODER_H
+
+#include "MtDec.h"
+
+EXTERN_C_BEGIN
+
+/*
+  if (    defined MTCODER__USE_WRITE_THREAD) : main thread writes all data blocks to output stream
+  if (not defined MTCODER__USE_WRITE_THREAD) : any coder thread can write data blocks to output stream
+*/
+/* #define MTCODER__USE_WRITE_THREAD */
+
+#ifndef _7ZIP_ST
+  #define MTCODER__GET_NUM_BLOCKS_FROM_THREADS(numThreads) ((numThreads) + (numThreads) / 8 + 1)
+  #define MTCODER__THREADS_MAX 64
+  #define MTCODER__BLOCKS_MAX (MTCODER__GET_NUM_BLOCKS_FROM_THREADS(MTCODER__THREADS_MAX) + 3)
+#else
+  #define MTCODER__THREADS_MAX 1
+  #define MTCODER__BLOCKS_MAX 1
+#endif
+
+
+#ifndef _7ZIP_ST
+
+
+typedef struct
+{
+  ICompressProgress vt;
+  CMtProgress *mtProgress;
+  UInt64 inSize;
+  UInt64 outSize;
+} CMtProgressThunk;
+
+void MtProgressThunk_CreateVTable(CMtProgressThunk *p);
+    
+#define MtProgressThunk_Init(p) { (p)->inSize = 0; (p)->outSize = 0; }
+
+
+struct _CMtCoder;
+
+
+typedef struct
+{
+  struct _CMtCoder *mtCoder;
+  unsigned index;
+  int stop;
+  Byte *inBuf;
+
+  CAutoResetEvent startEvent;
+  CThread thread;
+} CMtCoderThread;
+
+
+typedef struct
+{
+  SRes (*Code)(void *p, unsigned coderIndex, unsigned outBufIndex,
+      const Byte *src, size_t srcSize, int finished);
+  SRes (*Write)(void *p, unsigned outBufIndex);
+} IMtCoderCallback2;
+
+
+typedef struct
+{
+  SRes res;
+  unsigned bufIndex;
+  BoolInt finished;
+} CMtCoderBlock;
+
+
+typedef struct _CMtCoder
+{
+  /* input variables */
+  
+  size_t blockSize;        /* size of input block */
+  unsigned numThreadsMax;
+  UInt64 expectedDataSize;
+
+  ISeqInStream *inStream;
+  const Byte *inData;
+  size_t inDataSize;
+
+  ICompressProgress *progress;
+  ISzAllocPtr allocBig;
+
+  IMtCoderCallback2 *mtCallback;
+  void *mtCallbackObject;
+
+  
+  /* internal variables */
+  
+  size_t allocatedBufsSize;
+
+  CAutoResetEvent readEvent;
+  CSemaphore blocksSemaphore;
+
+  BoolInt stopReading;
+  SRes readRes;
+
+  #ifdef MTCODER__USE_WRITE_THREAD
+    CAutoResetEvent writeEvents[MTCODER__BLOCKS_MAX];
+  #else
+    CAutoResetEvent finishedEvent;
+    SRes writeRes;
+    unsigned writeIndex;
+    Byte ReadyBlocks[MTCODER__BLOCKS_MAX];
+    LONG numFinishedThreads;
+  #endif
+
+  unsigned numStartedThreadsLimit;
+  unsigned numStartedThreads;
+
+  unsigned numBlocksMax;
+  unsigned blockIndex;
+  UInt64 readProcessed;
+
+  CCriticalSection cs;
+
+  unsigned freeBlockHead;
+  unsigned freeBlockList[MTCODER__BLOCKS_MAX];
+
+  CMtProgress mtProgress;
+  CMtCoderBlock blocks[MTCODER__BLOCKS_MAX];
+  CMtCoderThread threads[MTCODER__THREADS_MAX];
+} CMtCoder;
+
+
+void MtCoder_Construct(CMtCoder *p);
+void MtCoder_Destruct(CMtCoder *p);
+SRes MtCoder_Code(CMtCoder *p);
+
+
+#endif
+
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,201 @@
+/* MtDec.h -- Multi-thread Decoder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#ifndef __MT_DEC_H
+#define __MT_DEC_H
+
+#include "7zTypes.h"
+
+#ifndef _7ZIP_ST
+#include "Threads.h"
+#endif
+
+EXTERN_C_BEGIN
+
+#ifndef _7ZIP_ST
+
+#ifndef _7ZIP_ST
+  #define MTDEC__THREADS_MAX 32
+#else
+  #define MTDEC__THREADS_MAX 1
+#endif
+
+
+typedef struct
+{
+  ICompressProgress *progress;
+  SRes res;
+  UInt64 totalInSize;
+  UInt64 totalOutSize;
+  CCriticalSection cs;
+} CMtProgress;
+
+void MtProgress_Init(CMtProgress *p, ICompressProgress *progress);
+SRes MtProgress_Progress_ST(CMtProgress *p);
+SRes MtProgress_ProgressAdd(CMtProgress *p, UInt64 inSize, UInt64 outSize);
+SRes MtProgress_GetError(CMtProgress *p);
+void MtProgress_SetError(CMtProgress *p, SRes res);
+
+struct _CMtDec;
+
+typedef struct
+{
+  struct _CMtDec *mtDec;
+  unsigned index;
+  void *inBuf;
+
+  size_t inDataSize_Start; // size of input data in start block
+  UInt64 inDataSize;       // total size of input data in all blocks
+
+  CThread thread;
+  CAutoResetEvent canRead;
+  CAutoResetEvent canWrite;
+  void  *allocaPtr;
+} CMtDecThread;
+
+void MtDecThread_FreeInBufs(CMtDecThread *t);
+
+
+typedef enum
+{
+  MTDEC_PARSE_CONTINUE, // continue this block with more input data
+  MTDEC_PARSE_OVERFLOW, // MT buffers overflow, need switch to single-thread
+  MTDEC_PARSE_NEW,      // new block
+  MTDEC_PARSE_END       // end of block threading. But we still can return to threading after Write(&needContinue)
+} EMtDecParseState;
+
+typedef struct
+{
+  // in
+  int startCall;
+  const Byte *src;
+  size_t srcSize;
+      // in  : (srcSize == 0) is allowed
+      // out : it's allowed to return less that actually was used ?
+  int srcFinished;
+
+  // out
+  EMtDecParseState state;
+  BoolInt canCreateNewThread;
+  UInt64 outPos; // check it (size_t)
+} CMtDecCallbackInfo;
+
+
+typedef struct
+{
+  void (*Parse)(void *p, unsigned coderIndex, CMtDecCallbackInfo *ci);
+  
+  // PreCode() and Code():
+  // (SRes_return_result != SZ_OK) means stop decoding, no need another blocks
+  SRes (*PreCode)(void *p, unsigned coderIndex);
+  SRes (*Code)(void *p, unsigned coderIndex,
+      const Byte *src, size_t srcSize, int srcFinished,
+      UInt64 *inCodePos, UInt64 *outCodePos, int *stop);
+  // stop - means stop another Code calls
+
+
+  /* Write() must be called, if Parse() was called
+      set (needWrite) if
+      {
+         && (was not interrupted by progress)
+         && (was not interrupted in previous block)
+      }
+
+    out:
+      if (*needContinue), decoder still need to continue decoding with new iteration,
+         even after MTDEC_PARSE_END
+      if (*canRecode), we didn't flush current block data, so we still can decode current block later.
+  */
+  SRes (*Write)(void *p, unsigned coderIndex,
+      BoolInt needWriteToStream,
+      const Byte *src, size_t srcSize,
+      // int srcFinished,
+      BoolInt *needContinue,
+      BoolInt *canRecode);
+} IMtDecCallback;
+
+
+
+typedef struct _CMtDec
+{
+  /* input variables */
+  
+  size_t inBufSize;        /* size of input block */
+  unsigned numThreadsMax;
+  // size_t inBlockMax;
+  unsigned numThreadsMax_2;
+
+  ISeqInStream *inStream;
+  // const Byte *inData;
+  // size_t inDataSize;
+
+  ICompressProgress *progress;
+  ISzAllocPtr alloc;
+
+  IMtDecCallback *mtCallback;
+  void *mtCallbackObject;
+
+  
+  /* internal variables */
+  
+  size_t allocatedBufsSize;
+
+  BoolInt exitThread;
+  WRes exitThreadWRes;
+
+  UInt64 blockIndex;
+  BoolInt isAllocError;
+  BoolInt overflow;
+  SRes threadingErrorSRes;
+
+  BoolInt needContinue;
+
+  // CAutoResetEvent finishedEvent;
+
+  SRes readRes;
+  SRes codeRes;
+
+  BoolInt wasInterrupted;
+
+  unsigned numStartedThreads_Limit;
+  unsigned numStartedThreads;
+
+  Byte *crossBlock;
+  size_t crossStart;
+  size_t crossEnd;
+  UInt64 readProcessed;
+  BoolInt readWasFinished;
+  UInt64 inProcessed;
+
+  unsigned filledThreadStart;
+  unsigned numFilledThreads;
+
+  #ifndef _7ZIP_ST
+  BoolInt needInterrupt;
+  UInt64 interruptIndex;
+  CMtProgress mtProgress;
+  CMtDecThread threads[MTDEC__THREADS_MAX];
+  #endif
+} CMtDec;
+
+
+void MtDec_Construct(CMtDec *p);
+void MtDec_Destruct(CMtDec *p);
+
+/*
+MtDec_Code() returns:
+  SZ_OK - in most cases
+  MY_SRes_HRESULT_FROM_WRes(WRes_error) - in case of unexpected error in threading function
+*/
+  
+SRes MtDec_Code(CMtDec *p);
+Byte *MtDec_GetCrossBuff(CMtDec *p);
+
+int MtDec_PrepareRead(CMtDec *p);
+const Byte *MtDec_Read(CMtDec *p, size_t *inLim);
+
+#endif
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,85 @@
+/* Ppmd.h -- PPMD codec common code
+2017-04-03 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#ifndef __PPMD_H
+#define __PPMD_H
+
+#include "CpuArch.h"
+
+EXTERN_C_BEGIN
+
+#ifdef MY_CPU_32BIT
+  #define PPMD_32BIT
+#endif
+
+#define PPMD_INT_BITS 7
+#define PPMD_PERIOD_BITS 7
+#define PPMD_BIN_SCALE (1 << (PPMD_INT_BITS + PPMD_PERIOD_BITS))
+
+#define PPMD_GET_MEAN_SPEC(summ, shift, round) (((summ) + (1 << ((shift) - (round)))) >> (shift))
+#define PPMD_GET_MEAN(summ) PPMD_GET_MEAN_SPEC((summ), PPMD_PERIOD_BITS, 2)
+#define PPMD_UPDATE_PROB_0(prob) ((prob) + (1 << PPMD_INT_BITS) - PPMD_GET_MEAN(prob))
+#define PPMD_UPDATE_PROB_1(prob) ((prob) - PPMD_GET_MEAN(prob))
+
+#define PPMD_N1 4
+#define PPMD_N2 4
+#define PPMD_N3 4
+#define PPMD_N4 ((128 + 3 - 1 * PPMD_N1 - 2 * PPMD_N2 - 3 * PPMD_N3) / 4)
+#define PPMD_NUM_INDEXES (PPMD_N1 + PPMD_N2 + PPMD_N3 + PPMD_N4)
+
+#pragma pack(push, 1)
+/* Most compilers works OK here even without #pragma pack(push, 1), but some GCC compilers need it. */
+
+/* SEE-contexts for PPM-contexts with masked symbols */
+typedef struct
+{
+  UInt16 Summ; /* Freq */
+  Byte Shift;  /* Speed of Freq change; low Shift is for fast change */
+  Byte Count;  /* Count to next change of Shift */
+} CPpmd_See;
+
+#define Ppmd_See_Update(p)  if ((p)->Shift < PPMD_PERIOD_BITS && --(p)->Count == 0) \
+    { (p)->Summ <<= 1; (p)->Count = (Byte)(3 << (p)->Shift++); }
+
+typedef struct
+{
+  Byte Symbol;
+  Byte Freq;
+  UInt16 SuccessorLow;
+  UInt16 SuccessorHigh;
+} CPpmd_State;
+
+#pragma pack(pop)
+
+typedef
+  #ifdef PPMD_32BIT
+    CPpmd_State *
+  #else
+    UInt32
+  #endif
+  CPpmd_State_Ref;
+
+typedef
+  #ifdef PPMD_32BIT
+    void *
+  #else
+    UInt32
+  #endif
+  CPpmd_Void_Ref;
+
+typedef
+  #ifdef PPMD_32BIT
+    Byte *
+  #else
+    UInt32
+  #endif
+  CPpmd_Byte_Ref;
+
+#define PPMD_SetAllBitsIn256Bytes(p) \
+  { size_t z; for (z = 0; z < 256 / sizeof(p[0]); z += 8) { \
+  p[z+7] = p[z+6] = p[z+5] = p[z+4] = p[z+3] = p[z+2] = p[z+1] = p[z+0] = ~(size_t)0; }}
+
+EXTERN_C_END
+ 
+#endif
@@ -0,0 +1,712 @@
+/* Ppmd7.c -- PPMdH codec
+2018-07-04 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "Ppmd7.h"
+
+const Byte PPMD7_kExpEscape[16] = { 25, 14, 9, 7, 5, 5, 4, 4, 4, 3, 3, 3, 2, 2, 2, 2 };
+static const UInt16 kInitBinEsc[] = { 0x3CDD, 0x1F3F, 0x59BF, 0x48F3, 0x64A1, 0x5ABC, 0x6632, 0x6051};
+
+#define MAX_FREQ 124
+#define UNIT_SIZE 12
+
+#define U2B(nu) ((UInt32)(nu) * UNIT_SIZE)
+#define U2I(nu) (p->Units2Indx[(size_t)(nu) - 1])
+#define I2U(indx) (p->Indx2Units[indx])
+
+#ifdef PPMD_32BIT
+  #define REF(ptr) (ptr)
+#else
+  #define REF(ptr) ((UInt32)((Byte *)(ptr) - (p)->Base))
+#endif
+
+#define STATS_REF(ptr) ((CPpmd_State_Ref)REF(ptr))
+
+#define CTX(ref) ((CPpmd7_Context *)Ppmd7_GetContext(p, ref))
+#define STATS(ctx) Ppmd7_GetStats(p, ctx)
+#define ONE_STATE(ctx) Ppmd7Context_OneState(ctx)
+#define SUFFIX(ctx) CTX((ctx)->Suffix)
+
+typedef CPpmd7_Context * CTX_PTR;
+
+struct CPpmd7_Node_;
+
+typedef
+  #ifdef PPMD_32BIT
+    struct CPpmd7_Node_ *
+  #else
+    UInt32
+  #endif
+  CPpmd7_Node_Ref;
+
+typedef struct CPpmd7_Node_
+{
+  UInt16 Stamp; /* must be at offset 0 as CPpmd7_Context::NumStats. Stamp=0 means free */
+  UInt16 NU;
+  CPpmd7_Node_Ref Next; /* must be at offset >= 4 */
+  CPpmd7_Node_Ref Prev;
+} CPpmd7_Node;
+
+#ifdef PPMD_32BIT
+  #define NODE(ptr) (ptr)
+#else
+  #define NODE(offs) ((CPpmd7_Node *)(p->Base + (offs)))
+#endif
+
+void Ppmd7_Construct(CPpmd7 *p)
+{
+  unsigned i, k, m;
+
+  p->Base = 0;
+
+  for (i = 0, k = 0; i < PPMD_NUM_INDEXES; i++)
+  {
+    unsigned step = (i >= 12 ? 4 : (i >> 2) + 1);
+    do { p->Units2Indx[k++] = (Byte)i; } while (--step);
+    p->Indx2Units[i] = (Byte)k;
+  }
+
+  p->NS2BSIndx[0] = (0 << 1);
+  p->NS2BSIndx[1] = (1 << 1);
+  memset(p->NS2BSIndx + 2, (2 << 1), 9);
+  memset(p->NS2BSIndx + 11, (3 << 1), 256 - 11);
+
+  for (i = 0; i < 3; i++)
+    p->NS2Indx[i] = (Byte)i;
+  for (m = i, k = 1; i < 256; i++)
+  {
+    p->NS2Indx[i] = (Byte)m;
+    if (--k == 0)
+      k = (++m) - 2;
+  }
+
+  memset(p->HB2Flag, 0, 0x40);
+  memset(p->HB2Flag + 0x40, 8, 0x100 - 0x40);
+}
+
+void Ppmd7_Free(CPpmd7 *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->Base);
+  p->Size = 0;
+  p->Base = 0;
+}
+
+BoolInt Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc)
+{
+  if (!p->Base || p->Size != size)
+  {
+    size_t size2;
+    Ppmd7_Free(p, alloc);
+    size2 = 0
+      #ifndef PPMD_32BIT
+      + UNIT_SIZE
+      #endif
+      ;
+    p->AlignOffset =
+      #ifdef PPMD_32BIT
+        (4 - size) & 3;
+      #else
+        4 - (size & 3);
+      #endif
+    if ((p->Base = (Byte *)ISzAlloc_Alloc(alloc, p->AlignOffset + size + size2)) == 0)
+      return False;
+    p->Size = size;
+  }
+  return True;
+}
+
+static void InsertNode(CPpmd7 *p, void *node, unsigned indx)
+{
+  *((CPpmd_Void_Ref *)node) = p->FreeList[indx];
+  p->FreeList[indx] = REF(node);
+}
+
+static void *RemoveNode(CPpmd7 *p, unsigned indx)
+{
+  CPpmd_Void_Ref *node = (CPpmd_Void_Ref *)Ppmd7_GetPtr(p, p->FreeList[indx]);
+  p->FreeList[indx] = *node;
+  return node;
+}
+
+static void SplitBlock(CPpmd7 *p, void *ptr, unsigned oldIndx, unsigned newIndx)
+{
+  unsigned i, nu = I2U(oldIndx) - I2U(newIndx);
+  ptr = (Byte *)ptr + U2B(I2U(newIndx));
+  if (I2U(i = U2I(nu)) != nu)
+  {
+    unsigned k = I2U(--i);
+    InsertNode(p, ((Byte *)ptr) + U2B(k), nu - k - 1);
+  }
+  InsertNode(p, ptr, i);
+}
+
+static void GlueFreeBlocks(CPpmd7 *p)
+{
+  #ifdef PPMD_32BIT
+  CPpmd7_Node headItem;
+  CPpmd7_Node_Ref head = &headItem;
+  #else
+  CPpmd7_Node_Ref head = p->AlignOffset + p->Size;
+  #endif
+  
+  CPpmd7_Node_Ref n = head;
+  unsigned i;
+
+  p->GlueCount = 255;
+
+  /* create doubly-linked list of free blocks */
+  for (i = 0; i < PPMD_NUM_INDEXES; i++)
+  {
+    UInt16 nu = I2U(i);
+    CPpmd7_Node_Ref next = (CPpmd7_Node_Ref)p->FreeList[i];
+    p->FreeList[i] = 0;
+    while (next != 0)
+    {
+      CPpmd7_Node *node = NODE(next);
+      node->Next = n;
+      n = NODE(n)->Prev = next;
+      next = *(const CPpmd7_Node_Ref *)node;
+      node->Stamp = 0;
+      node->NU = (UInt16)nu;
+    }
+  }
+  NODE(head)->Stamp = 1;
+  NODE(head)->Next = n;
+  NODE(n)->Prev = head;
+  if (p->LoUnit != p->HiUnit)
+    ((CPpmd7_Node *)p->LoUnit)->Stamp = 1;
+  
+  /* Glue free blocks */
+  while (n != head)
+  {
+    CPpmd7_Node *node = NODE(n);
+    UInt32 nu = (UInt32)node->NU;
+    for (;;)
+    {
+      CPpmd7_Node *node2 = NODE(n) + nu;
+      nu += node2->NU;
+      if (node2->Stamp != 0 || nu >= 0x10000)
+        break;
+      NODE(node2->Prev)->Next = node2->Next;
+      NODE(node2->Next)->Prev = node2->Prev;
+      node->NU = (UInt16)nu;
+    }
+    n = node->Next;
+  }
+  
+  /* Fill lists of free blocks */
+  for (n = NODE(head)->Next; n != head;)
+  {
+    CPpmd7_Node *node = NODE(n);
+    unsigned nu;
+    CPpmd7_Node_Ref next = node->Next;
+    for (nu = node->NU; nu > 128; nu -= 128, node += 128)
+      InsertNode(p, node, PPMD_NUM_INDEXES - 1);
+    if (I2U(i = U2I(nu)) != nu)
+    {
+      unsigned k = I2U(--i);
+      InsertNode(p, node + k, nu - k - 1);
+    }
+    InsertNode(p, node, i);
+    n = next;
+  }
+}
+
+static void *AllocUnitsRare(CPpmd7 *p, unsigned indx)
+{
+  unsigned i;
+  void *retVal;
+  if (p->GlueCount == 0)
+  {
+    GlueFreeBlocks(p);
+    if (p->FreeList[indx] != 0)
+      return RemoveNode(p, indx);
+  }
+  i = indx;
+  do
+  {
+    if (++i == PPMD_NUM_INDEXES)
+    {
+      UInt32 numBytes = U2B(I2U(indx));
+      p->GlueCount--;
+      return ((UInt32)(p->UnitsStart - p->Text) > numBytes) ? (p->UnitsStart -= numBytes) : (NULL);
+    }
+  }
+  while (p->FreeList[i] == 0);
+  retVal = RemoveNode(p, i);
+  SplitBlock(p, retVal, i, indx);
+  return retVal;
+}
+
+static void *AllocUnits(CPpmd7 *p, unsigned indx)
+{
+  UInt32 numBytes;
+  if (p->FreeList[indx] != 0)
+    return RemoveNode(p, indx);
+  numBytes = U2B(I2U(indx));
+  if (numBytes <= (UInt32)(p->HiUnit - p->LoUnit))
+  {
+    void *retVal = p->LoUnit;
+    p->LoUnit += numBytes;
+    return retVal;
+  }
+  return AllocUnitsRare(p, indx);
+}
+
+#define MyMem12Cpy(dest, src, num) \
+  { UInt32 *d = (UInt32 *)dest; const UInt32 *s = (const UInt32 *)src; UInt32 n = num; \
+    do { d[0] = s[0]; d[1] = s[1]; d[2] = s[2]; s += 3; d += 3; } while (--n); }
+
+static void *ShrinkUnits(CPpmd7 *p, void *oldPtr, unsigned oldNU, unsigned newNU)
+{
+  unsigned i0 = U2I(oldNU);
+  unsigned i1 = U2I(newNU);
+  if (i0 == i1)
+    return oldPtr;
+  if (p->FreeList[i1] != 0)
+  {
+    void *ptr = RemoveNode(p, i1);
+    MyMem12Cpy(ptr, oldPtr, newNU);
+    InsertNode(p, oldPtr, i0);
+    return ptr;
+  }
+  SplitBlock(p, oldPtr, i0, i1);
+  return oldPtr;
+}
+
+#define SUCCESSOR(p) ((CPpmd_Void_Ref)((p)->SuccessorLow | ((UInt32)(p)->SuccessorHigh << 16)))
+
+static void SetSuccessor(CPpmd_State *p, CPpmd_Void_Ref v)
+{
+  (p)->SuccessorLow = (UInt16)((UInt32)(v) & 0xFFFF);
+  (p)->SuccessorHigh = (UInt16)(((UInt32)(v) >> 16) & 0xFFFF);
+}
+
+static void RestartModel(CPpmd7 *p)
+{
+  unsigned i, k, m;
+
+  memset(p->FreeList, 0, sizeof(p->FreeList));
+  p->Text = p->Base + p->AlignOffset;
+  p->HiUnit = p->Text + p->Size;
+  p->LoUnit = p->UnitsStart = p->HiUnit - p->Size / 8 / UNIT_SIZE * 7 * UNIT_SIZE;
+  p->GlueCount = 0;
+
+  p->OrderFall = p->MaxOrder;
+  p->RunLength = p->InitRL = -(Int32)((p->MaxOrder < 12) ? p->MaxOrder : 12) - 1;
+  p->PrevSuccess = 0;
+
+  p->MinContext = p->MaxContext = (CTX_PTR)(p->HiUnit -= UNIT_SIZE); /* AllocContext(p); */
+  p->MinContext->Suffix = 0;
+  p->MinContext->NumStats = 256;
+  p->MinContext->SummFreq = 256 + 1;
+  p->FoundState = (CPpmd_State *)p->LoUnit; /* AllocUnits(p, PPMD_NUM_INDEXES - 1); */
+  p->LoUnit += U2B(256 / 2);
+  p->MinContext->Stats = REF(p->FoundState);
+  for (i = 0; i < 256; i++)
+  {
+    CPpmd_State *s = &p->FoundState[i];
+    s->Symbol = (Byte)i;
+    s->Freq = 1;
+    SetSuccessor(s, 0);
+  }
+
+  for (i = 0; i < 128; i++)
+    for (k = 0; k < 8; k++)
+    {
+      UInt16 *dest = p->BinSumm[i] + k;
+      UInt16 val = (UInt16)(PPMD_BIN_SCALE - kInitBinEsc[k] / (i + 2));
+      for (m = 0; m < 64; m += 8)
+        dest[m] = val;
+    }
+  
+  for (i = 0; i < 25; i++)
+    for (k = 0; k < 16; k++)
+    {
+      CPpmd_See *s = &p->See[i][k];
+      s->Summ = (UInt16)((5 * i + 10) << (s->Shift = PPMD_PERIOD_BITS - 4));
+      s->Count = 4;
+    }
+}
+
+void Ppmd7_Init(CPpmd7 *p, unsigned maxOrder)
+{
+  p->MaxOrder = maxOrder;
+  RestartModel(p);
+  p->DummySee.Shift = PPMD_PERIOD_BITS;
+  p->DummySee.Summ = 0; /* unused */
+  p->DummySee.Count = 64; /* unused */
+}
+
+static CTX_PTR CreateSuccessors(CPpmd7 *p, BoolInt skip)
+{
+  CPpmd_State upState;
+  CTX_PTR c = p->MinContext;
+  CPpmd_Byte_Ref upBranch = (CPpmd_Byte_Ref)SUCCESSOR(p->FoundState);
+  CPpmd_State *ps[PPMD7_MAX_ORDER];
+  unsigned numPs = 0;
+  
+  if (!skip)
+    ps[numPs++] = p->FoundState;
+  
+  while (c->Suffix)
+  {
+    CPpmd_Void_Ref successor;
+    CPpmd_State *s;
+    c = SUFFIX(c);
+    if (c->NumStats != 1)
+    {
+      for (s = STATS(c); s->Symbol != p->FoundState->Symbol; s++);
+    }
+    else
+      s = ONE_STATE(c);
+    successor = SUCCESSOR(s);
+    if (successor != upBranch)
+    {
+      c = CTX(successor);
+      if (numPs == 0)
+        return c;
+      break;
+    }
+    ps[numPs++] = s;
+  }
+  
+  upState.Symbol = *(const Byte *)Ppmd7_GetPtr(p, upBranch);
+  SetSuccessor(&upState, upBranch + 1);
+  
+  if (c->NumStats == 1)
+    upState.Freq = ONE_STATE(c)->Freq;
+  else
+  {
+    UInt32 cf, s0;
+    CPpmd_State *s;
+    for (s = STATS(c); s->Symbol != upState.Symbol; s++);
+    cf = s->Freq - 1;
+    s0 = c->SummFreq - c->NumStats - cf;
+    upState.Freq = (Byte)(1 + ((2 * cf <= s0) ? (5 * cf > s0) : ((2 * cf + 3 * s0 - 1) / (2 * s0))));
+  }
+
+  do
+  {
+    /* Create Child */
+    CTX_PTR c1; /* = AllocContext(p); */
+    if (p->HiUnit != p->LoUnit)
+      c1 = (CTX_PTR)(p->HiUnit -= UNIT_SIZE);
+    else if (p->FreeList[0] != 0)
+      c1 = (CTX_PTR)RemoveNode(p, 0);
+    else
+    {
+      c1 = (CTX_PTR)AllocUnitsRare(p, 0);
+      if (!c1)
+        return NULL;
+    }
+    c1->NumStats = 1;
+    *ONE_STATE(c1) = upState;
+    c1->Suffix = REF(c);
+    SetSuccessor(ps[--numPs], REF(c1));
+    c = c1;
+  }
+  while (numPs != 0);
+  
+  return c;
+}
+
+static void SwapStates(CPpmd_State *t1, CPpmd_State *t2)
+{
+  CPpmd_State tmp = *t1;
+  *t1 = *t2;
+  *t2 = tmp;
+}
+
+static void UpdateModel(CPpmd7 *p)
+{
+  CPpmd_Void_Ref successor, fSuccessor = SUCCESSOR(p->FoundState);
+  CTX_PTR c;
+  unsigned s0, ns;
+  
+  if (p->FoundState->Freq < MAX_FREQ / 4 && p->MinContext->Suffix != 0)
+  {
+    c = SUFFIX(p->MinContext);
+    
+    if (c->NumStats == 1)
+    {
+      CPpmd_State *s = ONE_STATE(c);
+      if (s->Freq < 32)
+        s->Freq++;
+    }
+    else
+    {
+      CPpmd_State *s = STATS(c);
+      if (s->Symbol != p->FoundState->Symbol)
+      {
+        do { s++; } while (s->Symbol != p->FoundState->Symbol);
+        if (s[0].Freq >= s[-1].Freq)
+        {
+          SwapStates(&s[0], &s[-1]);
+          s--;
+        }
+      }
+      if (s->Freq < MAX_FREQ - 9)
+      {
+        s->Freq += 2;
+        c->SummFreq += 2;
+      }
+    }
+  }
+
+  if (p->OrderFall == 0)
+  {
+    p->MinContext = p->MaxContext = CreateSuccessors(p, True);
+    if (p->MinContext == 0)
+    {
+      RestartModel(p);
+      return;
+    }
+    SetSuccessor(p->FoundState, REF(p->MinContext));
+    return;
+  }
+  
+  *p->Text++ = p->FoundState->Symbol;
+  successor = REF(p->Text);
+  if (p->Text >= p->UnitsStart)
+  {
+    RestartModel(p);
+    return;
+  }
+  
+  if (fSuccessor)
+  {
+    if (fSuccessor <= successor)
+    {
+      CTX_PTR cs = CreateSuccessors(p, False);
+      if (cs == NULL)
+      {
+        RestartModel(p);
+        return;
+      }
+      fSuccessor = REF(cs);
+    }
+    if (--p->OrderFall == 0)
+    {
+      successor = fSuccessor;
+      p->Text -= (p->MaxContext != p->MinContext);
+    }
+  }
+  else
+  {
+    SetSuccessor(p->FoundState, successor);
+    fSuccessor = REF(p->MinContext);
+  }
+  
+  s0 = p->MinContext->SummFreq - (ns = p->MinContext->NumStats) - (p->FoundState->Freq - 1);
+  
+  for (c = p->MaxContext; c != p->MinContext; c = SUFFIX(c))
+  {
+    unsigned ns1;
+    UInt32 cf, sf;
+    if ((ns1 = c->NumStats) != 1)
+    {
+      if ((ns1 & 1) == 0)
+      {
+        /* Expand for one UNIT */
+        unsigned oldNU = ns1 >> 1;
+        unsigned i = U2I(oldNU);
+        if (i != U2I((size_t)oldNU + 1))
+        {
+          void *ptr = AllocUnits(p, i + 1);
+          void *oldPtr;
+          if (!ptr)
+          {
+            RestartModel(p);
+            return;
+          }
+          oldPtr = STATS(c);
+          MyMem12Cpy(ptr, oldPtr, oldNU);
+          InsertNode(p, oldPtr, i);
+          c->Stats = STATS_REF(ptr);
+        }
+      }
+      c->SummFreq = (UInt16)(c->SummFreq + (2 * ns1 < ns) + 2 * ((4 * ns1 <= ns) & (c->SummFreq <= 8 * ns1)));
+    }
+    else
+    {
+      CPpmd_State *s = (CPpmd_State*)AllocUnits(p, 0);
+      if (!s)
+      {
+        RestartModel(p);
+        return;
+      }
+      *s = *ONE_STATE(c);
+      c->Stats = REF(s);
+      if (s->Freq < MAX_FREQ / 4 - 1)
+        s->Freq <<= 1;
+      else
+        s->Freq = MAX_FREQ - 4;
+      c->SummFreq = (UInt16)(s->Freq + p->InitEsc + (ns > 3));
+    }
+    cf = 2 * (UInt32)p->FoundState->Freq * (c->SummFreq + 6);
+    sf = (UInt32)s0 + c->SummFreq;
+    if (cf < 6 * sf)
+    {
+      cf = 1 + (cf > sf) + (cf >= 4 * sf);
+      c->SummFreq += 3;
+    }
+    else
+    {
+      cf = 4 + (cf >= 9 * sf) + (cf >= 12 * sf) + (cf >= 15 * sf);
+      c->SummFreq = (UInt16)(c->SummFreq + cf);
+    }
+    {
+      CPpmd_State *s = STATS(c) + ns1;
+      SetSuccessor(s, successor);
+      s->Symbol = p->FoundState->Symbol;
+      s->Freq = (Byte)cf;
+      c->NumStats = (UInt16)(ns1 + 1);
+    }
+  }
+  p->MaxContext = p->MinContext = CTX(fSuccessor);
+}
+  
+static void Rescale(CPpmd7 *p)
+{
+  unsigned i, adder, sumFreq, escFreq;
+  CPpmd_State *stats = STATS(p->MinContext);
+  CPpmd_State *s = p->FoundState;
+  {
+    CPpmd_State tmp = *s;
+    for (; s != stats; s--)
+      s[0] = s[-1];
+    *s = tmp;
+  }
+  escFreq = p->MinContext->SummFreq - s->Freq;
+  s->Freq += 4;
+  adder = (p->OrderFall != 0);
+  s->Freq = (Byte)((s->Freq + adder) >> 1);
+  sumFreq = s->Freq;
+  
+  i = p->MinContext->NumStats - 1;
+  do
+  {
+    escFreq -= (++s)->Freq;
+    s->Freq = (Byte)((s->Freq + adder) >> 1);
+    sumFreq += s->Freq;
+    if (s[0].Freq > s[-1].Freq)
+    {
+      CPpmd_State *s1 = s;
+      CPpmd_State tmp = *s1;
+      do
+        s1[0] = s1[-1];
+      while (--s1 != stats && tmp.Freq > s1[-1].Freq);
+      *s1 = tmp;
+    }
+  }
+  while (--i);
+  
+  if (s->Freq == 0)
+  {
+    unsigned numStats = p->MinContext->NumStats;
+    unsigned n0, n1;
+    do { i++; } while ((--s)->Freq == 0);
+    escFreq += i;
+    p->MinContext->NumStats = (UInt16)(p->MinContext->NumStats - i);
+    if (p->MinContext->NumStats == 1)
+    {
+      CPpmd_State tmp = *stats;
+      do
+      {
+        tmp.Freq = (Byte)(tmp.Freq - (tmp.Freq >> 1));
+        escFreq >>= 1;
+      }
+      while (escFreq > 1);
+      InsertNode(p, stats, U2I(((numStats + 1) >> 1)));
+      *(p->FoundState = ONE_STATE(p->MinContext)) = tmp;
+      return;
+    }
+    n0 = (numStats + 1) >> 1;
+    n1 = (p->MinContext->NumStats + 1) >> 1;
+    if (n0 != n1)
+      p->MinContext->Stats = STATS_REF(ShrinkUnits(p, stats, n0, n1));
+  }
+  p->MinContext->SummFreq = (UInt16)(sumFreq + escFreq - (escFreq >> 1));
+  p->FoundState = STATS(p->MinContext);
+}
+
+CPpmd_See *Ppmd7_MakeEscFreq(CPpmd7 *p, unsigned numMasked, UInt32 *escFreq)
+{
+  CPpmd_See *see;
+  unsigned nonMasked = p->MinContext->NumStats - numMasked;
+  if (p->MinContext->NumStats != 256)
+  {
+    see = p->See[(unsigned)p->NS2Indx[(size_t)nonMasked - 1]] +
+        (nonMasked < (unsigned)SUFFIX(p->MinContext)->NumStats - p->MinContext->NumStats) +
+        2 * (unsigned)(p->MinContext->SummFreq < 11 * p->MinContext->NumStats) +
+        4 * (unsigned)(numMasked > nonMasked) +
+        p->HiBitsFlag;
+    {
+      unsigned r = (see->Summ >> see->Shift);
+      see->Summ = (UInt16)(see->Summ - r);
+      *escFreq = r + (r == 0);
+    }
+  }
+  else
+  {
+    see = &p->DummySee;
+    *escFreq = 1;
+  }
+  return see;
+}
+
+static void NextContext(CPpmd7 *p)
+{
+  CTX_PTR c = CTX(SUCCESSOR(p->FoundState));
+  if (p->OrderFall == 0 && (Byte *)c > p->Text)
+    p->MinContext = p->MaxContext = c;
+  else
+    UpdateModel(p);
+}
+
+void Ppmd7_Update1(CPpmd7 *p)
+{
+  CPpmd_State *s = p->FoundState;
+  s->Freq += 4;
+  p->MinContext->SummFreq += 4;
+  if (s[0].Freq > s[-1].Freq)
+  {
+    SwapStates(&s[0], &s[-1]);
+    p->FoundState = --s;
+    if (s->Freq > MAX_FREQ)
+      Rescale(p);
+  }
+  NextContext(p);
+}
+
+void Ppmd7_Update1_0(CPpmd7 *p)
+{
+  p->PrevSuccess = (2 * p->FoundState->Freq > p->MinContext->SummFreq);
+  p->RunLength += p->PrevSuccess;
+  p->MinContext->SummFreq += 4;
+  if ((p->FoundState->Freq += 4) > MAX_FREQ)
+    Rescale(p);
+  NextContext(p);
+}
+
+void Ppmd7_UpdateBin(CPpmd7 *p)
+{
+  p->FoundState->Freq = (Byte)(p->FoundState->Freq + (p->FoundState->Freq < 128 ? 1: 0));
+  p->PrevSuccess = 1;
+  p->RunLength++;
+  NextContext(p);
+}
+
+void Ppmd7_Update2(CPpmd7 *p)
+{
+  p->MinContext->SummFreq += 4;
+  if ((p->FoundState->Freq += 4) > MAX_FREQ)
+    Rescale(p);
+  p->RunLength = p->InitRL;
+  UpdateModel(p);
+}
@@ -0,0 +1,142 @@
+/* Ppmd7.h -- PPMdH compression codec
+2018-07-04 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+/* This code supports virtual RangeDecoder and includes the implementation
+of RangeCoder from 7z, instead of RangeCoder from original PPMd var.H.
+If you need the compatibility with original PPMd var.H, you can use external RangeDecoder */
+
+#ifndef __PPMD7_H
+#define __PPMD7_H
+
+#include "Ppmd.h"
+
+EXTERN_C_BEGIN
+
+#define PPMD7_MIN_ORDER 2
+#define PPMD7_MAX_ORDER 64
+
+#define PPMD7_MIN_MEM_SIZE (1 << 11)
+#define PPMD7_MAX_MEM_SIZE (0xFFFFFFFF - 12 * 3)
+
+struct CPpmd7_Context_;
+
+typedef
+  #ifdef PPMD_32BIT
+    struct CPpmd7_Context_ *
+  #else
+    UInt32
+  #endif
+  CPpmd7_Context_Ref;
+
+typedef struct CPpmd7_Context_
+{
+  UInt16 NumStats;
+  UInt16 SummFreq;
+  CPpmd_State_Ref Stats;
+  CPpmd7_Context_Ref Suffix;
+} CPpmd7_Context;
+
+#define Ppmd7Context_OneState(p) ((CPpmd_State *)&(p)->SummFreq)
+
+typedef struct
+{
+  CPpmd7_Context *MinContext, *MaxContext;
+  CPpmd_State *FoundState;
+  unsigned OrderFall, InitEsc, PrevSuccess, MaxOrder, HiBitsFlag;
+  Int32 RunLength, InitRL; /* must be 32-bit at least */
+
+  UInt32 Size;
+  UInt32 GlueCount;
+  Byte *Base, *LoUnit, *HiUnit, *Text, *UnitsStart;
+  UInt32 AlignOffset;
+
+  Byte Indx2Units[PPMD_NUM_INDEXES];
+  Byte Units2Indx[128];
+  CPpmd_Void_Ref FreeList[PPMD_NUM_INDEXES];
+  Byte NS2Indx[256], NS2BSIndx[256], HB2Flag[256];
+  CPpmd_See DummySee, See[25][16];
+  UInt16 BinSumm[128][64];
+} CPpmd7;
+
+void Ppmd7_Construct(CPpmd7 *p);
+BoolInt Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc);
+void Ppmd7_Free(CPpmd7 *p, ISzAllocPtr alloc);
+void Ppmd7_Init(CPpmd7 *p, unsigned maxOrder);
+#define Ppmd7_WasAllocated(p) ((p)->Base != NULL)
+
+
+/* ---------- Internal Functions ---------- */
+
+extern const Byte PPMD7_kExpEscape[16];
+
+#ifdef PPMD_32BIT
+  #define Ppmd7_GetPtr(p, ptr) (ptr)
+  #define Ppmd7_GetContext(p, ptr) (ptr)
+  #define Ppmd7_GetStats(p, ctx) ((ctx)->Stats)
+#else
+  #define Ppmd7_GetPtr(p, offs) ((void *)((p)->Base + (offs)))
+  #define Ppmd7_GetContext(p, offs) ((CPpmd7_Context *)Ppmd7_GetPtr((p), (offs)))
+  #define Ppmd7_GetStats(p, ctx) ((CPpmd_State *)Ppmd7_GetPtr((p), ((ctx)->Stats)))
+#endif
+
+void Ppmd7_Update1(CPpmd7 *p);
+void Ppmd7_Update1_0(CPpmd7 *p);
+void Ppmd7_Update2(CPpmd7 *p);
+void Ppmd7_UpdateBin(CPpmd7 *p);
+
+#define Ppmd7_GetBinSumm(p) \
+    &p->BinSumm[(size_t)(unsigned)Ppmd7Context_OneState(p->MinContext)->Freq - 1][p->PrevSuccess + \
+    p->NS2BSIndx[(size_t)Ppmd7_GetContext(p, p->MinContext->Suffix)->NumStats - 1] + \
+    (p->HiBitsFlag = p->HB2Flag[p->FoundState->Symbol]) + \
+    2 * p->HB2Flag[(unsigned)Ppmd7Context_OneState(p->MinContext)->Symbol] + \
+    ((p->RunLength >> 26) & 0x20)]
+
+CPpmd_See *Ppmd7_MakeEscFreq(CPpmd7 *p, unsigned numMasked, UInt32 *scale);
+
+
+/* ---------- Decode ---------- */
+
+typedef struct IPpmd7_RangeDec IPpmd7_RangeDec;
+
+struct IPpmd7_RangeDec
+{
+  UInt32 (*GetThreshold)(const IPpmd7_RangeDec *p, UInt32 total);
+  void (*Decode)(const IPpmd7_RangeDec *p, UInt32 start, UInt32 size);
+  UInt32 (*DecodeBit)(const IPpmd7_RangeDec *p, UInt32 size0);
+};
+
+typedef struct
+{
+  IPpmd7_RangeDec vt;
+  UInt32 Range;
+  UInt32 Code;
+  IByteIn *Stream;
+} CPpmd7z_RangeDec;
+
+void Ppmd7z_RangeDec_CreateVTable(CPpmd7z_RangeDec *p);
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p);
+#define Ppmd7z_RangeDec_IsFinishedOK(p) ((p)->Code == 0)
+
+int Ppmd7_DecodeSymbol(CPpmd7 *p, const IPpmd7_RangeDec *rc);
+
+
+/* ---------- Encode ---------- */
+
+typedef struct
+{
+  UInt64 Low;
+  UInt32 Range;
+  Byte Cache;
+  UInt64 CacheSize;
+  IByteOut *Stream;
+} CPpmd7z_RangeEnc;
+
+void Ppmd7z_RangeEnc_Init(CPpmd7z_RangeEnc *p);
+void Ppmd7z_RangeEnc_FlushData(CPpmd7z_RangeEnc *p);
+
+void Ppmd7_EncodeSymbol(CPpmd7 *p, CPpmd7z_RangeEnc *rc, int symbol);
+
+EXTERN_C_END
+ 
+#endif
@@ -0,0 +1,191 @@
+/* Ppmd7Dec.c -- PPMdH Decoder
+2018-07-04 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#include "Precomp.h"
+
+#include "Ppmd7.h"
+
+#define kTopValue (1 << 24)
+
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p)
+{
+  unsigned i;
+  p->Code = 0;
+  p->Range = 0xFFFFFFFF;
+  if (IByteIn_Read(p->Stream) != 0)
+    return False;
+  for (i = 0; i < 4; i++)
+    p->Code = (p->Code << 8) | IByteIn_Read(p->Stream);
+  return (p->Code < 0xFFFFFFFF);
+}
+
+#define GET_Ppmd7z_RangeDec CPpmd7z_RangeDec *p = CONTAINER_FROM_VTBL(pp, CPpmd7z_RangeDec, vt);
+ 
+static UInt32 Range_GetThreshold(const IPpmd7_RangeDec *pp, UInt32 total)
+{
+  GET_Ppmd7z_RangeDec
+  return p->Code / (p->Range /= total);
+}
+
+static void Range_Normalize(CPpmd7z_RangeDec *p)
+{
+  if (p->Range < kTopValue)
+  {
+    p->Code = (p->Code << 8) | IByteIn_Read(p->Stream);
+    p->Range <<= 8;
+    if (p->Range < kTopValue)
+    {
+      p->Code = (p->Code << 8) | IByteIn_Read(p->Stream);
+      p->Range <<= 8;
+    }
+  }
+}
+
+static void Range_Decode(const IPpmd7_RangeDec *pp, UInt32 start, UInt32 size)
+{
+  GET_Ppmd7z_RangeDec
+  p->Code -= start * p->Range;
+  p->Range *= size;
+  Range_Normalize(p);
+}
+
+static UInt32 Range_DecodeBit(const IPpmd7_RangeDec *pp, UInt32 size0)
+{
+  GET_Ppmd7z_RangeDec
+  UInt32 newBound = (p->Range >> 14) * size0;
+  UInt32 symbol;
+  if (p->Code < newBound)
+  {
+    symbol = 0;
+    p->Range = newBound;
+  }
+  else
+  {
+    symbol = 1;
+    p->Code -= newBound;
+    p->Range -= newBound;
+  }
+  Range_Normalize(p);
+  return symbol;
+}
+
+void Ppmd7z_RangeDec_CreateVTable(CPpmd7z_RangeDec *p)
+{
+  p->vt.GetThreshold = Range_GetThreshold;
+  p->vt.Decode = Range_Decode;
+  p->vt.DecodeBit = Range_DecodeBit;
+}
+
+
+#define MASK(sym) ((signed char *)charMask)[sym]
+
+int Ppmd7_DecodeSymbol(CPpmd7 *p, const IPpmd7_RangeDec *rc)
+{
+  size_t charMask[256 / sizeof(size_t)];
+  if (p->MinContext->NumStats != 1)
+  {
+    CPpmd_State *s = Ppmd7_GetStats(p, p->MinContext);
+    unsigned i;
+    UInt32 count, hiCnt;
+    if ((count = rc->GetThreshold(rc, p->MinContext->SummFreq)) < (hiCnt = s->Freq))
+    {
+      Byte symbol;
+      rc->Decode(rc, 0, s->Freq);
+      p->FoundState = s;
+      symbol = s->Symbol;
+      Ppmd7_Update1_0(p);
+      return symbol;
+    }
+    p->PrevSuccess = 0;
+    i = p->MinContext->NumStats - 1;
+    do
+    {
+      if ((hiCnt += (++s)->Freq) > count)
+      {
+        Byte symbol;
+        rc->Decode(rc, hiCnt - s->Freq, s->Freq);
+        p->FoundState = s;
+        symbol = s->Symbol;
+        Ppmd7_Update1(p);
+        return symbol;
+      }
+    }
+    while (--i);
+    if (count >= p->MinContext->SummFreq)
+      return -2;
+    p->HiBitsFlag = p->HB2Flag[p->FoundState->Symbol];
+    rc->Decode(rc, hiCnt, p->MinContext->SummFreq - hiCnt);
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    MASK(s->Symbol) = 0;
+    i = p->MinContext->NumStats - 1;
+    do { MASK((--s)->Symbol) = 0; } while (--i);
+  }
+  else
+  {
+    UInt16 *prob = Ppmd7_GetBinSumm(p);
+    if (rc->DecodeBit(rc, *prob) == 0)
+    {
+      Byte symbol;
+      *prob = (UInt16)PPMD_UPDATE_PROB_0(*prob);
+      symbol = (p->FoundState = Ppmd7Context_OneState(p->MinContext))->Symbol;
+      Ppmd7_UpdateBin(p);
+      return symbol;
+    }
+    *prob = (UInt16)PPMD_UPDATE_PROB_1(*prob);
+    p->InitEsc = PPMD7_kExpEscape[*prob >> 10];
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    MASK(Ppmd7Context_OneState(p->MinContext)->Symbol) = 0;
+    p->PrevSuccess = 0;
+  }
+  for (;;)
+  {
+    CPpmd_State *ps[256], *s;
+    UInt32 freqSum, count, hiCnt;
+    CPpmd_See *see;
+    unsigned i, num, numMasked = p->MinContext->NumStats;
+    do
+    {
+      p->OrderFall++;
+      if (!p->MinContext->Suffix)
+        return -1;
+      p->MinContext = Ppmd7_GetContext(p, p->MinContext->Suffix);
+    }
+    while (p->MinContext->NumStats == numMasked);
+    hiCnt = 0;
+    s = Ppmd7_GetStats(p, p->MinContext);
+    i = 0;
+    num = p->MinContext->NumStats - numMasked;
+    do
+    {
+      int k = (int)(MASK(s->Symbol));
+      hiCnt += (s->Freq & k);
+      ps[i] = s++;
+      i -= k;
+    }
+    while (i != num);
+    
+    see = Ppmd7_MakeEscFreq(p, numMasked, &freqSum);
+    freqSum += hiCnt;
+    count = rc->GetThreshold(rc, freqSum);
+    
+    if (count < hiCnt)
+    {
+      Byte symbol;
+      CPpmd_State **pps = ps;
+      for (hiCnt = 0; (hiCnt += (*pps)->Freq) <= count; pps++);
+      s = *pps;
+      rc->Decode(rc, hiCnt - s->Freq, s->Freq);
+      Ppmd_See_Update(see);
+      p->FoundState = s;
+      symbol = s->Symbol;
+      Ppmd7_Update2(p);
+      return symbol;
+    }
+    if (count >= freqSum)
+      return -2;
+    rc->Decode(rc, hiCnt, freqSum - hiCnt);
+    see->Summ = (UInt16)(see->Summ + freqSum);
+    do { MASK(ps[--i]->Symbol) = 0; } while (i != 0);
+  }
+}
@@ -0,0 +1,187 @@
+/* Ppmd7Enc.c -- PPMdH Encoder
+2017-04-03 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#include "Precomp.h"
+
+#include "Ppmd7.h"
+
+#define kTopValue (1 << 24)
+
+void Ppmd7z_RangeEnc_Init(CPpmd7z_RangeEnc *p)
+{
+  p->Low = 0;
+  p->Range = 0xFFFFFFFF;
+  p->Cache = 0;
+  p->CacheSize = 1;
+}
+
+static void RangeEnc_ShiftLow(CPpmd7z_RangeEnc *p)
+{
+  if ((UInt32)p->Low < (UInt32)0xFF000000 || (unsigned)(p->Low >> 32) != 0)
+  {
+    Byte temp = p->Cache;
+    do
+    {
+      IByteOut_Write(p->Stream, (Byte)(temp + (Byte)(p->Low >> 32)));
+      temp = 0xFF;
+    }
+    while (--p->CacheSize != 0);
+    p->Cache = (Byte)((UInt32)p->Low >> 24);
+  }
+  p->CacheSize++;
+  p->Low = (UInt32)p->Low << 8;
+}
+
+static void RangeEnc_Encode(CPpmd7z_RangeEnc *p, UInt32 start, UInt32 size, UInt32 total)
+{
+  p->Low += start * (p->Range /= total);
+  p->Range *= size;
+  while (p->Range < kTopValue)
+  {
+    p->Range <<= 8;
+    RangeEnc_ShiftLow(p);
+  }
+}
+
+static void RangeEnc_EncodeBit_0(CPpmd7z_RangeEnc *p, UInt32 size0)
+{
+  p->Range = (p->Range >> 14) * size0;
+  while (p->Range < kTopValue)
+  {
+    p->Range <<= 8;
+    RangeEnc_ShiftLow(p);
+  }
+}
+
+static void RangeEnc_EncodeBit_1(CPpmd7z_RangeEnc *p, UInt32 size0)
+{
+  UInt32 newBound = (p->Range >> 14) * size0;
+  p->Low += newBound;
+  p->Range -= newBound;
+  while (p->Range < kTopValue)
+  {
+    p->Range <<= 8;
+    RangeEnc_ShiftLow(p);
+  }
+}
+
+void Ppmd7z_RangeEnc_FlushData(CPpmd7z_RangeEnc *p)
+{
+  unsigned i;
+  for (i = 0; i < 5; i++)
+    RangeEnc_ShiftLow(p);
+}
+
+
+#define MASK(sym) ((signed char *)charMask)[sym]
+
+void Ppmd7_EncodeSymbol(CPpmd7 *p, CPpmd7z_RangeEnc *rc, int symbol)
+{
+  size_t charMask[256 / sizeof(size_t)];
+  if (p->MinContext->NumStats != 1)
+  {
+    CPpmd_State *s = Ppmd7_GetStats(p, p->MinContext);
+    UInt32 sum;
+    unsigned i;
+    if (s->Symbol == symbol)
+    {
+      RangeEnc_Encode(rc, 0, s->Freq, p->MinContext->SummFreq);
+      p->FoundState = s;
+      Ppmd7_Update1_0(p);
+      return;
+    }
+    p->PrevSuccess = 0;
+    sum = s->Freq;
+    i = p->MinContext->NumStats - 1;
+    do
+    {
+      if ((++s)->Symbol == symbol)
+      {
+        RangeEnc_Encode(rc, sum, s->Freq, p->MinContext->SummFreq);
+        p->FoundState = s;
+        Ppmd7_Update1(p);
+        return;
+      }
+      sum += s->Freq;
+    }
+    while (--i);
+    
+    p->HiBitsFlag = p->HB2Flag[p->FoundState->Symbol];
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    MASK(s->Symbol) = 0;
+    i = p->MinContext->NumStats - 1;
+    do { MASK((--s)->Symbol) = 0; } while (--i);
+    RangeEnc_Encode(rc, sum, p->MinContext->SummFreq - sum, p->MinContext->SummFreq);
+  }
+  else
+  {
+    UInt16 *prob = Ppmd7_GetBinSumm(p);
+    CPpmd_State *s = Ppmd7Context_OneState(p->MinContext);
+    if (s->Symbol == symbol)
+    {
+      RangeEnc_EncodeBit_0(rc, *prob);
+      *prob = (UInt16)PPMD_UPDATE_PROB_0(*prob);
+      p->FoundState = s;
+      Ppmd7_UpdateBin(p);
+      return;
+    }
+    else
+    {
+      RangeEnc_EncodeBit_1(rc, *prob);
+      *prob = (UInt16)PPMD_UPDATE_PROB_1(*prob);
+      p->InitEsc = PPMD7_kExpEscape[*prob >> 10];
+      PPMD_SetAllBitsIn256Bytes(charMask);
+      MASK(s->Symbol) = 0;
+      p->PrevSuccess = 0;
+    }
+  }
+  for (;;)
+  {
+    UInt32 escFreq;
+    CPpmd_See *see;
+    CPpmd_State *s;
+    UInt32 sum;
+    unsigned i, numMasked = p->MinContext->NumStats;
+    do
+    {
+      p->OrderFall++;
+      if (!p->MinContext->Suffix)
+        return; /* EndMarker (symbol = -1) */
+      p->MinContext = Ppmd7_GetContext(p, p->MinContext->Suffix);
+    }
+    while (p->MinContext->NumStats == numMasked);
+    
+    see = Ppmd7_MakeEscFreq(p, numMasked, &escFreq);
+    s = Ppmd7_GetStats(p, p->MinContext);
+    sum = 0;
+    i = p->MinContext->NumStats;
+    do
+    {
+      int cur = s->Symbol;
+      if (cur == symbol)
+      {
+        UInt32 low = sum;
+        CPpmd_State *s1 = s;
+        do
+        {
+          sum += (s->Freq & (int)(MASK(s->Symbol)));
+          s++;
+        }
+        while (--i);
+        RangeEnc_Encode(rc, low, s1->Freq, sum + escFreq);
+        Ppmd_See_Update(see);
+        p->FoundState = s1;
+        Ppmd7_Update2(p);
+        return;
+      }
+      sum += (s->Freq & (int)(MASK(cur)));
+      MASK(cur) = 0;
+      s++;
+    }
+    while (--i);
+    
+    RangeEnc_Encode(rc, sum, escFreq, sum + escFreq);
+    see->Summ = (UInt16)(see->Summ + sum + escFreq);
+  }
+}
@@ -0,0 +1,10 @@
+/* Precomp.h -- StdAfx
+2013-11-12 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_PRECOMP_H
+#define __7Z_PRECOMP_H
+
+#include "Compiler.h"
+/* #include "7zTypes.h" */
+
+#endif
@@ -0,0 +1,30 @@
+/* RotateDefs.h -- Rotate functions
+2015-03-25 : Igor Pavlov : Public domain */
+
+#ifndef __ROTATE_DEFS_H
+#define __ROTATE_DEFS_H
+
+#ifdef _MSC_VER
+
+#include <stdlib.h>
+
+/* don't use _rotl with MINGW. It can insert slow call to function. */
+ 
+/* #if (_MSC_VER >= 1200) */
+#pragma intrinsic(_rotl)
+#pragma intrinsic(_rotr)
+/* #endif */
+
+#define rotlFixed(x, n) _rotl((x), (n))
+#define rotrFixed(x, n) _rotr((x), (n))
+
+#else
+
+/* new compilers can translate these macros to fast commands. */
+
+#define rotlFixed(x, n) (((x) << (n)) | ((x) >> (32 - (n))))
+#define rotrFixed(x, n) (((x) >> (n)) | ((x) << (32 - (n))))
+
+#endif
+
+#endif
@@ -0,0 +1,248 @@
+/* Crypto/Sha256.c -- SHA-256 Hash
+2017-04-03 : Igor Pavlov : Public domain
+This code is based on public domain code from Wei Dai's Crypto++ library. */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "CpuArch.h"
+#include "RotateDefs.h"
+#include "Sha256.h"
+
+/* define it for speed optimization */
+#ifndef _SFX
+#define _SHA256_UNROLL
+#define _SHA256_UNROLL2
+#endif
+
+/* #define _SHA256_UNROLL2 */
+
+void Sha256_Init(CSha256 *p)
+{
+  p->state[0] = 0x6a09e667;
+  p->state[1] = 0xbb67ae85;
+  p->state[2] = 0x3c6ef372;
+  p->state[3] = 0xa54ff53a;
+  p->state[4] = 0x510e527f;
+  p->state[5] = 0x9b05688c;
+  p->state[6] = 0x1f83d9ab;
+  p->state[7] = 0x5be0cd19;
+  p->count = 0;
+}
+
+#define S0(x) (rotrFixed(x, 2) ^ rotrFixed(x,13) ^ rotrFixed(x, 22))
+#define S1(x) (rotrFixed(x, 6) ^ rotrFixed(x,11) ^ rotrFixed(x, 25))
+#define s0(x) (rotrFixed(x, 7) ^ rotrFixed(x,18) ^ (x >> 3))
+#define s1(x) (rotrFixed(x,17) ^ rotrFixed(x,19) ^ (x >> 10))
+
+#define blk0(i) (W[i])
+#define blk2(i) (W[i] += s1(W[((i)-2)&15]) + W[((i)-7)&15] + s0(W[((i)-15)&15]))
+
+#define Ch(x,y,z) (z^(x&(y^z)))
+#define Maj(x,y,z) ((x&y)|(z&(x|y)))
+
+#ifdef _SHA256_UNROLL2
+
+#define R(a,b,c,d,e,f,g,h, i) \
+    h += S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + (j ? blk2(i) : blk0(i)); \
+    d += h; \
+    h += S0(a) + Maj(a, b, c)
+
+#define RX_8(i) \
+  R(a,b,c,d,e,f,g,h, i); \
+  R(h,a,b,c,d,e,f,g, i+1); \
+  R(g,h,a,b,c,d,e,f, i+2); \
+  R(f,g,h,a,b,c,d,e, i+3); \
+  R(e,f,g,h,a,b,c,d, i+4); \
+  R(d,e,f,g,h,a,b,c, i+5); \
+  R(c,d,e,f,g,h,a,b, i+6); \
+  R(b,c,d,e,f,g,h,a, i+7)
+
+#define RX_16  RX_8(0); RX_8(8);
+
+#else
+
+#define a(i) T[(0-(i))&7]
+#define b(i) T[(1-(i))&7]
+#define c(i) T[(2-(i))&7]
+#define d(i) T[(3-(i))&7]
+#define e(i) T[(4-(i))&7]
+#define f(i) T[(5-(i))&7]
+#define g(i) T[(6-(i))&7]
+#define h(i) T[(7-(i))&7]
+
+#define R(i) \
+    h(i) += S1(e(i)) + Ch(e(i),f(i),g(i)) + K[(i)+(size_t)(j)] + (j ? blk2(i) : blk0(i)); \
+    d(i) += h(i); \
+    h(i) += S0(a(i)) + Maj(a(i), b(i), c(i)) \
+
+#ifdef _SHA256_UNROLL
+
+#define RX_8(i)  R(i+0); R(i+1); R(i+2); R(i+3); R(i+4); R(i+5); R(i+6); R(i+7);
+#define RX_16  RX_8(0); RX_8(8);
+
+#else
+
+#define RX_16  unsigned i; for (i = 0; i < 16; i++) { R(i); }
+
+#endif
+
+#endif
+
+static const UInt32 K[64] = {
+  0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
+  0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+  0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+  0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+  0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
+  0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+  0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
+  0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+  0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+  0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+  0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
+  0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+  0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
+  0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+  0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+  0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+};
+
+static void Sha256_WriteByteBlock(CSha256 *p)
+{
+  UInt32 W[16];
+  unsigned j;
+  UInt32 *state;
+
+  #ifdef _SHA256_UNROLL2
+  UInt32 a,b,c,d,e,f,g,h;
+  #else
+  UInt32 T[8];
+  #endif
+
+  for (j = 0; j < 16; j += 4)
+  {
+    const Byte *ccc = p->buffer + j * 4;
+    W[j    ] = GetBe32(ccc);
+    W[j + 1] = GetBe32(ccc + 4);
+    W[j + 2] = GetBe32(ccc + 8);
+    W[j + 3] = GetBe32(ccc + 12);
+  }
+
+  state = p->state;
+
+  #ifdef _SHA256_UNROLL2
+  a = state[0];
+  b = state[1];
+  c = state[2];
+  d = state[3];
+  e = state[4];
+  f = state[5];
+  g = state[6];
+  h = state[7];
+  #else
+  for (j = 0; j < 8; j++)
+    T[j] = state[j];
+  #endif
+
+  for (j = 0; j < 64; j += 16)
+  {
+    RX_16
+  }
+
+  #ifdef _SHA256_UNROLL2
+  state[0] += a;
+  state[1] += b;
+  state[2] += c;
+  state[3] += d;
+  state[4] += e;
+  state[5] += f;
+  state[6] += g;
+  state[7] += h;
+  #else
+  for (j = 0; j < 8; j++)
+    state[j] += T[j];
+  #endif
+  
+  /* Wipe variables */
+  /* memset(W, 0, sizeof(W)); */
+  /* memset(T, 0, sizeof(T)); */
+}
+
+#undef S0
+#undef S1
+#undef s0
+#undef s1
+
+void Sha256_Update(CSha256 *p, const Byte *data, size_t size)
+{
+  if (size == 0)
+    return;
+
+  {
+    unsigned pos = (unsigned)p->count & 0x3F;
+    unsigned num;
+    
+    p->count += size;
+    
+    num = 64 - pos;
+    if (num > size)
+    {
+      memcpy(p->buffer + pos, data, size);
+      return;
+    }
+    
+    size -= num;
+    memcpy(p->buffer + pos, data, num);
+    data += num;
+  }
+
+  for (;;)
+  {
+    Sha256_WriteByteBlock(p);
+    if (size < 64)
+      break;
+    size -= 64;
+    memcpy(p->buffer, data, 64);
+    data += 64;
+  }
+
+  if (size != 0)
+    memcpy(p->buffer, data, size);
+}
+
+void Sha256_Final(CSha256 *p, Byte *digest)
+{
+  unsigned pos = (unsigned)p->count & 0x3F;
+  unsigned i;
+  
+  p->buffer[pos++] = 0x80;
+  
+  while (pos != (64 - 8))
+  {
+    pos &= 0x3F;
+    if (pos == 0)
+      Sha256_WriteByteBlock(p);
+    p->buffer[pos++] = 0;
+  }
+
+  {
+    UInt64 numBits = (p->count << 3);
+    SetBe32(p->buffer + 64 - 8, (UInt32)(numBits >> 32));
+    SetBe32(p->buffer + 64 - 4, (UInt32)(numBits));
+  }
+  
+  Sha256_WriteByteBlock(p);
+
+  for (i = 0; i < 8; i += 2)
+  {
+    UInt32 v0 = p->state[i];
+    UInt32 v1 = p->state[i + 1];
+    SetBe32(digest    , v0);
+    SetBe32(digest + 4, v1);
+    digest += 8;
+  }
+  
+  Sha256_Init(p);
+}
@@ -0,0 +1,26 @@
+/* Sha256.h -- SHA-256 Hash
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __CRYPTO_SHA256_H
+#define __CRYPTO_SHA256_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define SHA256_DIGEST_SIZE 32
+
+typedef struct
+{
+  UInt32 state[8];
+  UInt64 count;
+  Byte buffer[64];
+} CSha256;
+
+void Sha256_Init(CSha256 *p);
+void Sha256_Update(CSha256 *p, const Byte *data, size_t size);
+void Sha256_Final(CSha256 *p, Byte *digest);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,141 @@
+/* Sort.c -- Sort functions
+2014-04-05 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Sort.h"
+
+#define HeapSortDown(p, k, size, temp) \
+  { for (;;) { \
+    size_t s = (k << 1); \
+    if (s > size) break; \
+    if (s < size && p[s + 1] > p[s]) s++; \
+    if (temp >= p[s]) break; \
+    p[k] = p[s]; k = s; \
+  } p[k] = temp; }
+
+void HeapSort(UInt32 *p, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt32 temp = p[i];
+      size_t k = i;
+      HeapSortDown(p, k, size, temp)
+    }
+    while (--i != 0);
+  }
+  /*
+  do
+  {
+    size_t k = 1;
+    UInt32 temp = p[size];
+    p[size--] = p[1];
+    HeapSortDown(p, k, size, temp)
+  }
+  while (size > 1);
+  */
+  while (size > 3)
+  {
+    UInt32 temp = p[size];
+    size_t k = (p[3] > p[2]) ? 3 : 2;
+    p[size--] = p[1];
+    p[1] = p[k];
+    HeapSortDown(p, k, size, temp)
+  }
+  {
+    UInt32 temp = p[size];
+    p[size] = p[1];
+    if (size > 2 && p[2] < temp)
+    {
+      p[1] = p[2];
+      p[2] = temp;
+    }
+    else
+      p[1] = temp;
+  }
+}
+
+void HeapSort64(UInt64 *p, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt64 temp = p[i];
+      size_t k = i;
+      HeapSortDown(p, k, size, temp)
+    }
+    while (--i != 0);
+  }
+  /*
+  do
+  {
+    size_t k = 1;
+    UInt64 temp = p[size];
+    p[size--] = p[1];
+    HeapSortDown(p, k, size, temp)
+  }
+  while (size > 1);
+  */
+  while (size > 3)
+  {
+    UInt64 temp = p[size];
+    size_t k = (p[3] > p[2]) ? 3 : 2;
+    p[size--] = p[1];
+    p[1] = p[k];
+    HeapSortDown(p, k, size, temp)
+  }
+  {
+    UInt64 temp = p[size];
+    p[size] = p[1];
+    if (size > 2 && p[2] < temp)
+    {
+      p[1] = p[2];
+      p[2] = temp;
+    }
+    else
+      p[1] = temp;
+  }
+}
+
+/*
+#define HeapSortRefDown(p, vals, n, size, temp) \
+  { size_t k = n; UInt32 val = vals[temp]; for (;;) { \
+    size_t s = (k << 1); \
+    if (s > size) break; \
+    if (s < size && vals[p[s + 1]] > vals[p[s]]) s++; \
+    if (val >= vals[p[s]]) break; \
+    p[k] = p[s]; k = s; \
+  } p[k] = temp; }
+
+void HeapSortRef(UInt32 *p, UInt32 *vals, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt32 temp = p[i];
+      HeapSortRefDown(p, vals, i, size, temp);
+    }
+    while (--i != 0);
+  }
+  do
+  {
+    UInt32 temp = p[size];
+    p[size--] = p[1];
+    HeapSortRefDown(p, vals, 1, size, temp);
+  }
+  while (size > 1);
+}
+*/
@@ -0,0 +1,18 @@
+/* Sort.h -- Sort functions
+2014-04-05 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_SORT_H
+#define __7Z_SORT_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+void HeapSort(UInt32 *p, size_t size);
+void HeapSort64(UInt64 *p, size_t size);
+
+/* void HeapSortRef(UInt32 *p, UInt32 *vals, size_t size); */
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,95 @@
+/* Threads.c -- multithreading library
+2017-06-26 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#ifndef UNDER_CE
+#include <process.h>
+#endif
+
+#include "Threads.h"
+
+static WRes GetError()
+{
+  DWORD res = GetLastError();
+  return res ? (WRes)res : 1;
+}
+
+static WRes HandleToWRes(HANDLE h) { return (h != NULL) ? 0 : GetError(); }
+static WRes BOOLToWRes(BOOL v) { return v ? 0 : GetError(); }
+
+WRes HandlePtr_Close(HANDLE *p)
+{
+  if (*p != NULL)
+  {
+    if (!CloseHandle(*p))
+      return GetError();
+    *p = NULL;
+  }
+  return 0;
+}
+
+WRes Handle_WaitObject(HANDLE h) { return (WRes)WaitForSingleObject(h, INFINITE); }
+
+WRes Thread_Create(CThread *p, THREAD_FUNC_TYPE func, LPVOID param)
+{
+  /* Windows Me/98/95: threadId parameter may not be NULL in _beginthreadex/CreateThread functions */
+  
+  #ifdef UNDER_CE
+  
+  DWORD threadId;
+  *p = CreateThread(0, 0, func, param, 0, &threadId);
+
+  #else
+
+  unsigned threadId;
+  *p = (HANDLE)_beginthreadex(NULL, 0, func, param, 0, &threadId);
+   
+  #endif
+
+  /* maybe we must use errno here, but probably GetLastError() is also OK. */
+  return HandleToWRes(*p);
+}
+
+static WRes Event_Create(CEvent *p, BOOL manualReset, int signaled)
+{
+  *p = CreateEvent(NULL, manualReset, (signaled ? TRUE : FALSE), NULL);
+  return HandleToWRes(*p);
+}
+
+WRes Event_Set(CEvent *p) { return BOOLToWRes(SetEvent(*p)); }
+WRes Event_Reset(CEvent *p) { return BOOLToWRes(ResetEvent(*p)); }
+
+WRes ManualResetEvent_Create(CManualResetEvent *p, int signaled) { return Event_Create(p, TRUE, signaled); }
+WRes AutoResetEvent_Create(CAutoResetEvent *p, int signaled) { return Event_Create(p, FALSE, signaled); }
+WRes ManualResetEvent_CreateNotSignaled(CManualResetEvent *p) { return ManualResetEvent_Create(p, 0); }
+WRes AutoResetEvent_CreateNotSignaled(CAutoResetEvent *p) { return AutoResetEvent_Create(p, 0); }
+
+
+WRes Semaphore_Create(CSemaphore *p, UInt32 initCount, UInt32 maxCount)
+{
+  *p = CreateSemaphore(NULL, (LONG)initCount, (LONG)maxCount, NULL);
+  return HandleToWRes(*p);
+}
+
+static WRes Semaphore_Release(CSemaphore *p, LONG releaseCount, LONG *previousCount)
+  { return BOOLToWRes(ReleaseSemaphore(*p, releaseCount, previousCount)); }
+WRes Semaphore_ReleaseN(CSemaphore *p, UInt32 num)
+  { return Semaphore_Release(p, (LONG)num, NULL); }
+WRes Semaphore_Release1(CSemaphore *p) { return Semaphore_ReleaseN(p, 1); }
+
+WRes CriticalSection_Init(CCriticalSection *p)
+{
+  /* InitializeCriticalSection can raise only STATUS_NO_MEMORY exception */
+  #ifdef _MSC_VER
+  __try
+  #endif
+  {
+    InitializeCriticalSection(p);
+    /* InitializeCriticalSectionAndSpinCount(p, 0); */
+  }
+  #ifdef _MSC_VER
+  __except (EXCEPTION_EXECUTE_HANDLER) { return 1; }
+  #endif
+  return 0;
+}
@@ -0,0 +1,68 @@
+/* Threads.h -- multithreading library
+2017-06-18 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_THREADS_H
+#define __7Z_THREADS_H
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+WRes HandlePtr_Close(HANDLE *h);
+WRes Handle_WaitObject(HANDLE h);
+
+typedef HANDLE CThread;
+#define Thread_Construct(p) *(p) = NULL
+#define Thread_WasCreated(p) (*(p) != NULL)
+#define Thread_Close(p) HandlePtr_Close(p)
+#define Thread_Wait(p) Handle_WaitObject(*(p))
+
+typedef
+#ifdef UNDER_CE
+  DWORD
+#else
+  unsigned
+#endif
+  THREAD_FUNC_RET_TYPE;
+
+#define THREAD_FUNC_CALL_TYPE MY_STD_CALL
+#define THREAD_FUNC_DECL THREAD_FUNC_RET_TYPE THREAD_FUNC_CALL_TYPE
+typedef THREAD_FUNC_RET_TYPE (THREAD_FUNC_CALL_TYPE * THREAD_FUNC_TYPE)(void *);
+WRes Thread_Create(CThread *p, THREAD_FUNC_TYPE func, LPVOID param);
+
+typedef HANDLE CEvent;
+typedef CEvent CAutoResetEvent;
+typedef CEvent CManualResetEvent;
+#define Event_Construct(p) *(p) = NULL
+#define Event_IsCreated(p) (*(p) != NULL)
+#define Event_Close(p) HandlePtr_Close(p)
+#define Event_Wait(p) Handle_WaitObject(*(p))
+WRes Event_Set(CEvent *p);
+WRes Event_Reset(CEvent *p);
+WRes ManualResetEvent_Create(CManualResetEvent *p, int signaled);
+WRes ManualResetEvent_CreateNotSignaled(CManualResetEvent *p);
+WRes AutoResetEvent_Create(CAutoResetEvent *p, int signaled);
+WRes AutoResetEvent_CreateNotSignaled(CAutoResetEvent *p);
+
+typedef HANDLE CSemaphore;
+#define Semaphore_Construct(p) *(p) = NULL
+#define Semaphore_IsCreated(p) (*(p) != NULL)
+#define Semaphore_Close(p) HandlePtr_Close(p)
+#define Semaphore_Wait(p) Handle_WaitObject(*(p))
+WRes Semaphore_Create(CSemaphore *p, UInt32 initCount, UInt32 maxCount);
+WRes Semaphore_ReleaseN(CSemaphore *p, UInt32 num);
+WRes Semaphore_Release1(CSemaphore *p);
+
+typedef CRITICAL_SECTION CCriticalSection;
+WRes CriticalSection_Init(CCriticalSection *p);
+#define CriticalSection_Delete(p) DeleteCriticalSection(p)
+#define CriticalSection_Enter(p) EnterCriticalSection(p)
+#define CriticalSection_Leave(p) LeaveCriticalSection(p)
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,90 @@
+/* Xz.c - Xz
+2017-05-12 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+#include "Xz.h"
+#include "XzCrc64.h"
+
+const Byte XZ_SIG[XZ_SIG_SIZE] = { 0xFD, '7', 'z', 'X', 'Z', 0 };
+/* const Byte XZ_FOOTER_SIG[XZ_FOOTER_SIG_SIZE] = { 'Y', 'Z' }; */
+
+unsigned Xz_WriteVarInt(Byte *buf, UInt64 v)
+{
+  unsigned i = 0;
+  do
+  {
+    buf[i++] = (Byte)((v & 0x7F) | 0x80);
+    v >>= 7;
+  }
+  while (v != 0);
+  buf[(size_t)i - 1] &= 0x7F;
+  return i;
+}
+
+void Xz_Construct(CXzStream *p)
+{
+  p->numBlocks = 0;
+  p->blocks = NULL;
+  p->flags = 0;
+}
+
+void Xz_Free(CXzStream *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->blocks);
+  p->numBlocks = 0;
+  p->blocks = NULL;
+}
+
+unsigned XzFlags_GetCheckSize(CXzStreamFlags f)
+{
+  unsigned t = XzFlags_GetCheckType(f);
+  return (t == 0) ? 0 : (4 << ((t - 1) / 3));
+}
+
+void XzCheck_Init(CXzCheck *p, unsigned mode)
+{
+  p->mode = mode;
+  switch (mode)
+  {
+    case XZ_CHECK_CRC32: p->crc = CRC_INIT_VAL; break;
+    case XZ_CHECK_CRC64: p->crc64 = CRC64_INIT_VAL; break;
+    case XZ_CHECK_SHA256: Sha256_Init(&p->sha); break;
+  }
+}
+
+void XzCheck_Update(CXzCheck *p, const void *data, size_t size)
+{
+  switch (p->mode)
+  {
+    case XZ_CHECK_CRC32: p->crc = CrcUpdate(p->crc, data, size); break;
+    case XZ_CHECK_CRC64: p->crc64 = Crc64Update(p->crc64, data, size); break;
+    case XZ_CHECK_SHA256: Sha256_Update(&p->sha, (const Byte *)data, size); break;
+  }
+}
+
+int XzCheck_Final(CXzCheck *p, Byte *digest)
+{
+  switch (p->mode)
+  {
+    case XZ_CHECK_CRC32:
+      SetUi32(digest, CRC_GET_DIGEST(p->crc));
+      break;
+    case XZ_CHECK_CRC64:
+    {
+      int i;
+      UInt64 v = CRC64_GET_DIGEST(p->crc64);
+      for (i = 0; i < 8; i++, v >>= 8)
+        digest[i] = (Byte)(v & 0xFF);
+      break;
+    }
+    case XZ_CHECK_SHA256:
+      Sha256_Final(&p->sha, digest);
+      break;
+    default:
+      return 0;
+  }
+  return 1;
+}
@@ -0,0 +1,460 @@
+/* Xz.h - Xz interface
+2018-07-04 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_H
+#define __XZ_H
+
+#include "Sha256.h"
+
+EXTERN_C_BEGIN
+
+#define XZ_ID_Subblock 1
+#define XZ_ID_Delta 3
+#define XZ_ID_X86 4
+#define XZ_ID_PPC 5
+#define XZ_ID_IA64 6
+#define XZ_ID_ARM 7
+#define XZ_ID_ARMT 8
+#define XZ_ID_SPARC 9
+#define XZ_ID_LZMA2 0x21
+
+unsigned Xz_ReadVarInt(const Byte *p, size_t maxSize, UInt64 *value);
+unsigned Xz_WriteVarInt(Byte *buf, UInt64 v);
+
+/* ---------- xz block ---------- */
+
+#define XZ_BLOCK_HEADER_SIZE_MAX 1024
+
+#define XZ_NUM_FILTERS_MAX 4
+#define XZ_BF_NUM_FILTERS_MASK 3
+#define XZ_BF_PACK_SIZE (1 << 6)
+#define XZ_BF_UNPACK_SIZE (1 << 7)
+
+#define XZ_FILTER_PROPS_SIZE_MAX 20
+
+typedef struct
+{
+  UInt64 id;
+  UInt32 propsSize;
+  Byte props[XZ_FILTER_PROPS_SIZE_MAX];
+} CXzFilter;
+
+typedef struct
+{
+  UInt64 packSize;
+  UInt64 unpackSize;
+  Byte flags;
+  CXzFilter filters[XZ_NUM_FILTERS_MAX];
+} CXzBlock;
+
+#define XzBlock_GetNumFilters(p) (((p)->flags & XZ_BF_NUM_FILTERS_MASK) + 1)
+#define XzBlock_HasPackSize(p)   (((p)->flags & XZ_BF_PACK_SIZE) != 0)
+#define XzBlock_HasUnpackSize(p) (((p)->flags & XZ_BF_UNPACK_SIZE) != 0)
+#define XzBlock_HasUnsupportedFlags(p) (((p)->flags & ~(XZ_BF_NUM_FILTERS_MASK | XZ_BF_PACK_SIZE | XZ_BF_UNPACK_SIZE)) != 0)
+
+SRes XzBlock_Parse(CXzBlock *p, const Byte *header);
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes);
+
+/* ---------- xz stream ---------- */
+
+#define XZ_SIG_SIZE 6
+#define XZ_FOOTER_SIG_SIZE 2
+
+extern const Byte XZ_SIG[XZ_SIG_SIZE];
+
+/*
+extern const Byte XZ_FOOTER_SIG[XZ_FOOTER_SIG_SIZE];
+*/
+
+#define XZ_FOOTER_SIG_0 'Y'
+#define XZ_FOOTER_SIG_1 'Z'
+
+#define XZ_STREAM_FLAGS_SIZE 2
+#define XZ_STREAM_CRC_SIZE 4
+
+#define XZ_STREAM_HEADER_SIZE (XZ_SIG_SIZE + XZ_STREAM_FLAGS_SIZE + XZ_STREAM_CRC_SIZE)
+#define XZ_STREAM_FOOTER_SIZE (XZ_FOOTER_SIG_SIZE + XZ_STREAM_FLAGS_SIZE + XZ_STREAM_CRC_SIZE + 4)
+
+#define XZ_CHECK_MASK 0xF
+#define XZ_CHECK_NO 0
+#define XZ_CHECK_CRC32 1
+#define XZ_CHECK_CRC64 4
+#define XZ_CHECK_SHA256 10
+
+typedef struct
+{
+  unsigned mode;
+  UInt32 crc;
+  UInt64 crc64;
+  CSha256 sha;
+} CXzCheck;
+
+void XzCheck_Init(CXzCheck *p, unsigned mode);
+void XzCheck_Update(CXzCheck *p, const void *data, size_t size);
+int XzCheck_Final(CXzCheck *p, Byte *digest);
+
+typedef UInt16 CXzStreamFlags;
+
+#define XzFlags_IsSupported(f) ((f) <= XZ_CHECK_MASK)
+#define XzFlags_GetCheckType(f) ((f) & XZ_CHECK_MASK)
+#define XzFlags_HasDataCrc32(f) (Xz_GetCheckType(f) == XZ_CHECK_CRC32)
+unsigned XzFlags_GetCheckSize(CXzStreamFlags f);
+
+SRes Xz_ParseHeader(CXzStreamFlags *p, const Byte *buf);
+SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStream *inStream);
+
+typedef struct
+{
+  UInt64 unpackSize;
+  UInt64 totalSize;
+} CXzBlockSizes;
+
+typedef struct
+{
+  CXzStreamFlags flags;
+  size_t numBlocks;
+  CXzBlockSizes *blocks;
+  UInt64 startOffset;
+} CXzStream;
+
+void Xz_Construct(CXzStream *p);
+void Xz_Free(CXzStream *p, ISzAllocPtr alloc);
+
+#define XZ_SIZE_OVERFLOW ((UInt64)(Int64)-1)
+
+UInt64 Xz_GetUnpackSize(const CXzStream *p);
+UInt64 Xz_GetPackSize(const CXzStream *p);
+
+typedef struct
+{
+  size_t num;
+  size_t numAllocated;
+  CXzStream *streams;
+} CXzs;
+
+void Xzs_Construct(CXzs *p);
+void Xzs_Free(CXzs *p, ISzAllocPtr alloc);
+SRes Xzs_ReadBackward(CXzs *p, ILookInStream *inStream, Int64 *startOffset, ICompressProgress *progress, ISzAllocPtr alloc);
+
+UInt64 Xzs_GetNumBlocks(const CXzs *p);
+UInt64 Xzs_GetUnpackSize(const CXzs *p);
+
+
+// ECoderStatus values are identical to ELzmaStatus values of LZMA2 decoder
+
+typedef enum
+{
+  CODER_STATUS_NOT_SPECIFIED,               /* use main error code instead */
+  CODER_STATUS_FINISHED_WITH_MARK,          /* stream was finished with end mark. */
+  CODER_STATUS_NOT_FINISHED,                /* stream was not finished */
+  CODER_STATUS_NEEDS_MORE_INPUT             /* you must provide more input bytes */
+} ECoderStatus;
+
+
+// ECoderFinishMode values are identical to ELzmaFinishMode
+
+typedef enum
+{
+  CODER_FINISH_ANY,   /* finish at any point */
+  CODER_FINISH_END    /* block must be finished at the end */
+} ECoderFinishMode;
+
+
+typedef struct _IStateCoder
+{
+  void *p;
+  void (*Free)(void *p, ISzAllocPtr alloc);
+  SRes (*SetProps)(void *p, const Byte *props, size_t propSize, ISzAllocPtr alloc);
+  void (*Init)(void *p);
+  SRes (*Code2)(void *p, Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+      int srcWasFinished, ECoderFinishMode finishMode,
+      // int *wasFinished,
+      ECoderStatus *status);
+  SizeT (*Filter)(void *p, Byte *data, SizeT size);
+} IStateCoder;
+
+
+
+#define MIXCODER_NUM_FILTERS_MAX 4
+
+typedef struct
+{
+  ISzAllocPtr alloc;
+  Byte *buf;
+  unsigned numCoders;
+
+  Byte *outBuf;
+  size_t outBufSize;
+  size_t outWritten; // is equal to lzmaDecoder.dicPos (in outBuf mode)
+  BoolInt wasFinished;
+  SRes res;
+  ECoderStatus status;
+  // BoolInt SingleBufMode;
+  
+  int finished[MIXCODER_NUM_FILTERS_MAX - 1];
+  size_t pos[MIXCODER_NUM_FILTERS_MAX - 1];
+  size_t size[MIXCODER_NUM_FILTERS_MAX - 1];
+  UInt64 ids[MIXCODER_NUM_FILTERS_MAX];
+  SRes results[MIXCODER_NUM_FILTERS_MAX];
+  IStateCoder coders[MIXCODER_NUM_FILTERS_MAX];
+} CMixCoder;
+
+
+typedef enum
+{
+  XZ_STATE_STREAM_HEADER,
+  XZ_STATE_STREAM_INDEX,
+  XZ_STATE_STREAM_INDEX_CRC,
+  XZ_STATE_STREAM_FOOTER,
+  XZ_STATE_STREAM_PADDING,
+  XZ_STATE_BLOCK_HEADER,
+  XZ_STATE_BLOCK,
+  XZ_STATE_BLOCK_FOOTER
+} EXzState;
+
+
+typedef struct
+{
+  EXzState state;
+  UInt32 pos;
+  unsigned alignPos;
+  unsigned indexPreSize;
+
+  CXzStreamFlags streamFlags;
+  
+  UInt32 blockHeaderSize;
+  UInt64 packSize;
+  UInt64 unpackSize;
+
+  UInt64 numBlocks; // number of finished blocks in current stream
+  UInt64 indexSize;
+  UInt64 indexPos;
+  UInt64 padSize;
+
+  UInt64 numStartedStreams;
+  UInt64 numFinishedStreams;
+  UInt64 numTotalBlocks;
+
+  UInt32 crc;
+  CMixCoder decoder;
+  CXzBlock block;
+  CXzCheck check;
+  CSha256 sha;
+
+  BoolInt parseMode;
+  BoolInt headerParsedOk;
+  BoolInt decodeToStreamSignature;
+  unsigned decodeOnlyOneBlock;
+
+  Byte *outBuf;
+  size_t outBufSize;
+  size_t outDataWritten; // the size of data in (outBuf) that were fully unpacked
+
+  Byte shaDigest[SHA256_DIGEST_SIZE];
+  Byte buf[XZ_BLOCK_HEADER_SIZE_MAX];
+} CXzUnpacker;
+
+/* alloc : aligned for cache line allocation is better */
+void XzUnpacker_Construct(CXzUnpacker *p, ISzAllocPtr alloc);
+void XzUnpacker_Init(CXzUnpacker *p);
+void XzUnpacker_SetOutBuf(CXzUnpacker *p, Byte *outBuf, size_t outBufSize);
+void XzUnpacker_Free(CXzUnpacker *p);
+
+/*
+  XzUnpacker
+  The sequence for decoding functions:
+  {
+    XzUnpacker_Construct()
+    [Decoding_Calls]
+    XzUnpacker_Free()
+  }
+
+  [Decoding_Calls]
+
+  There are 3 types of interfaces for [Decoding_Calls] calls:
+
+  Interface-1 : Partial output buffers:
+    {
+      XzUnpacker_Init()
+      for()
+        XzUnpacker_Code();
+    }
+    
+  Interface-2 : Direct output buffer:
+    Use it, if you know exact size of decoded data, and you need
+    whole xz unpacked data in one output buffer.
+    xz unpacker doesn't allocate additional buffer for lzma2 dictionary in that mode.
+    {
+      XzUnpacker_Init()
+      XzUnpacker_SetOutBufMode(); // to set output buffer and size
+      for()
+        XzUnpacker_Code(); // (dest = NULL) in XzUnpacker_Code()
+    }
+
+  Interface-3 : Direct output buffer : One call full decoding
+    It unpacks whole input buffer to output buffer in one call.
+    It uses Interface-2 internally.
+    {
+      XzUnpacker_CodeFull()
+    }
+*/
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  CODER_FINISH_ANY - use smallest number of input bytes
+  CODER_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      CODER_STATUS_NOT_FINISHED,
+      CODER_STATUS_NEEDS_MORE_INPUT - maybe there are more xz streams,
+                                      call XzUnpacker_IsStreamWasFinished to check that current stream was finished
+  SZ_ERROR_MEM  - Memory allocation error
+  SZ_ERROR_DATA - Data error
+  SZ_ERROR_UNSUPPORTED - Unsupported method or method properties
+  SZ_ERROR_CRC  - CRC error
+  // SZ_ERROR_INPUT_EOF - It needs more bytes in input buffer (src).
+
+  SZ_ERROR_NO_ARCHIVE - the error with xz Stream Header with one of the following reasons:
+     - xz Stream Signature failure
+     - CRC32 of xz Stream Header is failed
+     - The size of Stream padding is not multiple of four bytes.
+    It's possible to get that error, if xz stream was finished and the stream
+    contains some another data. In that case you can call XzUnpacker_GetExtraSize()
+    function to get real size of xz stream.
+*/
+
+
+SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen, int srcFinished,
+    ECoderFinishMode finishMode, ECoderStatus *status);
+
+SRes XzUnpacker_CodeFull(CXzUnpacker *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen,
+    ECoderFinishMode finishMode, ECoderStatus *status);
+
+BoolInt XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p);
+
+/*
+XzUnpacker_GetExtraSize() returns then number of uncofirmed bytes,
+ if it's in (XZ_STATE_STREAM_HEADER) state or in (XZ_STATE_STREAM_PADDING) state.
+These bytes can be some bytes after xz archive, or
+it can be start of new xz stream.
+ 
+Call XzUnpacker_GetExtraSize() after XzUnpacker_Code() function to detect real size of
+xz stream in two cases, if XzUnpacker_Code() returns:
+  res == SZ_OK && status == CODER_STATUS_NEEDS_MORE_INPUT
+  res == SZ_ERROR_NO_ARCHIVE
+*/
+
+UInt64 XzUnpacker_GetExtraSize(const CXzUnpacker *p);
+
+
+/*
+  for random block decoding:
+    XzUnpacker_Init();
+    set CXzUnpacker::streamFlags
+    XzUnpacker_PrepareToRandomBlockDecoding()
+    loop
+    {
+      XzUnpacker_Code()
+      XzUnpacker_IsBlockFinished()
+    }
+*/
+
+void XzUnpacker_PrepareToRandomBlockDecoding(CXzUnpacker *p);
+BoolInt XzUnpacker_IsBlockFinished(const CXzUnpacker *p);
+
+#define XzUnpacker_GetPackSizeForIndex(p) ((p)->packSize + (p)->blockHeaderSize + XzFlags_GetCheckSize((p)->streamFlags))
+
+
+
+/* ---------- Multi Threading Decoding ---------- */
+
+
+typedef struct
+{
+  size_t inBufSize_ST;
+  size_t outStep_ST;
+  BoolInt ignoreErrors;
+  
+  #ifndef _7ZIP_ST
+  unsigned numThreads;
+  size_t inBufSize_MT;
+  size_t memUseMax;
+  #endif
+} CXzDecMtProps;
+
+void XzDecMtProps_Init(CXzDecMtProps *p);
+
+
+typedef void * CXzDecMtHandle;
+
+/*
+  alloc    : XzDecMt uses CAlignOffsetAlloc for addresses allocated by (alloc).
+  allocMid : for big allocations, aligned allocation is better
+*/
+
+CXzDecMtHandle XzDecMt_Create(ISzAllocPtr alloc, ISzAllocPtr allocMid);
+void XzDecMt_Destroy(CXzDecMtHandle p);
+
+
+typedef struct
+{
+  Byte UnpackSize_Defined;
+  Byte NumStreams_Defined;
+  Byte NumBlocks_Defined;
+
+  Byte DataAfterEnd;
+  Byte DecodingTruncated; // Decoding was Truncated, we need only partial output data
+
+  UInt64 InSize;  // pack size processed
+  UInt64 OutSize;
+
+  UInt64 NumStreams;
+  UInt64 NumBlocks;
+
+  SRes DecodeRes;
+  SRes ReadRes;
+  SRes ProgressRes;
+  SRes CombinedRes;
+  SRes CombinedRes_Type;
+
+} CXzStatInfo;
+
+void XzStatInfo_Clear(CXzStatInfo *p);
+
+/*
+XzDecMt_Decode()
+SRes:
+  SZ_OK               - OK
+  SZ_ERROR_MEM        - Memory allocation error
+  SZ_ERROR_NO_ARCHIVE - is not xz archive
+  SZ_ERROR_ARCHIVE    - Headers error
+  SZ_ERROR_DATA       - Data Error
+  SZ_ERROR_CRC        - CRC Error
+  SZ_ERROR_INPUT_EOF  - it needs more input data
+  SZ_ERROR_WRITE      - ISeqOutStream error
+  (SZ_ERROR_READ)     - ISeqInStream errors
+  (SZ_ERROR_PROGRESS) - ICompressProgress errors
+  // SZ_ERROR_THREAD     - error in multi-threading functions
+  MY_SRes_HRESULT_FROM_WRes(WRes_error) - error in multi-threading function
+*/
+
+SRes XzDecMt_Decode(CXzDecMtHandle p,
+    const CXzDecMtProps *props,
+    const UInt64 *outDataSize, // NULL means undefined
+    int finishMode,            // 0 - partial unpacking is allowed, 1 - xz stream(s) must be finished
+    ISeqOutStream *outStream,
+    // Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    // const Byte *inData, size_t inDataSize,
+    CXzStatInfo *stat,
+    int *isMT,                 // 0 means that ST (Single-Thread) version was used
+    ICompressProgress *progress);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,86 @@
+/* XzCrc64.c -- CRC64 calculation
+2017-05-23 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "XzCrc64.h"
+#include "CpuArch.h"
+
+#define kCrc64Poly UINT64_CONST(0xC96C5795D7870F42)
+
+#ifdef MY_CPU_LE
+  #define CRC64_NUM_TABLES 4
+#else
+  #define CRC64_NUM_TABLES 5
+  #define CRC_UINT64_SWAP(v) \
+      ((v >> 56) \
+    | ((v >> 40) & ((UInt64)0xFF <<  8)) \
+    | ((v >> 24) & ((UInt64)0xFF << 16)) \
+    | ((v >>  8) & ((UInt64)0xFF << 24)) \
+    | ((v <<  8) & ((UInt64)0xFF << 32)) \
+    | ((v << 24) & ((UInt64)0xFF << 40)) \
+    | ((v << 40) & ((UInt64)0xFF << 48)) \
+    | ((v << 56)))
+
+  UInt64 MY_FAST_CALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+
+#ifndef MY_CPU_BE
+  UInt64 MY_FAST_CALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+
+typedef UInt64 (MY_FAST_CALL *CRC64_FUNC)(UInt64 v, const void *data, size_t size, const UInt64 *table);
+
+static CRC64_FUNC g_Crc64Update;
+UInt64 g_Crc64Table[256 * CRC64_NUM_TABLES];
+
+UInt64 MY_FAST_CALL Crc64Update(UInt64 v, const void *data, size_t size)
+{
+  return g_Crc64Update(v, data, size, g_Crc64Table);
+}
+
+UInt64 MY_FAST_CALL Crc64Calc(const void *data, size_t size)
+{
+  return g_Crc64Update(CRC64_INIT_VAL, data, size, g_Crc64Table) ^ CRC64_INIT_VAL;
+}
+
+void MY_FAST_CALL Crc64GenerateTable()
+{
+  UInt32 i;
+  for (i = 0; i < 256; i++)
+  {
+    UInt64 r = i;
+    unsigned j;
+    for (j = 0; j < 8; j++)
+      r = (r >> 1) ^ (kCrc64Poly & ((UInt64)0 - (r & 1)));
+    g_Crc64Table[i] = r;
+  }
+  for (i = 256; i < 256 * CRC64_NUM_TABLES; i++)
+  {
+    UInt64 r = g_Crc64Table[(size_t)i - 256];
+    g_Crc64Table[i] = g_Crc64Table[r & 0xFF] ^ (r >> 8);
+  }
+  
+  #ifdef MY_CPU_LE
+
+  g_Crc64Update = XzCrc64UpdateT4;
+
+  #else
+  {
+    #ifndef MY_CPU_BE
+    UInt32 k = 1;
+    if (*(const Byte *)&k == 1)
+      g_Crc64Update = XzCrc64UpdateT4;
+    else
+    #endif
+    {
+      for (i = 256 * CRC64_NUM_TABLES - 1; i >= 256; i--)
+      {
+        UInt64 x = g_Crc64Table[(size_t)i - 256];
+        g_Crc64Table[i] = CRC_UINT64_SWAP(x);
+      }
+      g_Crc64Update = XzCrc64UpdateT1_BeT4;
+    }
+  }
+  #endif
+}
@@ -0,0 +1,26 @@
+/* XzCrc64.h -- CRC64 calculation
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_CRC64_H
+#define __XZ_CRC64_H
+
+#include <stddef.h>
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+extern UInt64 g_Crc64Table[];
+
+void MY_FAST_CALL Crc64GenerateTable(void);
+
+#define CRC64_INIT_VAL UINT64_CONST(0xFFFFFFFFFFFFFFFF)
+#define CRC64_GET_DIGEST(crc) ((crc) ^ CRC64_INIT_VAL)
+#define CRC64_UPDATE_BYTE(crc, b) (g_Crc64Table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt64 MY_FAST_CALL Crc64Update(UInt64 crc, const void *data, size_t size);
+UInt64 MY_FAST_CALL Crc64Calc(const void *data, size_t size);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,69 @@
+/* XzCrc64Opt.c -- CRC64 calculation
+2017-06-30 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifndef MY_CPU_BE
+
+#define CRC64_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt64 MY_FAST_CALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    UInt32 d = (UInt32)v ^ *(const UInt32 *)p;
+    v = (v >> 32)
+        ^ (table + 0x300)[((d      ) & 0xFF)]
+        ^ (table + 0x200)[((d >>  8) & 0xFF)]
+        ^ (table + 0x100)[((d >> 16) & 0xFF)]
+        ^ (table + 0x000)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+#endif
+
+
+#ifndef MY_CPU_LE
+
+#define CRC_UINT64_SWAP(v) \
+      ((v >> 56) \
+    | ((v >> 40) & ((UInt64)0xFF <<  8)) \
+    | ((v >> 24) & ((UInt64)0xFF << 16)) \
+    | ((v >>  8) & ((UInt64)0xFF << 24)) \
+    | ((v <<  8) & ((UInt64)0xFF << 32)) \
+    | ((v << 24) & ((UInt64)0xFF << 40)) \
+    | ((v << 40) & ((UInt64)0xFF << 48)) \
+    | ((v << 56)))
+
+#define CRC64_UPDATE_BYTE_2_BE(crc, b) (table[(Byte)((crc) >> 56) ^ (b)] ^ ((crc) << 8))
+
+UInt64 MY_FAST_CALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT64_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    UInt32 d = (UInt32)(v >> 32) ^ *(const UInt32 *)p;
+    v = (v << 32)
+        ^ (table + 0x000)[((d      ) & 0xFF)]
+        ^ (table + 0x100)[((d >>  8) & 0xFF)]
+        ^ (table + 0x200)[((d >> 16) & 0xFF)]
+        ^ (table + 0x300)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT64_SWAP(v);
+}
+
+#endif
@@ -0,0 +1,60 @@
+/* XzEnc.h -- Xz Encode
+2017-06-27 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_ENC_H
+#define __XZ_ENC_H
+
+#include "Lzma2Enc.h"
+
+#include "Xz.h"
+
+EXTERN_C_BEGIN
+
+
+#define XZ_PROPS__BLOCK_SIZE__AUTO   LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO
+#define XZ_PROPS__BLOCK_SIZE__SOLID  LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+
+
+typedef struct
+{
+  UInt32 id;
+  UInt32 delta;
+  UInt32 ip;
+  int ipDefined;
+} CXzFilterProps;
+
+void XzFilterProps_Init(CXzFilterProps *p);
+
+
+typedef struct
+{
+  CLzma2EncProps lzma2Props;
+  CXzFilterProps filterProps;
+  unsigned checkId;
+  UInt64 blockSize;
+  int numBlockThreads_Reduced;
+  int numBlockThreads_Max;
+  int numTotalThreads;
+  int forceWriteSizesInHeader;
+  UInt64 reduceSize;
+} CXzProps;
+
+void XzProps_Init(CXzProps *p);
+
+
+typedef void * CXzEncHandle;
+
+CXzEncHandle XzEnc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig);
+void XzEnc_Destroy(CXzEncHandle p);
+SRes XzEnc_SetProps(CXzEncHandle p, const CXzProps *props);
+void XzEnc_SetDataSize(CXzEncHandle p, UInt64 expectedDataSiize);
+SRes XzEnc_Encode(CXzEncHandle p, ISeqOutStream *outStream, ISeqInStream *inStream, ICompressProgress *progress);
+
+SRes Xz_Encode(ISeqOutStream *outStream, ISeqInStream *inStream,
+    const CXzProps *props, ICompressProgress *progress);
+
+SRes Xz_EncodeEmpty(ISeqOutStream *outStream);
+
+EXTERN_C_END
+
+#endif
@@ -0,0 +1,319 @@
+/* XzIn.c - Xz input
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+#include "Xz.h"
+
+/*
+#define XZ_FOOTER_SIG_CHECK(p) (memcmp((p), XZ_FOOTER_SIG, XZ_FOOTER_SIG_SIZE) == 0)
+*/
+#define XZ_FOOTER_SIG_CHECK(p) ((p)[0] == XZ_FOOTER_SIG_0 && (p)[1] == XZ_FOOTER_SIG_1)
+
+
+SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStream *inStream)
+{
+  Byte sig[XZ_STREAM_HEADER_SIZE];
+  RINOK(SeqInStream_Read2(inStream, sig, XZ_STREAM_HEADER_SIZE, SZ_ERROR_NO_ARCHIVE));
+  if (memcmp(sig, XZ_SIG, XZ_SIG_SIZE) != 0)
+    return SZ_ERROR_NO_ARCHIVE;
+  return Xz_ParseHeader(p, sig);
+}
+
+#define READ_VARINT_AND_CHECK(buf, pos, size, res) \
+  { unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
+  if (s == 0) return SZ_ERROR_ARCHIVE; pos += s; }
+
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes)
+{
+  Byte header[XZ_BLOCK_HEADER_SIZE_MAX];
+  unsigned headerSize;
+  *headerSizeRes = 0;
+  RINOK(SeqInStream_ReadByte(inStream, &header[0]));
+  headerSize = (unsigned)header[0];
+  if (headerSize == 0)
+  {
+    *headerSizeRes = 1;
+    *isIndex = True;
+    return SZ_OK;
+  }
+
+  *isIndex = False;
+  headerSize = (headerSize << 2) + 4;
+  *headerSizeRes = headerSize;
+  RINOK(SeqInStream_Read(inStream, header + 1, headerSize - 1));
+  return XzBlock_Parse(p, header);
+}
+
+#define ADD_SIZE_CHECK(size, val) \
+  { UInt64 newSize = size + (val); if (newSize < size) return XZ_SIZE_OVERFLOW; size = newSize; }
+
+UInt64 Xz_GetUnpackSize(const CXzStream *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->numBlocks; i++)
+    ADD_SIZE_CHECK(size, p->blocks[i].unpackSize);
+  return size;
+}
+
+UInt64 Xz_GetPackSize(const CXzStream *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->numBlocks; i++)
+    ADD_SIZE_CHECK(size, (p->blocks[i].totalSize + 3) & ~(UInt64)3);
+  return size;
+}
+
+/*
+SRes XzBlock_ReadFooter(CXzBlock *p, CXzStreamFlags f, ISeqInStream *inStream)
+{
+  return SeqInStream_Read(inStream, p->check, XzFlags_GetCheckSize(f));
+}
+*/
+
+static SRes Xz_ReadIndex2(CXzStream *p, const Byte *buf, size_t size, ISzAllocPtr alloc)
+{
+  size_t numBlocks, pos = 1;
+  UInt32 crc;
+
+  if (size < 5 || buf[0] != 0)
+    return SZ_ERROR_ARCHIVE;
+
+  size -= 4;
+  crc = CrcCalc(buf, size);
+  if (crc != GetUi32(buf + size))
+    return SZ_ERROR_ARCHIVE;
+
+  {
+    UInt64 numBlocks64;
+    READ_VARINT_AND_CHECK(buf, pos, size, &numBlocks64);
+    numBlocks = (size_t)numBlocks64;
+    if (numBlocks != numBlocks64 || numBlocks * 2 > size)
+      return SZ_ERROR_ARCHIVE;
+  }
+  
+  Xz_Free(p, alloc);
+  if (numBlocks != 0)
+  {
+    size_t i;
+    p->numBlocks = numBlocks;
+    p->blocks = (CXzBlockSizes *)ISzAlloc_Alloc(alloc, sizeof(CXzBlockSizes) * numBlocks);
+    if (!p->blocks)
+      return SZ_ERROR_MEM;
+    for (i = 0; i < numBlocks; i++)
+    {
+      CXzBlockSizes *block = &p->blocks[i];
+      READ_VARINT_AND_CHECK(buf, pos, size, &block->totalSize);
+      READ_VARINT_AND_CHECK(buf, pos, size, &block->unpackSize);
+      if (block->totalSize == 0)
+        return SZ_ERROR_ARCHIVE;
+    }
+  }
+  while ((pos & 3) != 0)
+    if (buf[pos++] != 0)
+      return SZ_ERROR_ARCHIVE;
+  return (pos == size) ? SZ_OK : SZ_ERROR_ARCHIVE;
+}
+
+static SRes Xz_ReadIndex(CXzStream *p, ILookInStream *stream, UInt64 indexSize, ISzAllocPtr alloc)
+{
+  SRes res;
+  size_t size;
+  Byte *buf;
+  if (indexSize > ((UInt32)1 << 31))
+    return SZ_ERROR_UNSUPPORTED;
+  size = (size_t)indexSize;
+  if (size != indexSize)
+    return SZ_ERROR_UNSUPPORTED;
+  buf = (Byte *)ISzAlloc_Alloc(alloc, size);
+  if (!buf)
+    return SZ_ERROR_MEM;
+  res = LookInStream_Read2(stream, buf, size, SZ_ERROR_UNSUPPORTED);
+  if (res == SZ_OK)
+    res = Xz_ReadIndex2(p, buf, size, alloc);
+  ISzAlloc_Free(alloc, buf);
+  return res;
+}
+
+static SRes LookInStream_SeekRead_ForArc(ILookInStream *stream, UInt64 offset, void *buf, size_t size)
+{
+  RINOK(LookInStream_SeekTo(stream, offset));
+  return LookInStream_Read(stream, buf, size);
+  /* return LookInStream_Read2(stream, buf, size, SZ_ERROR_NO_ARCHIVE); */
+}
+
+static SRes Xz_ReadBackward(CXzStream *p, ILookInStream *stream, Int64 *startOffset, ISzAllocPtr alloc)
+{
+  UInt64 indexSize;
+  Byte buf[XZ_STREAM_FOOTER_SIZE];
+  UInt64 pos = *startOffset;
+
+  if ((pos & 3) != 0 || pos < XZ_STREAM_FOOTER_SIZE)
+    return SZ_ERROR_NO_ARCHIVE;
+
+  pos -= XZ_STREAM_FOOTER_SIZE;
+  RINOK(LookInStream_SeekRead_ForArc(stream, pos, buf, XZ_STREAM_FOOTER_SIZE));
+  
+  if (!XZ_FOOTER_SIG_CHECK(buf + 10))
+  {
+    UInt32 total = 0;
+    pos += XZ_STREAM_FOOTER_SIZE;
+    
+    for (;;)
+    {
+      size_t i;
+      #define TEMP_BUF_SIZE (1 << 10)
+      Byte temp[TEMP_BUF_SIZE];
+      
+      i = (pos > TEMP_BUF_SIZE) ? TEMP_BUF_SIZE : (size_t)pos;
+      pos -= i;
+      RINOK(LookInStream_SeekRead_ForArc(stream, pos, temp, i));
+      total += (UInt32)i;
+      for (; i != 0; i--)
+        if (temp[i - 1] != 0)
+          break;
+      if (i != 0)
+      {
+        if ((i & 3) != 0)
+          return SZ_ERROR_NO_ARCHIVE;
+        pos += i;
+        break;
+      }
+      if (pos < XZ_STREAM_FOOTER_SIZE || total > (1 << 16))
+        return SZ_ERROR_NO_ARCHIVE;
+    }
+    
+    if (pos < XZ_STREAM_FOOTER_SIZE)
+      return SZ_ERROR_NO_ARCHIVE;
+    pos -= XZ_STREAM_FOOTER_SIZE;
+    RINOK(LookInStream_SeekRead_ForArc(stream, pos, buf, XZ_STREAM_FOOTER_SIZE));
+    if (!XZ_FOOTER_SIG_CHECK(buf + 10))
+      return SZ_ERROR_NO_ARCHIVE;
+  }
+  
+  p->flags = (CXzStreamFlags)GetBe16(buf + 8);
+
+  if (!XzFlags_IsSupported(p->flags))
+    return SZ_ERROR_UNSUPPORTED;
+
+  if (GetUi32(buf) != CrcCalc(buf + 4, 6))
+    return SZ_ERROR_ARCHIVE;
+
+  indexSize = ((UInt64)GetUi32(buf + 4) + 1) << 2;
+
+  if (pos < indexSize)
+    return SZ_ERROR_ARCHIVE;
+
+  pos -= indexSize;
+  RINOK(LookInStream_SeekTo(stream, pos));
+  RINOK(Xz_ReadIndex(p, stream, indexSize, alloc));
+
+  {
+    UInt64 totalSize = Xz_GetPackSize(p);
+    if (totalSize == XZ_SIZE_OVERFLOW
+        || totalSize >= ((UInt64)1 << 63)
+        || pos < totalSize + XZ_STREAM_HEADER_SIZE)
+      return SZ_ERROR_ARCHIVE;
+    pos -= (totalSize + XZ_STREAM_HEADER_SIZE);
+    RINOK(LookInStream_SeekTo(stream, pos));
+    *startOffset = pos;
+  }
+  {
+    CXzStreamFlags headerFlags;
+    CSecToRead secToRead;
+    SecToRead_CreateVTable(&secToRead);
+    secToRead.realStream = stream;
+
+    RINOK(Xz_ReadHeader(&headerFlags, &secToRead.vt));
+    return (p->flags == headerFlags) ? SZ_OK : SZ_ERROR_ARCHIVE;
+  }
+}
+
+
+/* ---------- Xz Streams ---------- */
+
+void Xzs_Construct(CXzs *p)
+{
+  p->num = p->numAllocated = 0;
+  p->streams = 0;
+}
+
+void Xzs_Free(CXzs *p, ISzAllocPtr alloc)
+{
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    Xz_Free(&p->streams[i], alloc);
+  ISzAlloc_Free(alloc, p->streams);
+  p->num = p->numAllocated = 0;
+  p->streams = 0;
+}
+
+UInt64 Xzs_GetNumBlocks(const CXzs *p)
+{
+  UInt64 num = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    num += p->streams[i].numBlocks;
+  return num;
+}
+
+UInt64 Xzs_GetUnpackSize(const CXzs *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    ADD_SIZE_CHECK(size, Xz_GetUnpackSize(&p->streams[i]));
+  return size;
+}
+
+/*
+UInt64 Xzs_GetPackSize(const CXzs *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    ADD_SIZE_CHECK(size, Xz_GetTotalSize(&p->streams[i]));
+  return size;
+}
+*/
+
+SRes Xzs_ReadBackward(CXzs *p, ILookInStream *stream, Int64 *startOffset, ICompressProgress *progress, ISzAllocPtr alloc)
+{
+  Int64 endOffset = 0;
+  RINOK(ILookInStream_Seek(stream, &endOffset, SZ_SEEK_END));
+  *startOffset = endOffset;
+  for (;;)
+  {
+    CXzStream st;
+    SRes res;
+    Xz_Construct(&st);
+    res = Xz_ReadBackward(&st, stream, startOffset, alloc);
+    st.startOffset = *startOffset;
+    RINOK(res);
+    if (p->num == p->numAllocated)
+    {
+      size_t newNum = p->num + p->num / 4 + 1;
+      Byte *data = (Byte *)ISzAlloc_Alloc(alloc, newNum * sizeof(CXzStream));
+      if (!data)
+        return SZ_ERROR_MEM;
+      p->numAllocated = newNum;
+      if (p->num != 0)
+        memcpy(data, p->streams, p->num * sizeof(CXzStream));
+      ISzAlloc_Free(alloc, p->streams);
+      p->streams = (CXzStream *)data;
+    }
+    p->streams[p->num++] = st;
+    if (*startOffset == 0)
+      break;
+    RINOK(LookInStream_SeekTo(stream, *startOffset));
+    if (progress && ICompressProgress_Progress(progress, endOffset - *startOffset, (UInt64)(Int64)-1) != SZ_OK)
+      return SZ_ERROR_PROGRESS;
+  }
+  return SZ_OK;
+}
@@ -0,0 +1,241 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup Label="ProjectConfigurations">
+    <ProjectConfiguration Include="Debug|Win32">
+      <Configuration>Debug</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|Win32">
+      <Configuration>Release</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug|x64">
+      <Configuration>Debug</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|x64">
+      <Configuration>Release</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="7z\7z.h" />
+    <ClInclude Include="7z\7zAlloc.h" />
+    <ClInclude Include="7z\7zBuf.h" />
+    <ClInclude Include="7z\7zCrc.h" />
+    <ClInclude Include="7z\7zFile.h" />
+    <ClInclude Include="7z\7zTypes.h" />
+    <ClInclude Include="7z\7zVersion.h" />
+    <ClInclude Include="7z\Aes.h" />
+    <ClInclude Include="7z\Alloc.h" />
+    <ClInclude Include="7z\Bcj2.h" />
+    <ClInclude Include="7z\Bra.h" />
+    <ClInclude Include="7z\Compiler.h" />
+    <ClInclude Include="7z\CpuArch.h" />
+    <ClInclude Include="7z\Delta.h" />
+    <ClInclude Include="7z\DllSecur.h" />
+    <ClInclude Include="7z\LzFind.h" />
+    <ClInclude Include="7z\LzFindMt.h" />
+    <ClInclude Include="7z\LzHash.h" />
+    <ClInclude Include="7z\Lzma2Dec.h" />
+    <ClInclude Include="7z\Lzma2DecMt.h" />
+    <ClInclude Include="7z\Lzma2Enc.h" />
+    <ClInclude Include="7z\Lzma86.h" />
+    <ClInclude Include="7z\LzmaDec.h" />
+    <ClInclude Include="7z\LzmaEnc.h" />
+    <ClInclude Include="7z\LzmaLib.h" />
+    <ClInclude Include="7z\MtCoder.h" />
+    <ClInclude Include="7z\MtDec.h" />
+    <ClInclude Include="7z\Ppmd.h" />
+    <ClInclude Include="7z\Ppmd7.h" />
+    <ClInclude Include="7z\Precomp.h" />
+    <ClInclude Include="7z\RotateDefs.h" />
+    <ClInclude Include="7z\Sha256.h" />
+    <ClInclude Include="7z\Sort.h" />
+    <ClInclude Include="7z\Threads.h" />
+    <ClInclude Include="7z\Xz.h" />
+    <ClInclude Include="7z\XzCrc64.h" />
+    <ClInclude Include="7z\XzEnc.h" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="7z\7zAlloc.c" />
+    <ClCompile Include="7z\7zArcIn.c" />
+    <ClCompile Include="7z\7zBuf.c" />
+    <ClCompile Include="7z\7zBuf2.c" />
+    <ClCompile Include="7z\7zCrc.c" />
+    <ClCompile Include="7z\7zCrcOpt.c" />
+    <ClCompile Include="7z\7zDec.c" />
+    <ClCompile Include="7z\7zFile.c" />
+    <ClCompile Include="7z\7zStream.c" />
+    <ClCompile Include="7z\Aes.c" />
+    <ClCompile Include="7z\AesOpt.c" />
+    <ClCompile Include="7z\Alloc.c" />
+    <ClCompile Include="7z\Bcj2.c" />
+    <ClCompile Include="7z\Bcj2Enc.c" />
+    <ClCompile Include="7z\Bra.c" />
+    <ClCompile Include="7z\Bra86.c" />
+    <ClCompile Include="7z\BraIA64.c" />
+    <ClCompile Include="7z\CpuArch.c" />
+    <ClCompile Include="7z\Delta.c" />
+    <ClCompile Include="7z\DllSecur.c" />
+    <ClCompile Include="7z\LzFind.c" />
+    <ClCompile Include="7z\LzFindMt.c" />
+    <ClCompile Include="7z\Lzma2Dec.c" />
+    <ClCompile Include="7z\Lzma2DecMt.c" />
+    <ClCompile Include="7z\Lzma2Enc.c" />
+    <ClCompile Include="7z\Lzma86Dec.c" />
+    <ClCompile Include="7z\Lzma86Enc.c" />
+    <ClCompile Include="7z\LzmaDec.c" />
+    <ClCompile Include="7z\LzmaEnc.c" />
+    <ClCompile Include="7z\LzmaLib.c" />
+    <ClCompile Include="7z\MtCoder.c" />
+    <ClCompile Include="7z\MtDec.c" />
+    <ClCompile Include="7z\Ppmd7.c" />
+    <ClCompile Include="7z\Ppmd7Dec.c" />
+    <ClCompile Include="7z\Ppmd7Enc.c" />
+    <ClCompile Include="7z\Sha256.c" />
+    <ClCompile Include="7z\Sort.c" />
+    <ClCompile Include="7z\Threads.c" />
+    <ClCompile Include="7z\Xz.c" />
+    <ClCompile Include="7z\XzCrc64.c" />
+    <ClCompile Include="7z\XzCrc64Opt.c" />
+    <ClCompile Include="7z\XzDec.c" />
+    <ClCompile Include="7z\XzEnc.c" />
+    <ClCompile Include="7z\XzIn.c" />
+  </ItemGroup>
+  <PropertyGroup Label="Globals">
+    <VCProjectVersion>16.0</VCProjectVersion>
+    <ProjectGuid>{5B146DEA-9ACE-4D32-A7FD-3F42464DD69C}</ProjectGuid>
+    <Keyword>Win32Proj</Keyword>
+    <RootNamespace>My7zlib</RootNamespace>
+  </PropertyGroup>
+  <Import Project="..\common_default.props" />
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <Import Project="..\common_default_macros.props" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+    <ConfigurationType>StaticLibrary</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+    <ConfigurationType>StaticLibrary</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+    <ConfigurationType>StaticLibrary</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+    <ConfigurationType>StaticLibrary</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings">
+  </ImportGroup>
+  <ImportGroup Label="Shared">
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup>
+    <OutDir>$(SolutionDir)lib/$(Configuration)-$(Platform)/</OutDir>
+    <IntDir>$(SolutionDir)tmp\$(ProjectName)-$(Configuration)-$(Platform)/</IntDir>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <LinkIncremental>false</LinkIncremental>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <LinkIncremental>true</LinkIncremental>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <LinkIncremental>true</LinkIncremental>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <LinkIncremental>false</LinkIncremental>
+  </PropertyGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>MaxSpeed</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>NDEBUG;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <PrecompiledHeaderFile>pch.h</PrecompiledHeaderFile>
+    </ClCompile>
+    <Link>
+      <SubSystem>Windows</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <ClCompile>
+      <PrecompiledHeader>Use</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>Disabled</Optimization>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <PrecompiledHeaderFile>pch.h</PrecompiledHeaderFile>
+    </ClCompile>
+    <Link>
+      <SubSystem>Windows</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>Disabled</Optimization>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>_DEBUG;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <PrecompiledHeaderFile>pch.h</PrecompiledHeaderFile>
+    </ClCompile>
+    <Link>
+      <SubSystem>Windows</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <ClCompile>
+      <PrecompiledHeader>Use</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>MaxSpeed</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <PrecompiledHeaderFile>pch.h</PrecompiledHeaderFile>
+    </ClCompile>
+    <Link>
+      <SubSystem>Windows</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+  </ImportGroup>
+</Project>
@@ -0,0 +1,264 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <Filter Include="Source Files">
+      <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
+      <Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+    </Filter>
+    <Filter Include="Header Files">
+      <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+      <Extensions>h;hh;hpp;hxx;hm;inl;inc;ipp;xsd</Extensions>
+    </Filter>
+    <Filter Include="Resource Files">
+      <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+      <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
+    </Filter>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="7z\7z.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zAlloc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zBuf.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zCrc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zFile.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zTypes.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\7zVersion.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Aes.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Alloc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Bcj2.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Bra.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Compiler.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\CpuArch.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Delta.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\DllSecur.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzFind.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzFindMt.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzHash.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Lzma2Dec.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Lzma2DecMt.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Lzma2Enc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Lzma86.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzmaDec.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzmaEnc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\LzmaLib.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\MtCoder.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\MtDec.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Ppmd.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Ppmd7.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Precomp.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\RotateDefs.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Sha256.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Sort.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Threads.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\Xz.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\XzCrc64.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+    <ClInclude Include="7z\XzEnc.h">
+      <Filter>Header Files</Filter>
+    </ClInclude>
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="7z\7zAlloc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zArcIn.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zBuf.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zBuf2.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zCrc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zCrcOpt.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zDec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zFile.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\7zStream.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Aes.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\AesOpt.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Alloc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Bcj2.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Bcj2Enc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Bra.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Bra86.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\BraIA64.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\CpuArch.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Delta.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\DllSecur.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\LzFind.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\LzFindMt.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Lzma2Dec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Lzma2DecMt.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Lzma2Enc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Lzma86Dec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Lzma86Enc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\LzmaDec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\LzmaEnc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\LzmaLib.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\MtCoder.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\MtDec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Ppmd7.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Ppmd7Dec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Ppmd7Enc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Sha256.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Sort.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Threads.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\Xz.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\XzCrc64.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\XzCrc64Opt.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\XzDec.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\XzEnc.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+    <ClCompile Include="7z\XzIn.c">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+  </ItemGroup>
+</Project>
@@ -0,0 +1,438 @@
+find_package(PkgConfig)
+include(ExternalProject)
+
+# Dummy target to use when lib isn't available
+add_library(3rdparty_dummy_lib INTERFACE)
+
+
+# ZLib
+if (USE_SYSTEM_ZLIB)
+	find_package(ZLIB QUIET)
+endif()
+
+if (NOT ZLIB_FOUND)
+	message(STATUS "Using builtin ZLIB")
+	set(SKIP_INSTALL_ALL ON)
+	add_subdirectory(zlib EXCLUDE_FROM_ALL)
+	set(ZLIB_INCLUDE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/zlib" "${CMAKE_CURRENT_BINARY_DIR}/zlib")
+	set(ZLIB_LIBRARY zlibstatic)
+endif()
+
+add_library(3rdparty_zlib INTERFACE)
+target_link_libraries(3rdparty_zlib INTERFACE ${ZLIB_LIBRARY})
+target_include_directories(3rdparty_zlib INTERFACE ${ZLIB_INCLUDE_DIR})
+
+# 7z sdk
+if(WIN32)
+	add_library(3rdparty_7z STATIC EXCLUDE_FROM_ALL
+		7z/Sha256.c
+		7z/Ppmd7Dec.c
+		7z/XzDec.c
+		7z/XzEnc.c
+		7z/Lzma2Dec.c
+		7z/XzCrc64.c
+		7z/DllSecur.c
+		7z/Lzma2DecMt.c
+		7z/BraIA64.c
+		7z/7zFile.c
+		7z/7zStream.c
+		7z/Lzma86Enc.c
+		7z/Threads.c
+		7z/7zAlloc.c
+		7z/LzmaEnc.c
+		7z/MtCoder.c
+		7z/Lzma86Dec.c
+		7z/Sort.c
+		7z/LzFindMt.c
+		7z/7zDec.c
+		7z/Bcj2.c
+		7z/Ppmd7.c
+		7z/Bra86.c
+		7z/Bcj2Enc.c
+		7z/7zBuf.c
+		7z/Aes.c
+		7z/AesOpt.c
+		7z/XzCrc64Opt.c
+		7z/7zArcIn.c
+		7z/Lzma2Enc.c
+		7z/Bra.c
+		7z/7zCrcOpt.c
+		7z/7zBuf2.c
+		7z/LzFind.c
+		7z/Ppmd7Enc.c
+		7z/CpuArch.c
+		7z/Delta.c
+		7z/XzIn.c
+		7z/Alloc.c
+		7z/Xz.c
+		7z/LzmaDec.c
+		7z/LzmaLib.c
+		7z/7zCrc.c
+		7z/MtDec.c)
+	target_include_directories(3rdparty_7z INTERFACE 7z)
+else()
+	add_library(3rdparty_7z INTERFACE)
+endif()
+
+# libPNG
+# Select the version of libpng to use, default is builtin
+if (NOT USE_SYSTEM_LIBPNG)
+	# We use libpng's static library and don't need to build the shared library and run the tests
+	set(PNG_SHARED OFF CACHE BOOL "Build shared lib" FORCE)
+	set(PNG_TESTS OFF CACHE BOOL "Build libpng tests" FORCE)
+	set(PNG_BUILD_ZLIB ON CACHE BOOL "ZLIB is already build or package is found" FORCE)
+	set(SKIP_INSTALL_ALL ON)
+	add_subdirectory(libpng EXCLUDE_FROM_ALL)
+
+	set(LIBPNG_TARGET png_static)
+
+	target_include_directories(png_static INTERFACE "${libpng_BINARY_DIR}" "${libpng_SOURCE_DIR}")
+else()
+	find_package(PNG REQUIRED)
+
+	add_library(3rdparty_system_libpng INTERFACE)
+	target_include_directories(3rdparty_system_libpng INTERFACE ${PNG_INCLUDE_DIR})
+	target_link_libraries(3rdparty_system_libpng INTERFACE ${PNG_LIBRARY})
+	target_compile_definitions(3rdparty_system_libpng INTERFACE ${PNG_DEFINITIONS})
+
+	set(LIBPNG_TARGET 3rdparty_system_libpng)
+endif()
+
+
+# pugixml
+add_subdirectory(pugixml EXCLUDE_FROM_ALL)
+
+
+# hidapi
+add_library(3rdparty_hidapi INTERFACE)
+target_include_directories(3rdparty_hidapi INTERFACE hidapi/hidapi)
+
+if(APPLE)
+	add_subdirectory(hidapi/mac EXCLUDE_FROM_ALL)
+	target_include_directories(hidapi-mac PUBLIC hidapi/hidapi)
+
+	target_link_libraries(3rdparty_hidapi INTERFACE hidapi-mac "-framework CoreFoundation" "-framework IOKit")
+elseif(CMAKE_SYSTEM MATCHES "Linux")
+	add_subdirectory(hidapi/linux EXCLUDE_FROM_ALL)
+	target_include_directories(hidapi-hidraw PUBLIC hidapi/hidapi)
+
+	target_link_libraries(3rdparty_hidapi INTERFACE hidapi-hidraw udev)
+elseif(WIN32)
+	add_subdirectory(hidapi/windows EXCLUDE_FROM_ALL)
+	target_include_directories(hidapi-hid PUBLIC hidapi/hidapi)
+
+	target_link_libraries(3rdparty_hidapi INTERFACE hidapi-hid Shlwapi.lib)
+else()
+	add_subdirectory(hidapi/libusb EXCLUDE_FROM_ALL)
+	target_include_directories(hidapi-libusb PUBLIC hidapi/hidapi)
+
+	target_link_libraries(3rdparty_hidapi INTERFACE hidapi-libusb usb)
+endif()
+
+
+# libusb
+if(CMAKE_SYSTEM MATCHES "DragonFly|FreeBSD")
+	# Always use system libusb as reference implementation isn't supported
+	add_library(usb-1.0-static INTERFACE)
+	target_link_libraries(usb-1.0-static INTERFACE usb)
+elseif(MSVC)
+	# Windows time.h defines timespec but doesn't add any flag for it, which makes libusb attempt to define it again
+	add_definitions(-DHAVE_STRUCT_TIMESPEC=1)
+	add_subdirectory(libusb_cmake EXCLUDE_FROM_ALL)
+else()
+	add_subdirectory(libusb_cmake EXCLUDE_FROM_ALL)
+endif()
+
+
+# yaml-cpp
+# We don't want to install yaml-cpp but its cmake file doesn't have option
+# to disable it...
+# So we just install it to a different directory
+set(CMAKE_INSTALL_PREFIX_OLD ${CMAKE_INSTALL_PREFIX})
+set(CMAKE_INSTALL_PREFIX ${CMAKE_BINARY_DIR}/yaml-cpp_install)
+
+set(YAML_CPP_BUILD_TESTS OFF CACHE BOOL "Enable testing" FORCE)
+set(YAML_CPP_BUILD_TOOLS OFF CACHE BOOL "Enable parse tools" FORCE)
+set(YAML_CPP_BUILD_CONTRIB OFF CACHE BOOL "Enable contrib stuff in library" FORCE)
+add_subdirectory(yaml-cpp EXCLUDE_FROM_ALL)
+
+set(CMAKE_INSTALL_PREFIX ${CMAKE_INSTALL_PREFIX_OLD})
+
+
+# xxHash
+set(XXHASH_BUNDLED_MODE ON)
+set(BUILD_SHARED_LIBS OFF CACHE BOOL "Make xxHash build static libs")
+add_subdirectory(xxHash/cmake_unofficial EXCLUDE_FROM_ALL)
+target_include_directories(xxhash INTERFACE xxHash)
+
+
+# cereal
+add_library(3rdparty_cereal INTERFACE)
+target_include_directories(3rdparty_cereal INTERFACE cereal/include)
+
+
+# OpenGL
+
+# Prefer GLVND for OpenGL rather than legacy
+set(OpenGL_GL_PREFERENCE GLVND)
+find_package(OpenGL REQUIRED)
+
+add_library(3rdparty_opengl INTERFACE)
+target_include_directories(3rdparty_opengl INTERFACE GL)
+
+if (WIN32)
+	if(NOT MSVC)
+		target_link_libraries(3rdparty_opengl INTERFACE ${OPENGL_LIBRARIES} opengl32.lib glu32.lib)
+	else()
+		target_link_libraries(3rdparty_opengl INTERFACE dxgi.lib d2d1.lib dwrite.lib)
+	endif()
+else()
+	target_link_libraries(3rdparty_opengl INTERFACE ${OPENGL_LIBRARIES})
+
+	target_compile_definitions(3rdparty_opengl
+		INTERFACE
+			-DGL_GLEXT_PROTOTYPES
+			-DGLX_GLXEXT_PROTOTYPES)
+endif()
+
+
+# span
+add_library(3rdparty_span INTERFACE)
+target_include_directories(3rdparty_span INTERFACE span/include)
+
+
+# stblib
+add_library(3rdparty_stblib INTERFACE)
+target_include_directories(3rdparty_stblib INTERFACE stblib)
+
+
+# discord_rpc
+add_library(3rdparty_discord-rpc INTERFACE)
+
+# We don't want Discord Rich Presence on the BSDs and other OSes
+if (USE_DISCORD_RPC AND (WIN32 OR CMAKE_SYSTEM MATCHES "Linux" OR APPLE))
+	if (WIN32 AND NOT MSVC)
+		ExternalProject_Add(discord-rpc
+				GIT_REPOSITORY https://github.com/discordapp/discord-rpc
+				BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR}/discord-rpc
+				INSTALL_COMMAND ""
+			)
+
+	endif()
+
+	target_include_directories(3rdparty_discord-rpc INTERFACE discord-rpc/include)
+	target_compile_definitions(3rdparty_discord-rpc INTERFACE -DWITH_DISCORD_RPC)
+
+	set(DISCORD_RPC_LIB NOTFOUND)
+	if (WIN32)
+		if (NOT MSVC)
+			set(DISCORD_RPC_LIB ${CMAKE_CURRENT_BINARY_DIR}/discord-rpc/src/libdiscord-rpc.a)
+		else()
+			find_library(DISCORD_RPC_LIB discord-rpc PATHS discord-rpc/lib/ NO_DEFAULT_PATH)
+		endif()
+	elseif(CMAKE_SYSTEM MATCHES "Linux")
+		find_library(DISCORD_RPC_LIB discord-rpc-linux PATHS discord-rpc/lib/ NO_DEFAULT_PATH)
+	elseif(APPLE)
+		find_library(DISCORD_RPC_LIB discord-rpc-mac PATHS discord-rpc/lib/ NO_DEFAULT_PATH)
+	endif()
+	target_link_libraries(3rdparty_discord-rpc INTERFACE ${DISCORD_RPC_LIB})
+	if(APPLE)
+		target_link_libraries(3rdparty_discord-rpc INTERFACE "objc" "-framework Foundation" "-framework CoreServices")
+	endif()
+endif()
+
+
+# ALSA
+set(ALSA_TARGET 3rdparty_dummy_lib)
+
+if(USE_ALSA)
+	find_package(ALSA)
+	if(ALSA_FOUND)
+		add_library(3rdparty_alsa INTERFACE)
+		target_compile_definitions(3rdparty_alsa INTERFACE -DHAVE_ALSA)
+		target_include_directories(3rdparty_alsa SYSTEM INTERFACE ${ALSA_INCLUDE_DIRS})
+		target_link_libraries(3rdparty_alsa INTERFACE ${ALSA_LIBRARIES})
+
+		set(ALSA_TARGET 3rdparty_alsa)
+	endif()
+endif()
+
+
+# Pulse
+set(PULSE_TARGET 3rdparty_dummy_lib)
+if(USE_PULSE)
+	pkg_check_modules(PULSE libpulse-simple)
+
+	if(PULSE_FOUND)
+		add_library(3rdparty_pulse INTERFACE)
+		target_compile_definitions(3rdparty_pulse INTERFACE -DHAVE_PULSE)
+		target_include_directories(3rdparty_pulse SYSTEM
+			INTERFACE ${PULSE_INCLUDE_DIRS})
+		target_link_libraries(3rdparty_pulse INTERFACE ${PULSE_LDFLAGS})
+
+		set(PULSE_TARGET 3rdparty_pulse)
+	endif()
+endif()
+
+# libevdev
+set(LIBEVDEV_TARGET 3rdparty_dummy_lib)
+if(USE_LIBEVDEV)
+	pkg_check_modules(LIBEVDEV libevdev)
+	if(LIBEVDEV_FOUND)
+		add_library(3rdparty_libevdev INTERFACE)
+		target_compile_definitions(3rdparty_libevdev INTERFACE -DHAVE_LIBEVDEV)
+		target_include_directories(3rdparty_libevdev SYSTEM
+			INTERFACE ${LIBEVDEV_INCLUDE_DIRS})
+		target_link_libraries(3rdparty_libevdev INTERFACE ${LIBEVDEV_LDFLAGS})
+
+		set(LIBEVDEV_TARGET 3rdparty_libevdev)
+	endif()
+endif()
+
+
+# Vulkan
+set(VULKAN_TARGET 3rdparty_dummy_lib)
+if(USE_VULKAN)
+	find_package(Vulkan)
+	if(VULKAN_FOUND)
+		add_library(3rdparty_vulkan INTERFACE)
+		target_compile_definitions(3rdparty_vulkan INTERFACE -DHAVE_VULKAN)
+		target_link_libraries(3rdparty_vulkan INTERFACE SPIRV Vulkan::Vulkan)
+
+		if(UNIX AND NOT APPLE)
+			find_package(Wayland)
+			if (WAYLAND_FOUND)
+				target_include_directories(3rdparty_vulkan
+					INTERFACE ${WAYLAND_INCLUDE_DIR})
+
+				target_compile_definitions(3rdparty_vulkan
+					INTERFACE -DVK_USE_PLATFORM_WAYLAND_KHR)
+			endif()
+		endif()
+
+		set(VULKAN_TARGET 3rdparty_vulkan)
+	else()
+		message("WARNING! USE_VULKAN was enabled, but libvulkan was not found. RPCS3 will be compiled without Vulkan support.")
+	endif()
+endif()
+
+
+# OpenAL
+if (MSVC)
+	find_path(OPENAL_INCLUDE_DIR al.h PATHS OpenAL/include)
+	find_library(OPENAL_LIBRARY OpenAL32 PATHS OpenAL/libs/Win64/)
+else()
+	find_package(OpenAL REQUIRED)
+endif()
+
+add_library(3rdparty_openal INTERFACE)
+target_include_directories(3rdparty_openal INTERFACE ${OPENAL_INCLUDE_DIR})
+target_link_libraries(3rdparty_openal INTERFACE ${OPENAL_LIBRARY})
+
+# FAudio
+set(FAUDIO_TARGET 3rdparty_dummy_lib)
+if(USE_FAUDIO)
+	# FAudio depends on SDL2
+	pkg_check_modules(SDL2 sdl2)
+	if (NOT SDL2_FOUND OR SDL2_VERSION VERSION_LESS 2.0.9)
+		message("-- RPCS3: FAudio requires SDL 2.0.9 or newer.")
+	else()
+		set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build shared library")
+		add_subdirectory(FAudio EXCLUDE_FROM_ALL)
+		target_compile_definitions(FAudio INTERFACE -DHAVE_FAUDIO)
+		set(FAUDIO_TARGET FAudio)
+	endif()
+endif()
+
+# FFMPEG
+add_library(3rdparty_ffmpeg INTERFACE)
+
+# Select the version of ffmpeg to use, default is builtin
+if(USE_SYSTEM_FFMPEG)
+	message("-- RPCS3: using shared ffmpeg")
+	find_package(FFMPEG REQUIRED)
+
+	target_include_directories(3rdparty_ffmpeg INTERFACE ${FFMPEG_INCLUDE_DIR})
+	target_link_libraries(3rdparty_ffmpeg INTERFACE ${FFMPEG_LIBRARIES})
+else()
+	if (NOT MSVC AND WIN32)
+		message("-- RPCS3: building ffmpeg submodule")
+
+		ExternalProject_Add(ffmpeg-mingw
+			DOWNLOAD_COMMAND ""
+			SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/ffmpeg
+			BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR}/ffmpeg
+			CONFIGURE_COMMAND  ${CMAKE_CURRENT_SOURCE_DIR}/ffmpeg/configure --prefix=./windows/x86_64 --arch=x86_64 --disable-avdevice --disable-programs --disable-avfilter --disable-postproc --disable-doc --disable-pthreads --enable-w32threads --disable-network --disable-everything --disable-encoders --disable-muxers --disable-hwaccels --disable-parsers --disable-protocols --enable-dxva2 --enable-static --disable-shared --enable-decoder=aac --enable-decoder=aac_latm --enable-decoder=atrac3 --enable-decoder=atrac3p --enable-decoder=mp3 --enable-decoder=pcm_s16le --enable-decoder=pcm_s8 --enable-decoder=h264 --enable-decoder=mpeg4 --enable-decoder=mpeg2video --enable-decoder=mjpeg --enable-decoder=mjpegb --enable-encoder=pcm_s16le --enable-encoder=ffv1 --enable-encoder=mpeg4 --enable-parser=h264 --enable-parser=mpeg4video --enable-parser=mpegaudio --enable-parser=mpegvideo --enable-parser=mjpeg --enable-parser=aac --enable-parser=aac_latm --enable-muxer=avi --enable-demuxer=h264 --enable-demuxer=m4v --enable-demuxer=mp3 --enable-demuxer=mpegvideo --enable-demuxer=mpegps --enable-demuxer=mjpeg --enable-demuxer=avi --enable-demuxer=aac --enable-demuxer=pmp --enable-demuxer=oma --enable-demuxer=pcm_s16le --enable-demuxer=pcm_s8 --enable-demuxer=wav --enable-hwaccel=h264_dxva2 --enable-indev=dshow --enable-protocol=file
+			BUILD_COMMAND make -j 4
+			INSTALL_COMMAND make install
+		)
+
+		set(FFMPEG_LIB_AVFORMAT "${CMAKE_CURRENT_BINARY_DIR}/ffmpeg/windows/x86_64/lib/libavformat.a")
+		set(FFMPEG_LIB_AVCODEC "${CMAKE_CURRENT_BINARY_DIR}/ffmpeg/windows/x86_64/lib/libavcodec.a")
+		set(FFMPEG_LIB_AVUTIL "${CMAKE_CURRENT_BINARY_DIR}/ffmpeg/windows/x86_64/lib/libavutil.a")
+		set(FFMPEG_LIB_SWSCALE "${CMAKE_CURRENT_BINARY_DIR}/ffmpeg/windows/x86_64/lib/libswscale.a")
+	else()
+		message("-- RPCS3: using builtin ffmpeg")
+
+		if (WIN32)
+			set(FFMPEG_LIB_DIR "ffmpeg/windows/x86_64")
+			target_link_libraries(3rdparty_ffmpeg INTERFACE "Bcrypt.lib")
+		elseif(CMAKE_SYSTEM MATCHES "Linux")
+			set(FFMPEG_LIB_DIR "ffmpeg/linux/x86_64")
+		elseif(APPLE)
+			set(FFMPEG_LIB_DIR "ffmpeg/macos/x86_64")
+		else()
+			message(FATAL_ERROR "Prebuilt ffmpeg is not available on this platform! Try USE_SYSTEM_FFMPEG=ON.")
+		endif()
+
+		find_library(FFMPEG_LIB_AVFORMAT avformat PATHS ${FFMPEG_LIB_DIR} NO_DEFAULT_PATH)
+		find_library(FFMPEG_LIB_AVCODEC avcodec PATHS ${FFMPEG_LIB_DIR} NO_DEFAULT_PATH)
+		find_library(FFMPEG_LIB_AVUTIL avutil PATHS ${FFMPEG_LIB_DIR} NO_DEFAULT_PATH)
+		find_library(FFMPEG_LIB_SWSCALE swscale PATHS ${FFMPEG_LIB_DIR} NO_DEFAULT_PATH)
+	endif()
+
+	target_include_directories(3rdparty_ffmpeg INTERFACE "ffmpeg/include")
+
+	target_link_libraries(3rdparty_ffmpeg
+		INTERFACE
+			${FFMPEG_LIB_AVFORMAT}
+			${FFMPEG_LIB_AVCODEC}
+			${FFMPEG_LIB_AVUTIL}
+			${FFMPEG_LIB_SWSCALE})
+endif()
+
+
+# GLEW
+add_library(3rdparty_glew INTERFACE)
+if(NOT MSVC)
+	find_package(GLEW 1.13.0 REQUIRED)
+	target_link_libraries(3rdparty_glew INTERFACE GLEW::GLEW)
+endif()
+
+
+# LLVM
+include(llvm.cmake)
+
+
+# add nice ALIAS targets for ease of use
+add_library(3rdparty::libusb ALIAS usb-1.0-static)
+add_library(3rdparty::zlib ALIAS 3rdparty_zlib)
+add_library(3rdparty::7z ALIAS 3rdparty_7z)
+add_library(3rdparty::pugixml ALIAS pugixml)
+add_library(3rdparty::yaml-cpp ALIAS yaml-cpp)
+add_library(3rdparty::xxhash ALIAS xxhash)
+add_library(3rdparty::hidapi ALIAS 3rdparty_hidapi)
+add_library(3rdparty::libpng ALIAS ${LIBPNG_TARGET})
+add_library(3rdparty::cereal ALIAS 3rdparty_cereal)
+add_library(3rdparty::opengl ALIAS 3rdparty_opengl)
+add_library(3rdparty::span ALIAS 3rdparty_span)
+add_library(3rdparty::stblib ALIAS 3rdparty_stblib)
+add_library(3rdparty::discord-rpc ALIAS 3rdparty_discord-rpc)
+add_library(3rdparty::alsa ALIAS ${ALSA_TARGET})
+add_library(3rdparty::pulse ALIAS ${PULSE_TARGET})
+add_library(3rdparty::faudio ALIAS ${FAUDIO_TARGET})
+add_library(3rdparty::libevdev ALIAS ${LIBEVDEV_TARGET})
+add_library(3rdparty::vulkan ALIAS ${VULKAN_TARGET})
+add_library(3rdparty::openal ALIAS 3rdparty_openal)
+add_library(3rdparty::ffmpeg ALIAS 3rdparty_ffmpeg)
+add_library(3rdparty::glew ALIAS 3rdparty_glew)
--- a/Show More
+++ b/Show More