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

Merge pull request #1701 from LeeYoung624/dev
memory leak fix
2019-07-25 13:44:51 -04:00 · 2019-07-25 11:56:37 -04:00 · 2019-07-25 21:07:57 +08:00 · 2019-07-24 19:07:55 -04:00 · 2019-07-24 16:04:37 -07:00 · 2019-07-24 16:03:01 -07:00
183 changed files with 9378 additions and 5257 deletions
@@ -1,33 +1,14 @@
 version: 2

-references:
-  # Install the dependencies required for tests.
-  # Add the step "- *install-dependencies" to the beginning of your job to run
-  # this command.
-  install-dependencies: &install-dependencies
-    run:
-      name: Install dependencies
-      # TODO: We can split these dependencies up by job to reduce installation
-      # time.
-      command: |
-        sudo dpkg --add-architecture i386
-        sudo apt-get -y -qq update
-        sudo apt-get -y install \
-            gcc-multilib-powerpc-linux-gnu gcc-arm-linux-gnueabi \
-            libc6-dev-armel-cross gcc-aarch64-linux-gnu libc6-dev-arm64-cross \
-            libc6-dev-ppc64-powerpc-cross zstd gzip coreutils \
-            libcurl4-openssl-dev
-
 jobs:
  # the first half of the jobs are in this test
  short-tests-0:
    # TODO: Create a small custom docker image with all the dependencies we need
    #       preinstalled to reduce installation time.
    docker:
-      - image: circleci/buildpack-deps:bionic
+      - image: fbopensource/zstd-circleci-primary:0.0.1
    steps:
      - checkout
-      - *install-dependencies
      - run:
          name: Test
          command: |
@@ -41,10 +22,9 @@ jobs:
  # the second half of the jobs are in this test
  short-tests-1:
    docker:
-      - image: circleci/buildpack-deps:bionic
+      - image: fbopensource/zstd-circleci-primary:0.0.1
    steps:
      - checkout
-      - *install-dependencies
      - run:
          name: Test
          command: |
@@ -61,12 +41,11 @@ jobs:
  # tagged release.
  publish-github-release:
    docker:
-      - image: circleci/buildpack-deps:bionic
+      - image: fbopensource/zstd-circleci-primary:0.0.1
    environment:
      CIRCLE_ARTIFACTS: /tmp/circleci-artifacts
    steps:
      - checkout
-      - *install-dependencies
      - run:
          name: Publish
          command: |
@@ -86,12 +65,11 @@ jobs:
  # This step should only be run in a cron job
  regression-test:
    docker:
-      - image: circleci/buildpack-deps:bionic
+      - image: fbopensource/zstd-circleci-primary:0.0.1
    environment:
      CIRCLE_ARTIFACTS: /tmp/circleci-artifacts
    steps:
      - checkout
-      - *install-dependencies
      # Restore the cached resources.
      - restore_cache:
          # We try our best to bust the cache when the data changes by hashing
@@ -0,0 +1,9 @@
+FROM circleci/buildpack-deps:bionic
+
+RUN sudo dpkg --add-architecture i386
+RUN sudo apt-get -y -qq update
+RUN sudo apt-get -y install \
+    gcc-multilib-powerpc-linux-gnu gcc-arm-linux-gnueabi \
+    libc6-dev-armel-cross gcc-aarch64-linux-gnu libc6-dev-arm64-cross \
+    libc6-dev-ppc64-powerpc-cross zstd gzip coreutils \
+    libcurl4-openssl-dev
@@ -0,0 +1,16 @@
+env:
+  CIRRUS_CLONE_DEPTH: 1
+  ARCH: amd64
+
+task:
+  freebsd_instance:
+    matrix:
+      image: freebsd-12-0-release-amd64
+      image: freebsd-11-2-release-amd64
+  install_script:
+    - sed -i.bak -e 's,pkg+http://pkg.FreeBSD.org/\${ABI}/quarterly,pkg+http://pkg.FreeBSD.org/\${ABI}/latest,' /etc/pkg/FreeBSD.conf
+    - pkg upgrade -y
+    - pkg install -y gmake coreutils
+  script: |
+    MOREFLAGS="-Werror" gmake -j all
+    gmake shortest
@@ -14,7 +14,7 @@
 *.dylib

 # Executables
-zstd
+/zstd
 zstdmt
 *.exe
 *.out
@@ -22,7 +22,7 @@ zstdmt

 # Test artefacts
 tmp*
-dictionary*
+dictionary.
 NUL

 # Build artefacts
@@ -41,3 +41,4 @@ _zstdbench/
 .DS_Store
 googletest/
 *.d
+*.vscode
@@ -2,7 +2,6 @@

 language: c
 dist: trusty
-sudo: required

 git:
  depth: 1
@@ -154,6 +153,12 @@ matrix:
        - make clean
        - make travis-install    # just ensures `make install` works

+    - name: c99 compatibility
+      if: branch = master
+      script:
+        - make c99build
+        - make -C tests test-zstd
+
    - name: PPC64
      if: branch = master
      script:
@@ -179,23 +184,36 @@ matrix:

    # meson dedicated test
    - name: Xenial (Meson + clang)
+      # env: ALLOW_FAILURES=true
      dist: xenial
      language: cpp
      compiler: clang
-      before_install:
+      install:
        - sudo apt-get install -qq liblz4-dev valgrind tree
-        - curl -o ~/get-pip.py 'https://bootstrap.pypa.io/get-pip.py'
-        - python3 ~/get-pip.py --user
-        - pip3 install --user meson ninja
+        - |
+          travis_retry curl -o ~/ninja.zip -L 'https://github.com/ninja-build/ninja/releases/download/v1.9.0/ninja-linux.zip' &&
+          unzip ~/ninja.zip -d ~/.local/bin
+        - |
+          travis_retry curl -o ~/get-pip.py -L 'https://bootstrap.pypa.io/get-pip.py' &&
+          python3 ~/get-pip.py --user &&
+          pip3 install --user meson
      script:
-        - meson --buildtype=debug
-                -Db_lundef=false
-                -Dauto_features=enabled
-                -Dbuild_{programs,tests,contrib}=true
-                -Ddefault_library=both
-                build/meson builddir
-        - cd builddir
+        - |
+          meson setup \
+            --buildtype=debugoptimized \
+            -Db_lundef=false \
+            -Dauto_features=enabled \
+            -Dbin_programs=true \
+            -Dbin_tests=true \
+            -Dbin_contrib=true \
+            -Ddefault_library=both \
+             build/meson builddir
+        - pushd builddir
+        - ninja
+        - meson test --verbose --no-rebuild
        - DESTDIR=./staging ninja install
        - tree ./staging
+      after_failure:
+        - cat "$TRAVIS_BUILD_DIR"/builddir/meson-logs/testlog.txt
  allow_failures:
-    - name: Xenial (Meson + clang)
+    - env: ALLOW_FAILURES=true
@@ -1,3 +1,76 @@
+v1.4.2
+bug: Fix bug in zstd-0.5 decoder by @terrelln (#1696)
+bug: Fix seekable decompression in-memory API by @iburinoc (#1695)
+misc: Validate blocks are smaller than size limit by @vivekmg (#1685)
+misc: Restructure source files by @ephiepark (#1679)
+
+v1.4.1
+bug: Fix data corruption in niche use cases by @terrelln (#1659)
+bug: Fuzz legacy modes, fix uncovered bugs by @terrelln (#1593, #1594, #1595)
+bug: Fix out of bounds read by @terrelln (#1590)
+perf: Improve decode speed by ~7% @mgrice (#1668)
+perf: Slightly improved compression ratio of level 3 and 4 (ZSTD_dfast) by @cyan4973 (#1681)
+perf: Slightly faster compression speed when re-using a context by @cyan4973 (#1658)
+perf: Improve compression ratio for small windowLog by @cyan4973 (#1624)
+perf: Faster compression speed in high compression mode for repetitive data by @terrelln (#1635)
+api: Add parameter to generate smaller dictionaries by @tyler-tran (#1656)
+cli: Recognize symlinks when built in C99 mode by @felixhandte (#1640)
+cli: Expose cpu load indicator for each file on -vv mode by @ephiepark (#1631)
+cli: Restrict read permissions on destination files by @chungy (#1644)
+cli: zstdgrep: handle -f flag by @felixhandte (#1618)
+cli: zstdcat: follow symlinks by @vejnar (#1604)
+doc: Remove extra size limit on compressed blocks by @felixhandte (#1689)
+doc: Fix typo by @yk-tanigawa (#1633)
+doc: Improve documentation on streaming buffer sizes by @cyan4973 (#1629)
+build: CMake: support building with LZ4 @leeyoung624 (#1626)
+build: CMake: install zstdless and zstdgrep by @leeyoung624 (#1647)
+build: CMake: respect existing uninstall target by @j301scott (#1619)
+build: Make: skip multithread tests when built without support by @michaelforney (#1620)
+build: Make: Fix examples/ test target by @sjnam (#1603)
+build: Meson: rename options out of deprecated namespace by @lzutao (#1665)
+build: Meson: fix build by @lzutao (#1602)
+build: Visual Studio: don't export symbols in static lib by @scharan (#1650)
+build: Visual Studio: fix linking by @absotively (#1639)
+build: Fix MinGW-W64 build by @myzhang1029 (#1600)
+misc: Expand decodecorpus coverage by @ephiepark (#1664)
+
+v1.4.0
+perf: Improve level 1 compression speed in most scenarios by 6% by @gbtucker and @terrelln
+api: Move the advanced API, including all functions in the staging section, to the stable section
+api: Make ZSTD_e_flush and ZSTD_e_end block for maximum forward progress
+api: Rename ZSTD_CCtxParam_getParameter to ZSTD_CCtxParams_getParameter
+api: Rename ZSTD_CCtxParam_setParameter to ZSTD_CCtxParams_setParameter
+api: Don't export ZSTDMT functions from the shared library by default
+api: Require ZSTD_MULTITHREAD to be defined to use ZSTDMT
+api: Add ZSTD_decompressBound() to provide an upper bound on decompressed size by @shakeelrao
+api: Fix ZSTD_decompressDCtx() corner cases with a dictionary
+api: Move ZSTD_getDictID_*() functions to the stable section
+api: Add ZSTD_c_literalCompressionMode flag to enable or disable literal compression by @terrelln
+api: Allow compression parameters to be set when a dictionary is used
+api: Allow setting parameters before or after ZSTD_CCtx_loadDictionary() is called
+api: Fix ZSTD_estimateCStreamSize_usingCCtxParams()
+api: Setting ZSTD_d_maxWindowLog to 0 means use the default
+cli: Ensure that a dictionary is not used to compress itself by @shakeelrao
+cli: Add --[no-]compress-literals flag to enable or disable literal compression
+doc: Update the examples to use the advanced API
+doc: Explain how to transition from old streaming functions to the advanced API in the header
+build: Improve the Windows release packages
+build: Improve CMake build by @hjmjohnson
+build: Build fixes for FreeBSD by @lwhsu
+build: Remove redundant warnings by @thatsafunnyname
+build: Fix tests on OpenBSD by @bket
+build: Extend fuzzer build system to work with the new clang engine
+build: CMake now creates the libzstd.so.1 symlink
+build: Improve Menson build by @lzutao
+misc: Fix symbolic link detection on FreeBSD
+misc: Use physical core count for -T0 on FreeBSD by @cemeyer
+misc: Fix zstd --list on truncated files by @kostmo
+misc: Improve logging in debug mode by @felixhandte
+misc: Add CirrusCI tests by @lwhsu
+misc: Optimize dictionary memory usage in corner cases
+misc: Improve the dictionary builder on small or homogeneous data
+misc: Fix spelling across the repo by @jsoref
+
 v1.3.8
 perf: better decompression speed on large files (+7%) and cold dictionaries (+15%)
 perf: slightly better compression ratio at high compression modes
@@ -239,7 +312,7 @@ v1.0.0
 Change Licensing, all project is now BSD, Copyright Facebook
 Small decompression speed improvement
 API : Streaming API supports legacy format
-API : ZDICT_getDictID(), ZSTD_sizeof_{CCtx, DCtx, CStream, DStream}(), ZSTD_setDStreamParamter()
+API : ZDICT_getDictID(), ZSTD_sizeof_{CCtx, DCtx, CStream, DStream}(), ZSTD_setDStreamParameter()
 CLI supports legacy formats v0.4+
 Fixed : compression fails on certain huge files, reported by Jesse McGrew
 Enhanced documentation, by Przemyslaw Skibinski
@@ -156,7 +156,7 @@ list:
 	    done \
 	} | column -t -s $$'\t'

-.PHONY: install clangtest armtest usan asan uasan
+.PHONY: install armtest usan asan uasan
 install:
 	@$(MAKE) -C $(ZSTDDIR) $@
 	@$(MAKE) -C $(PRGDIR) $@
@@ -188,7 +188,7 @@ gcc7build: clean
 .PHONY: clangbuild
 clangbuild: clean
 	clang -v
-	CXX=clang++ CC=clang $(MAKE) all MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
+	CXX=clang++ CC=clang CFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation" $(MAKE) all

 m32build: clean
 	gcc -v
@@ -232,10 +232,6 @@ gcc6test: clean
 	gcc-6 -v
 	$(MAKE) all CC=gcc-6 MOREFLAGS="-Werror"

-clangtest: clean
-	clang -v
-	$(MAKE) all CXX=clang++ CC=clang MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
-
 armtest: clean
 	$(MAKE) -C $(TESTDIR) datagen   # use native, faster
 	$(MAKE) -C $(TESTDIR) test CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static" FUZZER_FLAGS=--no-big-tests
@@ -14,6 +14,7 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
 [![Build Status][travisDevBadge]][travisLink]
 [![Build status][AppveyorDevBadge]][AppveyorLink]
 [![Build status][CircleDevBadge]][CircleLink]
+[![Build status][CirrusDevBadge]][CirrusLink]

 [travisDevBadge]: https://travis-ci.org/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
 [travisLink]: https://travis-ci.org/facebook/zstd
@@ -21,14 +22,16 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
 [AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
 [CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
 [CircleLink]: https://circleci.com/gh/facebook/zstd
+[CirrusDevBadge]: https://api.cirrus-ci.com/github/facebook/zstd.svg?branch=dev
+[CirrusLink]: https://cirrus-ci.com/github/facebook/zstd

 ## Benchmarks

 For reference, several fast compression algorithms were tested and compared
-on a server running Linux Debian (`Linux version 4.14.0-3-amd64`),
-with a Core i7-6700K CPU @ 4.0GHz,
+on a server running Arch Linux (`Linux version 5.0.5-arch1-1`),
+with a Core i9-9900K CPU @ 5.0GHz,
 using [lzbench], an open-source in-memory benchmark by @inikep
-compiled with [gcc] 7.3.0,
+compiled with [gcc] 8.2.1,
 on the [Silesia compression corpus].

 [lzbench]: https://github.com/inikep/lzbench
@@ -37,14 +40,14 @@ on the [Silesia compression corpus].

 | Compressor name         | Ratio | Compression| Decompress.|
 | ---------------         | ------| -----------| ---------- |
-| **zstd 1.3.4 -1**       | 2.877 |   470 MB/s |  1380 MB/s |
-| zlib 1.2.11 -1          | 2.743 |   110 MB/s |   400 MB/s |
-| brotli 1.0.2 -0         | 2.701 |   410 MB/s |   430 MB/s |
-| quicklz 1.5.0 -1        | 2.238 |   550 MB/s |   710 MB/s |
-| lzo1x 2.09 -1           | 2.108 |   650 MB/s |   830 MB/s |
-| lz4 1.8.1               | 2.101 |   750 MB/s |  3700 MB/s |
-| snappy 1.1.4            | 2.091 |   530 MB/s |  1800 MB/s |
-| lzf 3.6 -1              | 2.077 |   400 MB/s |   860 MB/s |
+| **zstd 1.4.0 -1**       | 2.884 |   530 MB/s |  1360 MB/s |
+| zlib 1.2.11 -1          | 2.743 |   110 MB/s |   440 MB/s |
+| brotli 1.0.7 -0         | 2.701 |   430 MB/s |   470 MB/s |
+| quicklz 1.5.0 -1        | 2.238 |   600 MB/s |   800 MB/s |
+| lzo1x 2.09 -1           | 2.106 |   680 MB/s |   950 MB/s |
+| lz4 1.8.3               | 2.101 |   800 MB/s |  4220 MB/s |
+| snappy 1.1.4            | 2.073 |   580 MB/s |  2020 MB/s |
+| lzf 3.6 -1              | 2.077 |   440 MB/s |   930 MB/s |

 [zlib]: http://www.zlib.net/
 [LZ4]: http://www.lz4.org/
@@ -29,3 +29,5 @@ compile_commands.json
 CTestTestfile.cmake
 build
 lib
+!cmake/lib
+!meson/lib
@@ -364,6 +364,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstdmt_compress.c"
 				>
@@ -408,6 +416,10 @@
 				RelativePath="..\..\..\programs\util.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\programs\timefn.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.c"
 				>
@@ -490,6 +502,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.h"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.h"
 				>
@@ -45,7 +45,7 @@
 				Name="VCCLCompilerTool"
 				Optimization="0"
 				AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
-				PreprocessorDefinitions="WIN32;_DEBUG;_CONSOLE"
+				PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE"
 				MinimalRebuild="true"
 				BasicRuntimeChecks="3"
 				RuntimeLibrary="3"
@@ -121,7 +121,7 @@
 				EnableIntrinsicFunctions="true"
 				OmitFramePointers="true"
 				AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
-				PreprocessorDefinitions="WIN32;NDEBUG;_CONSOLE"
+				PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE"
 				RuntimeLibrary="0"
 				EnableFunctionLevelLinking="true"
 				UsePrecompiledHeader="0"
@@ -195,7 +195,7 @@
 				Name="VCCLCompilerTool"
 				Optimization="0"
 				AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\programs"
-				PreprocessorDefinitions="WIN32;_DEBUG;_CONSOLE"
+				PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE"
 				MinimalRebuild="true"
 				BasicRuntimeChecks="3"
 				RuntimeLibrary="3"
@@ -272,7 +272,7 @@
 				EnableIntrinsicFunctions="true"
 				OmitFramePointers="true"
 				AdditionalIncludeDirectories="$(SolutionDir)..\..\lib;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\compress;$(SolutionDir)..\..\programs"
-				PreprocessorDefinitions="WIN32;NDEBUG;_CONSOLE"
+				PreprocessorDefinitions="ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE"
 				RuntimeLibrary="0"
 				EnableFunctionLevelLinking="true"
 				UsePrecompiledHeader="0"
@@ -332,6 +332,10 @@
 				RelativePath="..\..\..\programs\util.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\programs\timefn.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\programs\datagen.c"
 				>
@@ -408,6 +412,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\decompress\zstd_decompress.c"
 				>
@@ -526,6 +538,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.h"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.h"
 				>
@@ -336,6 +336,10 @@
 				RelativePath="..\..\..\programs\util.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\programs\timefn.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\programs\benchfn.c"
 				>
@@ -420,6 +424,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\decompress\zstd_decompress.c"
 				>
@@ -606,6 +618,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.h"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.h"
 				>
@@ -396,6 +396,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.c"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.c"
 				>
@@ -542,6 +550,14 @@
 				RelativePath="..\..\..\lib\compress\zstd_compress.h"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_literals.h"
+				>
+			</File>
+			<File
+				RelativePath="..\..\..\lib\compress\zstd_compress_sequences.h"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\compress\zstd_fast.h"
 				>
@@ -167,6 +167,7 @@
  <ItemGroup>
    <ClCompile Include="..\..\..\lib\common\xxhash.c" />
    <ClCompile Include="..\..\..\programs\util.c" />
+    <ClCompile Include="..\..\..\programs\timefn.c" />
    <ClCompile Include="..\..\..\programs\datagen.c" />
    <ClCompile Include="..\..\..\programs\benchfn.c" />
    <ClCompile Include="..\..\..\tests\fullbench.c" />
@@ -156,7 +156,6 @@
  </ItemDefinitionGroup>
  <ItemGroup>
    <ClCompile Include="..\..\..\lib\common\entropy_common.c" />
-    <ClCompile Include="..\..\..\programs\util.c" />
    <ClCompile Include="..\..\..\lib\common\debug.c" />
    <ClCompile Include="..\..\..\lib\common\fse_decompress.c" />
    <ClCompile Include="..\..\..\lib\common\zstd_common.c" />
@@ -168,6 +167,8 @@
    <ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
    <ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
@@ -178,6 +179,8 @@
    <ClCompile Include="..\..\..\lib\decompress\zstd_decompress.c" />
    <ClCompile Include="..\..\..\lib\decompress\zstd_decompress_block.c" />
    <ClCompile Include="..\..\..\lib\decompress\zstd_ddict.c" />
+    <ClCompile Include="..\..\..\programs\util.c" />
+    <ClCompile Include="..\..\..\programs\timefn.c" />
    <ClCompile Include="..\..\..\programs\datagen.c" />
    <ClCompile Include="..\..\..\programs\benchfn.c" />
    <ClCompile Include="..\..\..\tests\fullbench.c" />
@@ -192,6 +195,8 @@
    <ClInclude Include="..\..\..\lib\common\threading.h" />
    <ClInclude Include="..\..\..\lib\common\xxhash.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />
@@ -90,7 +90,7 @@
      </PrecompiledHeader>
      <WarningLevel>Level4</WarningLevel>
      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <TreatWarningAsError>true</TreatWarningAsError>
      <EnablePREfast>false</EnablePREfast>
    </ClCompile>
@@ -105,7 +105,7 @@
      </PrecompiledHeader>
      <WarningLevel>Level4</WarningLevel>
      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <TreatWarningAsError>true</TreatWarningAsError>
      <EnablePREfast>false</EnablePREfast>
    </ClCompile>
@@ -122,7 +122,7 @@
      <Optimization>MaxSpeed</Optimization>
      <FunctionLevelLinking>true</FunctionLevelLinking>
      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <EnablePREfast>false</EnablePREfast>
      <TreatWarningAsError>false</TreatWarningAsError>
      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
@@ -142,7 +142,7 @@
      <Optimization>MaxSpeed</Optimization>
      <FunctionLevelLinking>true</FunctionLevelLinking>
      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <TreatWarningAsError>false</TreatWarningAsError>
      <EnablePREfast>false</EnablePREfast>
      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
@@ -167,6 +167,8 @@
    <ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@@ -182,6 +184,7 @@
    <ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
    <ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
    <ClCompile Include="..\..\..\programs\util.c" />
+    <ClCompile Include="..\..\..\programs\timefn.c" />
    <ClCompile Include="..\..\..\programs\datagen.c" />
    <ClCompile Include="..\..\..\tests\fuzzer.c" />
  </ItemGroup>
@@ -195,6 +198,8 @@
    <ClInclude Include="..\..\..\lib\common\zstd_errors.h" />
    <ClInclude Include="..\..\..\lib\zstd.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />
@@ -31,6 +31,8 @@
    <ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@@ -78,6 +80,8 @@
    <ClInclude Include="..\..\..\lib\zstd.h" />
    <ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />
@@ -209,7 +213,6 @@
      <EnablePREfast>false</EnablePREfast>
      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
      <DebugInformationFormat>ProgramDatabase</DebugInformationFormat>
-      <AssemblerOutput>All</AssemblerOutput>
    </ClCompile>
    <Link>
      <SubSystem>Console</SubSystem>
@@ -234,7 +237,6 @@
      <DebugInformationFormat>ProgramDatabase</DebugInformationFormat>
      <WholeProgramOptimization>true</WholeProgramOptimization>
      <OmitFramePointers>true</OmitFramePointers>
-      <AssemblerOutput>All</AssemblerOutput>
    </ClCompile>
    <Link>
      <SubSystem>Console</SubSystem>
@@ -31,6 +31,8 @@
    <ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@@ -78,6 +80,8 @@
    <ClInclude Include="..\..\..\lib\zstd.h" />
    <ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />
@@ -90,31 +94,26 @@
    <ProjectGuid>{8BFD8150-94D5-4BF9-8A50-7BD9929A0850}</ProjectGuid>
    <Keyword>Win32Proj</Keyword>
    <RootNamespace>libzstd</RootNamespace>
+    <TargetName>libzstd_static</TargetName>
+    <CharacterSet>MultiByte</CharacterSet>
+    <ConfigurationType>StaticLibrary</ConfigurationType>
    <OutDir>$(SolutionDir)bin\$(Platform)_$(Configuration)\</OutDir>
    <IntDir>$(SolutionDir)bin\obj\$(RootNamespace)_$(Platform)_$(Configuration)\</IntDir>
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
-    <ConfigurationType>StaticLibrary</ConfigurationType>
    <UseDebugLibraries>true</UseDebugLibraries>
-    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
-    <ConfigurationType>StaticLibrary</ConfigurationType>
    <UseDebugLibraries>true</UseDebugLibraries>
-    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
-    <ConfigurationType>StaticLibrary</ConfigurationType>
    <UseDebugLibraries>false</UseDebugLibraries>
    <WholeProgramOptimization>true</WholeProgramOptimization>
-    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
-    <ConfigurationType>StaticLibrary</ConfigurationType>
    <UseDebugLibraries>false</UseDebugLibraries>
    <WholeProgramOptimization>true</WholeProgramOptimization>
-    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
@@ -134,35 +133,36 @@
  <PropertyGroup Label="UserMacros" />
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
    <LinkIncremental>true</LinkIncremental>
-    <TargetName>libzstd_static</TargetName>
    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs\legacy;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(UniversalCRT_IncludePath);</IncludePath>
    <RunCodeAnalysis>false</RunCodeAnalysis>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
    <LinkIncremental>true</LinkIncremental>
-    <TargetName>libzstd_static</TargetName>
    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs\legacy;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(UniversalCRT_IncludePath);</IncludePath>
    <RunCodeAnalysis>false</RunCodeAnalysis>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
    <LinkIncremental>false</LinkIncremental>
-    <TargetName>libzstd_static</TargetName>
    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs\legacy;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(UniversalCRT_IncludePath);</IncludePath>
    <RunCodeAnalysis>false</RunCodeAnalysis>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
    <LinkIncremental>false</LinkIncremental>
-    <TargetName>libzstd_static</TargetName>
    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs\legacy;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(SolutionDir)..\..\lib\dictBuilder;$(UniversalCRT_IncludePath);</IncludePath>
    <RunCodeAnalysis>false</RunCodeAnalysis>
  </PropertyGroup>
+  <ItemDefinitionGroup>
+    <ClCompile>
+      <ProgramDataBaseFileName>$(OutDir)$(TargetName).pdb</ProgramDataBaseFileName>
+    </ClCompile>
+  </ItemDefinitionGroup>
  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
    <ClCompile>
      <PrecompiledHeader>
      </PrecompiledHeader>
      <WarningLevel>Level4</WarningLevel>
      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>ZSTD_DLL_EXPORT=1;ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <MinimalRebuild>true</MinimalRebuild>
      <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
      <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
@@ -182,7 +182,7 @@
      </PrecompiledHeader>
      <WarningLevel>Level4</WarningLevel>
      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>ZSTD_DLL_EXPORT=1;ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <TreatWarningAsError>true</TreatWarningAsError>
      <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
      <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
@@ -202,11 +202,10 @@
      <Optimization>MaxSpeed</Optimization>
      <FunctionLevelLinking>true</FunctionLevelLinking>
      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>ZSTD_DLL_EXPORT=1;ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <EnablePREfast>false</EnablePREfast>
      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
      <DebugInformationFormat>ProgramDatabase</DebugInformationFormat>
-      <AssemblerOutput>All</AssemblerOutput>
    </ClCompile>
    <Link>
      <SubSystem>Console</SubSystem>
@@ -224,14 +223,13 @@
      <Optimization>MaxSpeed</Optimization>
      <FunctionLevelLinking>true</FunctionLevelLinking>
      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>ZSTD_DLL_EXPORT=1;ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>ZSTD_MULTITHREAD=1;ZSTD_LEGACY_SUPPORT=5;WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <TreatWarningAsError>false</TreatWarningAsError>
      <EnablePREfast>false</EnablePREfast>
      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
      <DebugInformationFormat>ProgramDatabase</DebugInformationFormat>
      <WholeProgramOptimization>true</WholeProgramOptimization>
      <OmitFramePointers>true</OmitFramePointers>
-      <AssemblerOutput>All</AssemblerOutput>
    </ClCompile>
    <Link>
      <SubSystem>Console</SubSystem>
@@ -32,6 +32,8 @@
    <ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
    <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@@ -53,6 +55,7 @@
    <ClCompile Include="..\..\..\lib\legacy\zstd_v06.c" />
    <ClCompile Include="..\..\..\lib\legacy\zstd_v07.c" />
    <ClCompile Include="..\..\..\programs\util.c" />
+    <ClCompile Include="..\..\..\programs\timefn.c" />
    <ClCompile Include="..\..\..\programs\benchfn.c" />
    <ClCompile Include="..\..\..\programs\benchzstd.c" />
    <ClCompile Include="..\..\..\programs\datagen.c" />
@@ -74,6 +77,8 @@
    <ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
    <ClInclude Include="..\..\..\lib\common\zstd_errors.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_compress.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_literals.h" />
+    <ClInclude Include="..\..\..\lib\compress\zstd_compress_sequences.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_double_fast.h" />
    <ClInclude Include="..\..\..\lib\compress\zstd_lazy.h" />
@@ -7,17 +7,57 @@
 # in the COPYING file in the root directory of this source tree).
 # ################################################################

-cmake_minimum_required(VERSION 2.8.9)
-
-project(zstd)
-set(ZSTD_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../..")
-
-if (NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
-  message(STATUS "No build type selected, defaulting to Release")
-  set(CMAKE_BUILD_TYPE "Release")
+cmake_minimum_required(VERSION 2.8.9 FATAL_ERROR)
+  
+# As of 2018-12-26 ZSTD has been validated to build with cmake version 3.13.2 new policies. 
+# Set and use the newest cmake policies that are validated to work 
+set(ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION "3") 
+set(ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION "13") #Policies never changed at PATCH level
+if("${CMAKE_MAJOR_VERSION}" LESS 3)
+  set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}") 
+elseif( "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}" EQUAL "${CMAKE_MAJOR_VERSION}" AND 
+        "${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}" GREATER "${CMAKE_MINOR_VERSION}")
+    set(ZSTD_CMAKE_POLICY_VERSION "${CMAKE_VERSION}") 
+else() 
+    set(ZSTD_CMAKE_POLICY_VERSION "${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}.${ZSTD_MAX_VALIDATED_CMAKE_MINOR_VERSION}.0") 
 endif()
+cmake_policy(VERSION ${ZSTD_CMAKE_POLICY_VERSION})

 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMakeModules")
+set(ZSTD_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../..")
+set(LIBRARY_DIR ${ZSTD_SOURCE_DIR}/lib)
+# Parse version
+include(GetZstdLibraryVersion)
+GetZstdLibraryVersion(${LIBRARY_DIR}/zstd.h zstd_VERSION_MAJOR zstd_VERSION_MINOR zstd_VERSION_PATCH)
+
+if( CMAKE_MAJOR_VERSION LESS 3 )
+  ## Provide cmake 3+ behavior for older versions of cmake
+  project(zstd)
+  set(PROJECT_VERSION_MAJOR ${zstd_VERSION_MAJOR})
+  set(PROJECT_VERSION_MINOR ${zstd_VERSION_MINOR})
+  set(PROJECT_VERSION_PATCH ${zstd_VERSION_PATCH})
+  set(PROJECT_VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
+  enable_language(C)   # Main library is in C
+  enable_language(CXX) # Testing contributed code also utilizes CXX
+else()
+  project(zstd
+    VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}"
+    LANGUAGES C   # Main library is in C
+              CXX # Testing contributed code also utilizes CXX
+    )
+endif()
+message(STATUS "ZSTD VERSION: ${zstd_VERSION}")
+set(zstd_HOMEPAGE_URL "http://www.zstd.net")
+set(zstd_DESCRIPTION  "Zstandard is a real-time compression algorithm, providing high compression ratios.")
+
+# Set a default build type if none was specified
+if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
+  message(STATUS "Setting build type to 'Release' as none was specified.")
+  set(CMAKE_BUILD_TYPE Release CACHE STRING "Choose the type of build." FORCE)
+  # Set the possible values of build type for cmake-gui
+  set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
+endif()
+
 include(GNUInstallDirs)

 #-----------------------------------------------------------------------------
@@ -50,9 +50,11 @@ macro(ADD_ZSTD_COMPILATION_FLAGS)
             CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO
             CMAKE_CXX_FLAGS CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE
             CMAKE_CXX_FLAGS_MINSIZEREL CMAKE_CXX_FLAGS_RELWITHDEBINFO)
-        separate_arguments(${flag_var})
-        list(REMOVE_DUPLICATES ${flag_var})
-        string(REPLACE ";" " " ${flag_var} "${${flag_var}}")
+        if( ${flag_var} )
+            separate_arguments(${flag_var})
+            list(REMOVE_DUPLICATES ${flag_var})
+            string(REPLACE ";" " " ${flag_var} "${${flag_var}}")
+        endif()
    endforeach ()

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

@@ -0,0 +1,49 @@
+# Find LibLZ4
+#
+# Find LibLZ4 headers and library
+#
+#   Result Variables
+#
+#   LIBLZ4_FOUND             - True if lz4 is found
+#   LIBLZ4_INCLUDE_DIRS      - lz4 headers directories
+#   LIBLZ4_LIBRARIES         - lz4 libraries
+#   LIBLZ4_VERSION_MAJOR     - The major version of lz4
+#   LIBLZ4_VERSION_MINOR     - The minor version of lz4
+#   LIBLZ4_VERSION_RELEASE   - The release version of lz4
+#   LIBLZ4_VERSION_STRING    - version number string (e.g. 1.8.3)
+#
+#   Hints
+#
+#   Set ``LZ4_ROOT_DIR`` to the directory of lz4.h and lz4 library
+
+set(_LIBLZ4_ROOT_HINTS
+    ENV LZ4_ROOT_DIR)
+
+find_path(  LIBLZ4_INCLUDE_DIR lz4.h
+            HINTS ${_LIBLZ4_ROOT_HINTS})
+find_library(   LIBLZ4_LIBRARY NAMES lz4 liblz4 liblz4_static
+                HINTS ${_LIBLZ4_ROOT_HINTS})
+
+if(LIBLZ4_INCLUDE_DIR)
+    file(STRINGS "${LIBLZ4_INCLUDE_DIR}/lz4.h" LIBLZ4_HEADER_CONTENT REGEX "#define LZ4_VERSION_[A-Z]+ +[0-9]+")
+
+    string(REGEX REPLACE ".*#define LZ4_VERSION_MAJOR +([0-9]+).*" "\\1" LIBLZ4_VERSION_MAJOR "${LIBLZ4_HEADER_CONTENT}")
+    string(REGEX REPLACE ".*#define LZ4_VERSION_MINOR +([0-9]+).*" "\\1" LIBLZ4_VERSION_MINOR "${LIBLZ4_HEADER_CONTENT}")
+    string(REGEX REPLACE ".*#define LZ4_VERSION_RELEASE +([0-9]+).*" "\\1" LIBLZ4_VERSION_RELEASE "${LIBLZ4_HEADER_CONTENT}")
+
+    set(LIBLZ4_VERSION_STRING "${LIBLZ4_VERSION_MAJOR}.${LIBLZ4_VERSION_MINOR}.${LIBLZ4_VERSION_RELEASE}")
+    unset(LIBLZ4_HEADER_CONTENT)
+endif()
+
+include(FindPackageHandleStandardArgs)
+FIND_PACKAGE_HANDLE_STANDARD_ARGS(LibLZ4    REQUIRED_VARS   LIBLZ4_INCLUDE_DIR
+                                                            LIBLZ4_LIBRARY
+                                            VERSION_VAR     LIBLZ4_VERSION_STRING
+                                            FAIL_MESSAGE    "Could NOT find LZ4, try to set the paths to lz4.h and lz4 library in environment variable LZ4_ROOT_DIR")
+
+if (LIBLZ4_FOUND)
+    set(LIBLZ4_LIBRARIES ${LIBLZ4_LIBRARY})
+    set(LIBLZ4_INCLUDE_DIRS ${LIBLZ4_INCLUDE_DIR})
+endif ()
+
+mark_as_advanced( LIBLZ4_INCLUDE_DIR LIBLZ4_LIBRARY )
@@ -1,9 +1,10 @@
-function(GetZstdLibraryVersion _header _major _minor _release)
+function(GetZstdLibraryVersion _header _major _minor _patch)
    # Read file content
    file(READ ${_header} CONTENT)

    string(REGEX MATCH ".*define ZSTD_VERSION_MAJOR *([0-9]+).*define ZSTD_VERSION_MINOR *([0-9]+).*define ZSTD_VERSION_RELEASE *([0-9]+)" VERSION_REGEX "${CONTENT}")
    set(${_major} ${CMAKE_MATCH_1} PARENT_SCOPE)
    set(${_minor} ${CMAKE_MATCH_2} PARENT_SCOPE)
-    set(${_release} ${CMAKE_MATCH_3} PARENT_SCOPE)
+    set(${_patch} ${CMAKE_MATCH_3} PARENT_SCOPE)
 endfunction()
+
@@ -3,7 +3,46 @@
 Contributions to the cmake build configurations are welcome. Please
 use case sensitivity that matches modern (ie. cmake version 2.6 and above)
 conventions of using lower-case for commands, and upper-case for
-varibles.
+variables.
+
+# How to build
+
+As cmake doesn't support command like `cmake clean`, it's recommanded to perform a "out of source build".
+To do this, you can create a new directory and build in it:
+```sh
+cd build/cmake
+mkdir builddir
+cd builddir
+cmake ..
+make
+```
+Then you can clean all cmake caches by simpily delete the new directory:
+```sh
+rm -rf build/cmake/builddir
+```
+
+And of course, you can directly build in build/cmake:
+```sh
+cd build/cmake
+cmake
+make
+```
+
+To show cmake build options, you can:
+```sh
+cd build/cmake/builddir
+cmake -LH ..
+```
+
+Bool options can be set to ON/OFF with -D\[option\]=\[ON/OFF\]. You can configure cmake options like this:
+```sh
+cd build/cmake/builddir
+cmake -DZSTD_BUILD_TESTS=ON -DZSTD_LEGACY_SUPPORT=ON ..
+make
+```
+
+## referring
+[Looking for a 'cmake clean' command to clear up CMake output](https://stackoverflow.com/questions/9680420/looking-for-a-cmake-clean-command-to-clear-up-cmake-output)

 # CMake Style Recommendations

@@ -18,70 +18,34 @@ if(NOT ZSTD_BUILD_SHARED AND NOT ZSTD_BUILD_STATIC)
 endif()

 # Define library directory, where sources and header files are located
-set(LIBRARY_DIR ${ZSTD_SOURCE_DIR}/lib)
 include_directories(${LIBRARY_DIR} ${LIBRARY_DIR}/common)

-# Parse version
-include(GetZstdLibraryVersion)
-GetZstdLibraryVersion(${LIBRARY_DIR}/zstd.h LIBVER_MAJOR LIBVER_MINOR LIBVER_RELEASE)
-message(STATUS "ZSTD VERSION ${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE}")
+file(GLOB CommonSources ${LIBRARY_DIR}/common/*.c)
+file(GLOB CompressSources ${LIBRARY_DIR}/compress/*.c)
+file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c)
+file(GLOB DictBuilderSources ${LIBRARY_DIR}/dictBuilder/*.c)
+file(GLOB DeprecatedSources ${LIBRARY_DIR}/deprecated/*.c)

 set(Sources
-        ${LIBRARY_DIR}/common/entropy_common.c
-        ${LIBRARY_DIR}/common/fse_decompress.c
-        ${LIBRARY_DIR}/common/threading.c
-        ${LIBRARY_DIR}/common/pool.c
-        ${LIBRARY_DIR}/common/zstd_common.c
-        ${LIBRARY_DIR}/common/error_private.c
-        ${LIBRARY_DIR}/common/xxhash.c
-        ${LIBRARY_DIR}/compress/hist.c
-        ${LIBRARY_DIR}/compress/fse_compress.c
-        ${LIBRARY_DIR}/compress/huf_compress.c
-        ${LIBRARY_DIR}/compress/zstd_compress.c
-        ${LIBRARY_DIR}/compress/zstdmt_compress.c
-        ${LIBRARY_DIR}/compress/zstd_fast.c
-        ${LIBRARY_DIR}/compress/zstd_double_fast.c
-        ${LIBRARY_DIR}/compress/zstd_lazy.c
-        ${LIBRARY_DIR}/compress/zstd_opt.c
-        ${LIBRARY_DIR}/compress/zstd_ldm.c
-        ${LIBRARY_DIR}/decompress/huf_decompress.c
-        ${LIBRARY_DIR}/decompress/zstd_decompress.c
-        ${LIBRARY_DIR}/decompress/zstd_decompress_block.c
-        ${LIBRARY_DIR}/decompress/zstd_ddict.c
-        ${LIBRARY_DIR}/dictBuilder/cover.c
-        ${LIBRARY_DIR}/dictBuilder/fastcover.c
-        ${LIBRARY_DIR}/dictBuilder/divsufsort.c
-        ${LIBRARY_DIR}/dictBuilder/zdict.c
-        ${LIBRARY_DIR}/deprecated/zbuff_common.c
-        ${LIBRARY_DIR}/deprecated/zbuff_compress.c
-        ${LIBRARY_DIR}/deprecated/zbuff_decompress.c)
+        ${CommonSources}
+        ${CompressSources}
+        ${DecompressSources}
+        ${DictBuilderSources}
+        ${DeprecatedSources})
+
+file(GLOB CommonHeaders ${LIBRARY_DIR}/common/*.h)
+file(GLOB CompressHeaders ${LIBRARY_DIR}/compress/*.h)
+file(GLOB DecompressHeaders ${LIBRARY_DIR}/decompress/*.h)
+file(GLOB DictBuilderHeaders ${LIBRARY_DIR}/dictBuilder/*.h)
+file(GLOB DeprecatedHeaders ${LIBRARY_DIR}/deprecated/*.h)

 set(Headers
        ${LIBRARY_DIR}/zstd.h
-        ${LIBRARY_DIR}/common/debug.h
-        ${LIBRARY_DIR}/common/pool.h
-        ${LIBRARY_DIR}/common/threading.h
-        ${LIBRARY_DIR}/common/bitstream.h
-        ${LIBRARY_DIR}/common/error_private.h
-        ${LIBRARY_DIR}/common/zstd_errors.h
-        ${LIBRARY_DIR}/common/fse.h
-        ${LIBRARY_DIR}/common/huf.h
-        ${LIBRARY_DIR}/common/mem.h
-        ${LIBRARY_DIR}/common/zstd_internal.h
-        ${LIBRARY_DIR}/compress/hist.h
-        ${LIBRARY_DIR}/compress/zstd_compress_internal.h
-        ${LIBRARY_DIR}/compress/zstd_fast.h
-        ${LIBRARY_DIR}/compress/zstd_double_fast.h
-        ${LIBRARY_DIR}/compress/zstd_lazy.h
-        ${LIBRARY_DIR}/compress/zstd_opt.h
-        ${LIBRARY_DIR}/compress/zstd_ldm.h
-        ${LIBRARY_DIR}/compress/zstdmt_compress.h
-        ${LIBRARY_DIR}/decompress/zstd_decompress_internal.h
-        ${LIBRARY_DIR}/decompress/zstd_decompress_block.h
-        ${LIBRARY_DIR}/decompress/zstd_ddict.h
-        ${LIBRARY_DIR}/dictBuilder/zdict.h
-        ${LIBRARY_DIR}/dictBuilder/cover.h
-        ${LIBRARY_DIR}/deprecated/zbuff.h)
+        ${CommonHeaders}
+        ${CompressHeaders}
+        ${DecompressHeaders}
+        ${DictBuilderHeaders}
+        ${DeprecatedHeaders})

 if (ZSTD_LEGACY_SUPPORT)
    set(LIBRARY_LEGACY_DIR ${LIBRARY_DIR}/legacy)
@@ -155,7 +119,8 @@ if (ZSTD_BUILD_SHARED)
            libzstd_shared
            PROPERTIES
            OUTPUT_NAME zstd
-            SOVERSION ${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE})
+            VERSION ${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}
+            SOVERSION ${zstd_VERSION_MAJOR})
 endif ()

 if (ZSTD_BUILD_STATIC)
@@ -170,7 +135,7 @@ if (UNIX)
    set(PREFIX "${CMAKE_INSTALL_PREFIX}")
    set(LIBDIR "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
    set(INCLUDEDIR "${CMAKE_INSTALL_PREFIX}/include")
-    set(VERSION "${LIBVER_MAJOR}.${LIBVER_MINOR}.${LIBVER_RELEASE}")
+    set(VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
    add_custom_target(libzstd.pc ALL
            ${CMAKE_COMMAND} -DIN="${LIBRARY_DIR}/libzstd.pc.in" -DOUT="libzstd.pc"
            -DPREFIX="${PREFIX}" -DLIBDIR="${LIBDIR}" -DINCLUDEDIR="${INCLUDEDIR}" -DVERSION="${VERSION}"
@@ -199,10 +164,12 @@ if (ZSTD_BUILD_STATIC)
 endif ()

 # uninstall target
-configure_file(
-        "${CMAKE_CURRENT_SOURCE_DIR}/cmake_uninstall.cmake.in"
-        "${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake"
-        IMMEDIATE @ONLY)
+if (NOT TARGET uninstall)
+    configure_file(
+            "${CMAKE_CURRENT_SOURCE_DIR}/cmake_uninstall.cmake.in"
+            "${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake"
+            IMMEDIATE @ONLY)

-add_custom_target(uninstall
-        COMMAND ${CMAKE_COMMAND} -P ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake)
+    add_custom_target(uninstall
+            COMMAND ${CMAKE_COMMAND} -P ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake)
+endif ()
@@ -26,7 +26,7 @@ if (MSVC)
    set(PlatformDependResources ${MSVC_RESOURCE_DIR}/zstd.rc)
 endif ()

-add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PlatformDependResources})
+add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PlatformDependResources})
 target_link_libraries(zstd libzstd_static)
 if (CMAKE_SYSTEM_NAME MATCHES "(Solaris|SunOS)")
    target_link_libraries(zstd rt)
@@ -38,6 +38,8 @@ if (UNIX)
    add_custom_target(unzstd ALL ${CMAKE_COMMAND} -E create_symlink zstd unzstd DEPENDS zstd COMMENT "Creating unzstd symlink")
    install(FILES ${CMAKE_CURRENT_BINARY_DIR}/zstdcat DESTINATION "bin")
    install(FILES ${CMAKE_CURRENT_BINARY_DIR}/unzstd DESTINATION "bin")
+    install(PROGRAMS ${PROGRAMS_DIR}/zstdgrep DESTINATION "bin")
+    install(PROGRAMS ${PROGRAMS_DIR}/zstdless DESTINATION "bin")

    add_custom_target(zstd.1 ALL
        ${CMAKE_COMMAND} -E copy ${PROGRAMS_DIR}/zstd.1 .
@@ -63,7 +65,7 @@ if (UNIX)
    install(FILES ${CMAKE_CURRENT_BINARY_DIR}/zstdgrep.1 DESTINATION "${MAN_INSTALL_DIR}")
    install(FILES ${CMAKE_CURRENT_BINARY_DIR}/zstdless.1 DESTINATION "${MAN_INSTALL_DIR}")

-    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/fileio.c)
+    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c)
    target_link_libraries(zstd-frugal libzstd_static)
    set_property(TARGET zstd-frugal APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_NOBENCH;ZSTD_NODICT")
 endif ()
@@ -83,7 +85,9 @@ endif ()

 option(ZSTD_ZLIB_SUPPORT "ZLIB SUPPORT" OFF)
 option(ZSTD_LZMA_SUPPORT "LZMA SUPPORT" OFF)
+option(ZSTD_LZ4_SUPPORT "LZ4 SUPPORT" OFF)

+# Add gzip support
 if (ZSTD_ZLIB_SUPPORT)
    find_package(ZLIB REQUIRED)

@@ -96,6 +100,7 @@ if (ZSTD_ZLIB_SUPPORT)
    endif ()
 endif ()

+# Add lzma support
 if (ZSTD_LZMA_SUPPORT)
    find_package(LibLZMA REQUIRED)

@@ -107,3 +112,16 @@ if (ZSTD_LZMA_SUPPORT)
        message(SEND_ERROR "lzma library is missing")
    endif ()
 endif ()
+
+# Add lz4 support
+if (ZSTD_LZ4_SUPPORT)
+    find_package(LibLZ4 REQUIRED)
+
+    if (LIBLZ4_FOUND)
+        include_directories(${LIBLZ4_INCLUDE_DIRS})
+        target_link_libraries(zstd ${LIBLZ4_LIBRARIES})
+        set_property(TARGET zstd APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_LZ4COMPRESS;ZSTD_LZ4DECOMPRESS")
+    else ()
+        message(SEND_ERROR "lz4 library is missing")
+    endif ()
+endif ()
@@ -43,13 +43,13 @@ include_directories(${TESTS_DIR} ${PROGRAMS_DIR} ${LIBRARY_DIR} ${LIBRARY_DIR}/c
 add_executable(datagen ${PROGRAMS_DIR}/datagen.c ${TESTS_DIR}/datagencli.c)
 target_link_libraries(datagen libzstd_static)

-add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
+add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
 target_link_libraries(fullbench libzstd_static)

-add_executable(fuzzer ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${TESTS_DIR}/fuzzer.c)
+add_executable(fuzzer ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/fuzzer.c)
 target_link_libraries(fuzzer libzstd_static)

 if (UNIX)
-    add_executable(paramgrill ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${TESTS_DIR}/paramgrill.c)
+    add_executable(paramgrill ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/paramgrill.c)
    target_link_libraries(paramgrill libzstd_static m) #m is math library
 endif ()
@@ -7,7 +7,7 @@ modern software development tools and practices, such as unit tests,
 coverage reports, Valgrind, CCache and the like.

 This Meson build system is provided with no guarantee and maintained
-by Dima Krasner <dima@dimakrasner.com>.
+by Dima Krasner \<dima@dimakrasner.com\>.

 It outputs one `libzstd`, either shared or static, depending on
 `default_library` option.
@@ -17,7 +17,7 @@ It outputs one `libzstd`, either shared or static, depending on
 `cd` to this meson directory (`build/meson`)

 ```sh
-meson --buildtype=release -D with-contrib=true -D with-tests=true -D with-contrib=true builddir
+meson setup -Dbin_programs=true -Dbin_contrib=true builddir
 cd builddir
 ninja             # to build
 ninja install     # to install
@@ -17,6 +17,7 @@ gen_html_includes = include_directories(join_paths(zstd_rootdir, 'programs'),
 gen_html = executable('gen_html',
  join_paths(zstd_rootdir, 'contrib/gen_html/gen_html.cpp'),
  include_directories: gen_html_includes,
+  native: true,
  install: false)

 # Update zstd manual
@@ -28,6 +28,8 @@ libzstd_sources = [join_paths(zstd_rootdir, 'lib/common/entropy_common.c'),
  join_paths(zstd_rootdir, 'lib/compress/fse_compress.c'),
  join_paths(zstd_rootdir, 'lib/compress/huf_compress.c'),
  join_paths(zstd_rootdir, 'lib/compress/zstd_compress.c'),
+  join_paths(zstd_rootdir, 'lib/compress/zstd_compress_literals.c'),
+  join_paths(zstd_rootdir, 'lib/compress/zstd_compress_sequences.c'),
  join_paths(zstd_rootdir, 'lib/compress/zstdmt_compress.c'),
  join_paths(zstd_rootdir, 'lib/compress/zstd_fast.c'),
  join_paths(zstd_rootdir, 'lib/compress/zstd_double_fast.c'),
@@ -98,7 +100,7 @@ if use_debug
  if cc_id == compiler_gcc or cc_id == compiler_clang
    libzstd_debug_cflags = ['-Wstrict-aliasing=1', '-Wswitch-enum',
      '-Wdeclaration-after-statement', '-Wstrict-prototypes',
-      '-Wundef', '-Wpointer-arith', '-Wformat-security', '-Wvla',
+      '-Wundef', '-Wpointer-arith', '-Wvla',
      '-Wformat=2', '-Winit-self', '-Wfloat-equal', '-Wwrite-strings',
      '-Wredundant-decls', '-Wmissing-prototypes', '-Wc++-compat']
  endif
@@ -116,9 +118,9 @@ libzstd = library('zstd',
 libzstd_dep = declare_dependency(link_with: libzstd,
  include_directories: libzstd_includes)

-pkgconfig.generate(name: 'libzstd',
+pkgconfig.generate(libzstd,
+  name: 'libzstd',
  filebase: 'libzstd',
-  libraries: [libzstd],
  description: 'fast lossless compression algorithm library',
  version: zstd_libversion,
  url: 'http://www.zstd.net/')
@@ -11,10 +11,12 @@
 project('zstd',
  ['c', 'cpp'],
  license: ['BSD', 'GPLv2'],
-  default_options : ['c_std=c99',
+  default_options : [
+    'c_std=gnu99',
    'cpp_std=c++11',
-    'buildtype=release'],
-  version: '1.3.8',
+    'buildtype=release'
+  ],
+  version: 'DUMMY',
  meson_version: '>=0.47.0')

 cc = meson.get_compiler('c')
@@ -41,13 +43,10 @@ zstd_h_file = join_paths(meson.current_source_dir(), '../../lib/zstd.h')
 GetZstdLibraryVersion_py = files('GetZstdLibraryVersion.py')
 r = run_command(python3, GetZstdLibraryVersion_py, zstd_h_file)
 if r.returncode() == 0
-  output = r.stdout().strip()
-  if output.version_compare('>@0@'.format(zstd_version))
-    zstd_version = output
-    message('Project version is now: @0@'.format(zstd_version))
-  endif
+  zstd_version = r.stdout().strip()
+  message('Project version is now: @0@'.format(zstd_version))
 else
-  message('Cannot find project version in @0@'.format(zstd_h_file))
+  error('Cannot find project version in @0@'.format(zstd_h_file))
 endif

 zstd_libversion = zstd_version
@@ -76,9 +75,9 @@ legacy_level = get_option('legacy_level')
 use_backtrace = get_option('backtrace')
 use_static_runtime = get_option('static_runtime')

-build_programs = get_option('build_programs')
-build_contrib = get_option('build_contrib')
-build_tests = get_option('build_tests')
+bin_programs = get_option('bin_programs')
+bin_contrib = get_option('bin_contrib')
+bin_tests = get_option('bin_tests')

 feature_multi_thread = get_option('multi_thread')
 feature_zlib = get_option('zlib')
@@ -89,7 +88,7 @@ feature_lz4 = get_option('lz4')
 # Dependencies
 # =============================================================================

-libm_dep = cc.find_library('m', required: build_tests)
+libm_dep = cc.find_library('m', required: bin_tests)
 thread_dep = dependency('threads', required: feature_multi_thread)
 use_multi_thread = thread_dep.found()
 # Arguments in dependency should be equivalent to those passed to pkg-config
@@ -134,14 +133,14 @@ endif

 subdir('lib')

-if build_programs
+if bin_programs
  subdir('programs')
 endif

-if build_tests
+if bin_tests
  subdir('tests')
 endif

-if build_contrib
+if bin_contrib
  subdir('contrib')
 endif
@@ -19,11 +19,11 @@ option('backtrace', type: 'boolean', value: false,
 option('static_runtime', type: 'boolean', value: false,
  description: 'Link to static run-time libraries on MSVC')

-option('build_programs', type: 'boolean', value: true,
+option('bin_programs', type: 'boolean', value: true,
  description: 'Enable programs build')
-option('build_tests', type: 'boolean', value: false,
+option('bin_tests', type: 'boolean', value: false,
  description: 'Enable tests build')
-option('build_contrib', type: 'boolean', value: false,
+option('bin_contrib', type: 'boolean', value: false,
  description: 'Enable contrib build')

 option('multi_thread', type: 'feature', value: 'enabled',
@@ -12,6 +12,7 @@ zstd_rootdir = '../../..'

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

 zstd_frugal_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
  join_paths(zstd_rootdir, 'programs/fileio.c')]

@@ -40,6 +40,7 @@ datagen = executable('datagen',

 fullbench_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'programs/benchfn.c'),
  join_paths(zstd_rootdir, 'programs/benchzstd.c'),
  join_paths(zstd_rootdir, 'tests/fullbench.c')]
@@ -51,6 +52,7 @@ fullbench = executable('fullbench',

 fuzzer_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'tests/fuzzer.c')]
 fuzzer = executable('fuzzer',
  fuzzer_sources,
@@ -60,6 +62,7 @@ fuzzer = executable('fuzzer',

 zbufftest_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'tests/zbufftest.c')]
 zbufftest = executable('zbufftest',
  zbufftest_sources,
@@ -70,6 +73,7 @@ zbufftest = executable('zbufftest',

 zstreamtest_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'tests/seqgen.c'),
  join_paths(zstd_rootdir, 'tests/zstreamtest.c')]
 zstreamtest = executable('zstreamtest',
@@ -79,6 +83,7 @@ zstreamtest = executable('zstreamtest',
  install: false)

 paramgrill_sources = [join_paths(zstd_rootdir, 'programs/benchfn.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'programs/benchzstd.c'),
  join_paths(zstd_rootdir, 'programs/datagen.c'),
  join_paths(zstd_rootdir, 'programs/util.c'),
@@ -107,15 +112,18 @@ invalidDictionaries = executable('invalidDictionaries',
  dependencies: [ libzstd_dep ],
  install: false)

-legacy_sources = [join_paths(zstd_rootdir, 'tests/legacy.c')]
-legacy = executable('legacy',
-  legacy_sources,
-  # Use -Dlegacy_level build option to control it
-  #c_args: '-DZSTD_LEGACY_SUPPORT=4',
-  dependencies: [ libzstd_dep ],
-  install: false)
+if 0 < legacy_level and legacy_level <= 4
+  legacy_sources = [join_paths(zstd_rootdir, 'tests/legacy.c')]
+  legacy = executable('legacy',
+    legacy_sources,
+    # Use -Dlegacy_level build option to control it
+    #c_args: '-DZSTD_LEGACY_SUPPORT=4',
+    dependencies: [ libzstd_dep ],
+    install: false)
+endif

 decodecorpus_sources = [join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'tests/decodecorpus.c')]
 decodecorpus = executable('decodecorpus',
  decodecorpus_sources,
@@ -132,6 +140,7 @@ symbols = executable('symbols',
  install: false)

 poolTests_sources = [join_paths(zstd_rootdir, 'programs/util.c'),
+  join_paths(zstd_rootdir, 'programs/timefn.c'),
  join_paths(zstd_rootdir, 'tests/poolTests.c'),
  join_paths(zstd_rootdir, 'lib/common/pool.c'),
  join_paths(zstd_rootdir, 'lib/common/threading.c'),
@@ -170,7 +179,8 @@ if host_machine_os != os_windows
    args: ZSTDRTTEST,
    env: ['ZSTD=' + zstd.full_path()],
    depends: [datagen],
-    timeout: 600) # Timeout should work on HDD drive
+    workdir: meson.current_build_dir(),
+    timeout: 2800) # Timeout should work on HDD drive
 endif

 test('test-fullbench-1',
@@ -188,7 +198,7 @@ if use_zlib
  test('test-fuzzer',
    fuzzer,
    args: ['-v', FUZZERTEST] + FUZZER_FLAGS,
-    timeout: 240)
+    timeout: 480)
 endif

 test('test-zbuff',
@@ -198,7 +208,7 @@ test('test-zbuff',
 test('test-zstream-1',
  zstreamtest,
  args: ['-v', ZSTREAM_TESTTIME] + FUZZER_FLAGS,
-  timeout: 120)
+  timeout: 240)
 test('test-zstream-2',
  zstreamtest,
  args: ['-mt', '-t1', ZSTREAM_TESTTIME] + FUZZER_FLAGS,
@@ -210,7 +220,9 @@ test('test-zstream-3',
 test('test-longmatch', longmatch, timeout: 36)
 test('test-invalidDictionaries', invalidDictionaries) # should be fast
 test('test-symbols', symbols) # should be fast
-test('test-legacy', legacy) # should be fast
+if 0 < legacy_level and legacy_level <= 4
+  test('test-legacy', legacy) # should be fast
+endif
 test('test-decodecorpus',
  decodecorpus,
  args: ['-t', DECODECORPUS_TESTTIME],
@@ -13,7 +13,7 @@ CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
 CFLAGS   ?= -O3
 CFLAGS   += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow                 \
            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-            -Wstrict-prototypes -Wundef -Wformat-security                   \
+            -Wstrict-prototypes -Wundef                                     \
            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings      \
            -Wredundant-decls
 CFLAGS   += $(DEBUGFLAGS)
@@ -22,10 +22,10 @@ FLAGS     = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) $(MULTITHREAD_LDFLAGS)

 all: adapt datagen

-adapt: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
+adapt: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
 	$(CC) $(FLAGS) $^ -o $@

-adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
+adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
 	$(CC) $(FLAGS) -DDEBUG_MODE=2 $^ -o adapt

 datagen : $(PRGDIR)/datagen.c datagencli.c
@@ -13,6 +13,7 @@
 #include <string.h>     /* memset */
 #include "zstd_internal.h"
 #include "util.h"
+#include "timefn.h"     /* UTIL_time_t, UTIL_getTime, UTIL_getSpanTimeMicro */

 #define DISPLAY(...) fprintf(stderr, __VA_ARGS__)
 #define PRINT(...) fprintf(stdout, __VA_ARGS__)
@@ -5,7 +5,7 @@ The `Dockerfile` script requires a version of `docker` >= 17.05

 ## Installing docker

-The officiel docker install docs use a ppa with a modern version available:
+The official docker install docs use a ppa with a modern version available:
 https://docs.docker.com/install/linux/docker-ce/ubuntu/

 ## How to run
@@ -127,7 +127,7 @@ dictInfo* createDictFromFiles(sampleInfo *info, unsigned maxDictSize,


 /** compressWithDict() :
- *  Compress samples from sample buffer given dicionary stored on dictionary buffer and compression level
+ *  Compress samples from sample buffer given dictionary stored on dictionary buffer and compression level
 *  @return compression ratio
 */
 double compressWithDict(sampleInfo *srcInfo, dictInfo* dInfo, int compressionLevel, int displayLevel) {
@@ -194,7 +194,7 @@ double compressWithDict(sampleInfo *srcInfo, dictInfo* dInfo, int compressionLev
    totalCompressedSize += compressedSize;
  }

-  /* Sum orignal sizes */
+  /* Sum original sizes */
  for (i = 0; i<srcInfo->nbSamples; i++) {
    totalOriginalSize += srcInfo->samplesSizes[i];
  }
@@ -125,7 +125,7 @@ typedef struct {
 *
 *     Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
 *
- * Once the dmer with hash value d is in the dictionay we set F(d) = F(d)/2.
+ * Once the dmer with hash value d is in the dictionary we set F(d) = F(d)/2.
 */
 static FASTCOVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
                                                  U32 *freqs, U32 begin,U32 end,
@@ -149,7 +149,7 @@ static FASTCOVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
    while (activeSegment.end < end) {
      /* Get hash value of current dmer */
      const size_t index = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, parameters.f, ctx->d);
-      /* Add frequency of this index to score if this is the first occurence of index in active segment */
+      /* Add frequency of this index to score if this is the first occurrence of index in active segment */
      if (ctx->segmentFreqs[index] == 0) {
        activeSegment.score += freqs[index];
      }
@@ -18,7 +18,7 @@ CFLAGS  ?= -O3
 CFLAGS  += -std=gnu99
 DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
            -Wstrict-aliasing=1 -Wswitch-enum \
-            -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
+            -Wstrict-prototypes -Wundef -Wpointer-arith \
            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
            -Wredundant-decls
 CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
@@ -28,14 +28,17 @@ default: largeNbDicts

 all : largeNbDicts

-largeNbDicts: util.o benchfn.o datagen.o xxhash.o largeNbDicts.c $(LIBZSTD)
+largeNbDicts: util.o timefn.o benchfn.o datagen.o xxhash.o largeNbDicts.c $(LIBZSTD)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@

 .PHONY: $(LIBZSTD)
 $(LIBZSTD):
 	$(MAKE) -C $(LIBDIR) libzstd.a CFLAGS="$(CFLAGS)"

-benchfn.o  : $(PROGDIR)/benchfn.c
+benchfn.o: $(PROGDIR)/benchfn.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c
+
+timefn.o: $(PROGDIR)/timefn.c
 	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c

 datagen.o: $(PROGDIR)/datagen.c
@@ -48,6 +51,7 @@ util.o: $(PROGDIR)/util.c
 xxhash.o : $(LIBDIR)/common/xxhash.c
 	$(CC) $(CPPFLAGS) $(CFLAGS) $^ -c

+
 clean:
 	$(RM) *.o
 	$(MAKE) -C $(LIBDIR) clean > /dev/null
@@ -424,7 +424,7 @@ static ddict_collection_t createDDictCollection(const void* dictBuffer, size_t d
 }


-/* mess with adresses, so that linear scanning dictionaries != linear address scanning */
+/* mess with addresses, so that linear scanning dictionaries != linear address scanning */
 void shuffleDictionaries(ddict_collection_t dicts)
 {
    size_t const nbDicts = dicts.nbDDict;
@@ -559,7 +559,7 @@ static int benchMem(slice_collection_t dstBlocks,
        CONTROL(BMK_isSuccessful_runOutcome(outcome));

        BMK_runTime_t const result = BMK_extract_runTime(outcome);
-        U64 const dTime_ns = result.nanoSecPerRun;
+        double const dTime_ns = result.nanoSecPerRun;
        double const dTime_sec = (double)dTime_ns / 1000000000;
        size_t const srcSize = result.sumOfReturn;
        double const dSpeed_MBps = (double)srcSize / dTime_sec / (1 MB);
@@ -4,7 +4,7 @@ Date: Mon, 17 Jul 2017 17:08:19 -0700
 Subject: [PATCH v5 2/5] lib: Add zstd modules

 Add zstd compression and decompression kernel modules.
-zstd offers a wide varity of compression speed and quality trade-offs.
+zstd offers a wide variety of compression speed and quality trade-offs.
 It can compress at speeds approaching lz4, and quality approaching lzma.
 zstd decompressions at speeds more than twice as fast as zlib, and
 decompression speed remains roughly the same across all compression levels.
@@ -21,7 +21,7 @@ will be easier to keep the kernel zstd up to date.
 I benchmarked zstd compression as a special character device. I ran zstd
 and zlib compression at several levels, as well as performing no
 compression, which measure the time spent copying the data to kernel space.
-Data is passed to the compresser 4096 B at a time. The benchmark file is
+Data is passed to the compressor 4096 B at a time. The benchmark file is
 located in the upstream zstd source repository under
 `contrib/linux-kernel/zstd_compress_test.c` [2].

@@ -86,7 +86,7 @@ Tested in userland using the test-suite in the zstd repo under
 `contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel
 functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under
 `contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8]
-with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the
+with ASAN, UBSAN, and MSAN. Additionally, it was tested while testing the
 BtrFS and SquashFS patches coming next.

 [1] https://clang.llvm.org/docs/ClangFormat.html
@@ -4200,14 +4200,14 @@ index 0000000..ff18ae6
 +	BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
 +	U32 const fcsCode =
 +	    params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
-+	BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
+	BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
 +	size_t pos;
 +
 +	if (dstCapacity < ZSTD_frameHeaderSize_max)
 +		return ERROR(dstSize_tooSmall);
 +
 +	ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
-+	op[4] = frameHeaderDecriptionByte;
+	op[4] = frameHeaderDescriptionByte;
 +	pos = 5;
 +	if (!singleSegment)
 +		op[pos++] = windowLogByte;
@@ -8812,8 +8812,8 @@ index 0000000..ef3d174
 +		U32 position = 0;
 +		U32 symbol;
 +		for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
-+			int nbOccurences;
-+			for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
+			int nbOccurrences;
+			for (nbOccurrences = 0; nbOccurrences < normalizedCounter[symbol]; nbOccurrences++) {
 +				tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
 +				position = (position + step) & tableMask;
 +				while (position > highThreshold)
@@ -9944,7 +9944,7 @@ index 0000000..2143da2
 +	HUF_repeat_none,  /**< Cannot use the previous table */
 +	HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
 +			     4}X_repeat */
-+	HUF_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
+	HUF_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
 +} HUF_repeat;
 +/** HUF_compress4X_repeat() :
 +*   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
@@ -11,7 +11,7 @@ Signed-off-by: Nick Terrell <terrelln@fb.com>
 ---
 v4 -> v5:
 - Fix patch documentation to reflect that Sean Purcell is the author
- Don't strip trailing whitespace of unreleated code
+- Don't strip trailing whitespace of unrelated code
 - Make zstd_display_options() static

 v5 -> v6:
@@ -224,7 +224,7 @@ index 0000000..dcab75a
 + * set the default options, this is to ensure any user supplied
 + * -X options on the appending mksquashfs command line are over-ridden.
 + *
-+ * This function returns 0 on sucessful extraction of options, and -1 on error.
+ * This function returns 0 on successful extraction of options, and -1 on error.
 + */
 +static int zstd_extract_options(int block_size, void *buffer, int size)
 +{
@@ -2436,14 +2436,14 @@ static size_t ZSTD_writeFrameHeader(void *dst, size_t dstCapacity, ZSTD_paramete
 	BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
 	U32 const fcsCode =
 	    params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
-	BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
+	BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
 	size_t pos;

 	if (dstCapacity < ZSTD_frameHeaderSize_max)
 		return ERROR(dstSize_tooSmall);

 	ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
-	op[4] = frameHeaderDecriptionByte;
+	op[4] = frameHeaderDescriptionByte;
 	pos = 5;
 	if (!singleSegment)
 		op[pos++] = windowLogByte;
@@ -141,8 +141,8 @@ size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsi
 		U32 position = 0;
 		U32 symbol;
 		for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
-			int nbOccurences;
-			for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
+			int nbOccurrences;
+			for (nbOccurrences = 0; nbOccurrences < normalizedCounter[symbol]; nbOccurrences++) {
 				tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
 				position = (position + step) & tableMask;
 				while (position > highThreshold)
@@ -134,7 +134,7 @@ typedef enum {
 	HUF_repeat_none,  /**< Cannot use the previous table */
 	HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
 			     4}X_repeat */
-	HUF_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
+	HUF_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
 } HUF_repeat;
 /** HUF_compress4X_repeat() :
 *   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
@@ -1,5 +1,5 @@
-#ifndef LINUX_COMIPLER_H_
-#define LINUX_COMIPLER_H_
+#ifndef LINUX_COMPILER_H_
+#define LINUX_COMPILER_H_

 #ifndef __always_inline
 #  define __always_inline inline
@@ -9,4 +9,4 @@
 #  define noinline __attribute__((__noinline__))
 #endif

-#endif // LINUX_COMIPLER_H_
+#endif // LINUX_COMPILER_H_
@@ -190,13 +190,15 @@ $(ZSTDDIR)/libzstd.a: $(ZSTD_FILES)
 	CFLAGS="$(ALL_CFLAGS)" LDFLAGS="$(ALL_LDFLAGS)" $(MAKE) -C $(ZSTDDIR) libzstd.a

 # Rules to build the tests
-test/RoundTripTest$(EXT): test/RoundTripTest.o $(PROGDIR)/datagen.o Options.o \
+test/RoundTripTest$(EXT): test/RoundTripTest.o $(PROGDIR)/datagen.o \
+                          $(PROGDIR)/util.o Options.o \
                          Pzstd.o SkippableFrame.o $(ZSTDDIR)/libzstd.a
 	$(LD_COMMAND)

 test/%Test$(EXT): PZSTD_LDFLAGS += $(GTEST_LIB)
 test/%Test$(EXT): LIBS += -lgtest -lgtest_main
-test/%Test$(EXT): test/%Test.o $(PROGDIR)/datagen.o Options.o Pzstd.o  \
+test/%Test$(EXT): test/%Test.o $(PROGDIR)/datagen.o \
+                  $(PROGDIR)/util.o Options.o Pzstd.o \
                  SkippableFrame.o $(ZSTDDIR)/libzstd.a
 	$(LD_COMMAND)

@@ -55,7 +55,7 @@ static std::uint64_t handleOneInput(const Options &options,
                             SharedState& state) {
  auto inputSize = fileSizeOrZero(inputFile);
  // WorkQueue outlives ThreadPool so in the case of error we are certain
-  // we don't accidently try to call push() on it after it is destroyed
+  // we don't accidentally try to call push() on it after it is destroyed
  WorkQueue<std::shared_ptr<BufferWorkQueue>> outs{options.numThreads + 1};
  std::uint64_t bytesRead;
  std::uint64_t bytesWritten;
@@ -9,7 +9,7 @@
 
 /**
 * A subset of `folly/Range.h`.
- * All code copied verbatiam modulo formatting
+ * All code copied verbatim modulo formatting
 */
 #pragma once

@@ -54,7 +54,7 @@ class ResourcePool {

  /**
   * @returns  A unique pointer to a resource.  The resource is null iff
-   *           there are no avaiable resources and `factory()` returns null.
+   *           there are no available resources and `factory()` returns null.
   */
  UniquePtr get() {
    std::lock_guard<std::mutex> lock(mutex_);
@@ -1,4 +1,5 @@
 seekable_compression
 seekable_decompression
+seekable_decompression_mem
 parallel_processing
 parallel_compression
@@ -24,7 +24,8 @@ SEEKABLE_OBJS = ../zstdseek_compress.c ../zstdseek_decompress.c $(ZSTDLIB)

 default: all

-all: seekable_compression seekable_decompression parallel_processing
+all: seekable_compression seekable_decompression seekable_decompression_mem \
+	parallel_processing

 $(ZSTDLIB):
 	make -C $(ZSTDLIB_PATH) $(ZSTDLIB_NAME)
@@ -35,6 +36,9 @@ seekable_compression : seekable_compression.c $(SEEKABLE_OBJS)
 seekable_decompression : seekable_decompression.c $(SEEKABLE_OBJS)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@

+seekable_decompression_mem : seekable_decompression_mem.c $(SEEKABLE_OBJS)
+	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
 parallel_processing : parallel_processing.c $(SEEKABLE_OBJS)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@ -pthread

@@ -44,5 +48,6 @@ parallel_compression : parallel_compression.c $(SEEKABLE_OBJS)
 clean:
 	@rm -f core *.o tmp* result* *.zst \
 		seekable_compression seekable_decompression \
+		seekable_decompression_mem \
 		parallel_processing parallel_compression
 	@echo Cleaning completed
@@ -0,0 +1,144 @@
+/*
+ * Copyright (c) 2017-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ */
+
+
+#include <stdlib.h>    // malloc, exit
+#include <stdio.h>     // fprintf, perror, feof
+#include <string.h>    // strerror
+#include <errno.h>     // errno
+#define ZSTD_STATIC_LINKING_ONLY
+#include <zstd.h>      // presumes zstd library is installed
+#include <zstd_errors.h>
+
+#include "zstd_seekable.h"
+
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+
+#define MAX_FILE_SIZE (8 * 1024 * 1024)
+
+static void* malloc_orDie(size_t size)
+{
+    void* const buff = malloc(size);
+    if (buff) return buff;
+    /* error */
+    perror("malloc");
+    exit(1);
+}
+
+static void* realloc_orDie(void* ptr, size_t size)
+{
+    ptr = realloc(ptr, size);
+    if (ptr) return ptr;
+    /* error */
+    perror("realloc");
+    exit(1);
+}
+
+static FILE* fopen_orDie(const char *filename, const char *instruction)
+{
+    FILE* const inFile = fopen(filename, instruction);
+    if (inFile) return inFile;
+    /* error */
+    perror(filename);
+    exit(3);
+}
+
+static size_t fread_orDie(void* buffer, size_t sizeToRead, FILE* file)
+{
+    size_t const readSize = fread(buffer, 1, sizeToRead, file);
+    if (readSize == sizeToRead) return readSize;   /* good */
+    if (feof(file)) return readSize;   /* good, reached end of file */
+    /* error */
+    perror("fread");
+    exit(4);
+}
+
+static size_t fwrite_orDie(const void* buffer, size_t sizeToWrite, FILE* file)
+{
+    size_t const writtenSize = fwrite(buffer, 1, sizeToWrite, file);
+    if (writtenSize == sizeToWrite) return sizeToWrite;   /* good */
+    /* error */
+    perror("fwrite");
+    exit(5);
+}
+
+static size_t fclose_orDie(FILE* file)
+{
+    if (!fclose(file)) return 0;
+    /* error */
+    perror("fclose");
+    exit(6);
+}
+
+static void fseek_orDie(FILE* file, long int offset, int origin) {
+    if (!fseek(file, offset, origin)) {
+        if (!fflush(file)) return;
+    }
+    /* error */
+    perror("fseek");
+    exit(7);
+}
+
+
+static void decompressFile_orDie(const char* fname, off_t startOffset, off_t endOffset)
+{
+    FILE* const fin  = fopen_orDie(fname, "rb");
+    FILE* const fout = stdout;
+    // Just for demo purposes, assume file is <= MAX_FILE_SIZE
+    void*  const buffIn = malloc_orDie(MAX_FILE_SIZE);
+    size_t const inSize = fread_orDie(buffIn, MAX_FILE_SIZE, fin);
+    size_t const buffOutSize = ZSTD_DStreamOutSize();  /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */
+    void*  const buffOut = malloc_orDie(buffOutSize);
+
+    ZSTD_seekable* const seekable = ZSTD_seekable_create();
+    if (seekable==NULL) { fprintf(stderr, "ZSTD_seekable_create() error \n"); exit(10); }
+
+    size_t const initResult = ZSTD_seekable_initBuff(seekable, buffIn, inSize);
+    if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_seekable_init() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
+
+    while (startOffset < endOffset) {
+        size_t const result = ZSTD_seekable_decompress(seekable, buffOut, MIN(endOffset - startOffset, buffOutSize), startOffset);
+
+        if (ZSTD_isError(result)) {
+            fprintf(stderr, "ZSTD_seekable_decompress() error : %s \n",
+                    ZSTD_getErrorName(result));
+            exit(12);
+        }
+        fwrite_orDie(buffOut, result, fout);
+        startOffset += result;
+    }
+
+    ZSTD_seekable_free(seekable);
+    fclose_orDie(fin);
+    fclose_orDie(fout);
+    free(buffIn);
+    free(buffOut);
+}
+
+
+int main(int argc, const char** argv)
+{
+    const char* const exeName = argv[0];
+
+    if (argc!=4) {
+        fprintf(stderr, "wrong arguments\n");
+        fprintf(stderr, "usage:\n");
+        fprintf(stderr, "%s FILE START END\n", exeName);
+        return 1;
+    }
+
+    {
+        const char* const inFilename = argv[1];
+        off_t const startOffset = atoll(argv[2]);
+        off_t const endOffset = atoll(argv[3]);
+        decompressFile_orDie(inFilename, startOffset, endOffset);
+    }
+
+    return 0;
+}
@@ -106,7 +106,7 @@ typedef struct {
 static int ZSTD_seekable_read_buff(void* opaque, void* buffer, size_t n)
 {
    buffWrapper_t* buff = (buffWrapper_t*) opaque;
-    if (buff->size + n > buff->pos) return -1;
+    if (buff->pos + n > buff->size) return -1;
    memcpy(buffer, (const BYTE*)buff->ptr + buff->pos, n);
    buff->pos += n;
    return 0;
@@ -124,7 +124,7 @@ static int ZSTD_seekable_seek_buff(void* opaque, long long offset, int origin)
        newOffset = (unsigned long long)buff->pos + offset;
        break;
    case SEEK_END:
-        newOffset = (unsigned long long)buff->size - offset;
+        newOffset = (unsigned long long)buff->size + offset;
        break;
    default:
        assert(0);  /* not possible */
@@ -12,8 +12,8 @@ __`zstd_compression_format.md`__ : This document defines the Zstandard compressi
 Compliant decoders must adhere to this document,
 and compliant encoders must generate data that follows it.

-Should you look for ressources to develop your own port of Zstandard algorithm,
-you may find the following ressources useful :
+Should you look for resources to develop your own port of Zstandard algorithm,
+you may find the following resources useful :

 __`educational_decoder`__ : This directory contains an implementation of a Zstandard decoder,
 compliant with the Zstandard compression format.
@@ -7,7 +7,7 @@ CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
 CFLAGS   ?= -O3
 CFLAGS   += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow                 \
            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-            -Wstrict-prototypes -Wundef -Wformat-security                   \
+            -Wstrict-prototypes -Wundef                                     \
            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings      \
            -Wredundant-decls
 CFLAGS   += $(DEBUGFLAGS)
@@ -358,7 +358,7 @@ static u32 copy_literals(const size_t seq, istream_t *litstream,
                         ostream_t *const out);

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

@@ -16,7 +16,7 @@ Distribution of this document is unlimited.

 ### Version

-0.3.1 (25/10/18)
+0.3.2 (17/07/19)


 Introduction
@@ -390,9 +390,7 @@ A block can contain any number of bytes (even zero), up to
 -  Window_Size
 -  128 KB

-A `Compressed_Block` has the extra restriction that `Block_Size` is always
-strictly less than the decompressed size.
-If this condition cannot be respected,
+If this condition cannot be respected when generating a `Compressed_Block`,
 the block must be sent uncompressed instead (`Raw_Block`).


@@ -1655,6 +1653,7 @@ or at least provide a meaningful error code explaining for which reason it canno

 Version changes
 ---------------
+- 0.3.2 : remove additional block size restriction on compressed blocks
 - 0.3.1 : minor clarification regarding offset history update rules
 - 0.3.0 : minor edits to match RFC8478
 - 0.2.9 : clarifications for huffman weights direct representation, by Ulrich Kunitz
@@ -1,26 +1,26 @@
 <html>
 <head>
 <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
-<title>zstd 1.3.8 Manual</title>
+<title>zstd 1.4.2 Manual</title>
 </head>
 <body>
-<h1>zstd 1.3.8 Manual</h1>
+<h1>zstd 1.4.2 Manual</h1>
 <hr>
 <a name="Contents"></a><h2>Contents</h2>
 <ol>
 <li><a href="#Chapter1">Introduction</a></li>
 <li><a href="#Chapter2">Version</a></li>
-<li><a href="#Chapter3">Default constant</a></li>
-<li><a href="#Chapter4">Simple API</a></li>
-<li><a href="#Chapter5">Explicit context</a></li>
-<li><a href="#Chapter6">Simple dictionary API</a></li>
-<li><a href="#Chapter7">Bulk processing dictionary API</a></li>
-<li><a href="#Chapter8">Streaming</a></li>
-<li><a href="#Chapter9">Streaming compression - HowTo</a></li>
-<li><a href="#Chapter10">Streaming decompression - HowTo</a></li>
-<li><a href="#Chapter11">ADVANCED AND EXPERIMENTAL FUNCTIONS</a></li>
-<li><a href="#Chapter12">Candidate API for promotion to stable status</a></li>
-<li><a href="#Chapter13">Advanced compression API</a></li>
+<li><a href="#Chapter3">Simple API</a></li>
+<li><a href="#Chapter4">Explicit context</a></li>
+<li><a href="#Chapter5">Advanced compression API</a></li>
+<li><a href="#Chapter6">Advanced decompression API</a></li>
+<li><a href="#Chapter7">Streaming</a></li>
+<li><a href="#Chapter8">Streaming compression - HowTo</a></li>
+<li><a href="#Chapter9">Streaming decompression - HowTo</a></li>
+<li><a href="#Chapter10">Simple dictionary API</a></li>
+<li><a href="#Chapter11">Bulk processing dictionary API</a></li>
+<li><a href="#Chapter12">Dictionary helper functions</a></li>
+<li><a href="#Chapter13">Advanced dictionary and prefix API</a></li>
 <li><a href="#Chapter14">experimental API (static linking only)</a></li>
 <li><a href="#Chapter15">Frame size functions</a></li>
 <li><a href="#Chapter16">Memory management</a></li>
@@ -30,8 +30,7 @@
 <li><a href="#Chapter20">Buffer-less and synchronous inner streaming functions</a></li>
 <li><a href="#Chapter21">Buffer-less streaming compression (synchronous mode)</a></li>
 <li><a href="#Chapter22">Buffer-less streaming decompression (synchronous mode)</a></li>
-<li><a href="#Chapter23">ZSTD_getFrameHeader() :</a></li>
-<li><a href="#Chapter24">Block level API</a></li>
+<li><a href="#Chapter23">Block level API</a></li>
 </ol>
 <hr>
 <a name="Chapter1"></a><h2>Introduction</h2><pre>
@@ -69,9 +68,7 @@

 <pre><b>unsigned ZSTD_versionNumber(void);   </b>/**< to check runtime library version */<b>
 </b></pre><BR>
-<a name="Chapter3"></a><h2>Default constant</h2><pre></pre>
-
-<a name="Chapter4"></a><h2>Simple API</h2><pre></pre>
+<a name="Chapter3"></a><h2>Simple API</h2><pre></pre>

 <pre><b>size_t ZSTD_compress( void* dst, size_t dstCapacity,
                const void* src, size_t srcSize,
@@ -126,18 +123,32 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
 @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. 
 </p></pre><BR>

+<pre><b>size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
+</b><p> `src` should point to the start of a ZSTD frame or skippable frame.
+ `srcSize` must be >= first frame size
+ @return : the compressed size of the first frame starting at `src`,
+           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
+        or an error code if input is invalid 
+</p></pre><BR>
+
 <h3>Helper functions</h3><pre></pre><b><pre>#define ZSTD_COMPRESSBOUND(srcSize)   ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) </b>/* margin, from 64 to 0 */ : 0))  /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */<b>
 size_t      ZSTD_compressBound(size_t srcSize); </b>/*!< maximum compressed size in worst case single-pass scenario */<b>
 unsigned    ZSTD_isError(size_t code);          </b>/*!< tells if a `size_t` function result is an error code */<b>
 const char* ZSTD_getErrorName(size_t code);     </b>/*!< provides readable string from an error code */<b>
+int         ZSTD_minCLevel(void);               </b>/*!< minimum negative compression level allowed */<b>
 int         ZSTD_maxCLevel(void);               </b>/*!< maximum compression level available */<b>
 </pre></b><BR>
-<a name="Chapter5"></a><h2>Explicit context</h2><pre></pre>
+<a name="Chapter4"></a><h2>Explicit context</h2><pre></pre>

 <h3>Compression context</h3><pre>  When compressing many times,
-  it is recommended to allocate a context just once, and re-use it for each successive compression operation.
+  it is recommended to allocate a context just once,
+  and re-use it for each successive compression operation.
  This will make workload friendlier for system's memory.
-  Use one context per thread for parallel execution in multi-threaded environments. 
+  Note : re-using context is just a speed / resource optimization.
+         It doesn't change the compression ratio, which remains identical.
+  Note 2 : In multi-threaded environments,
+         use one different context per thread for parallel execution.
+ 
 </pre><b><pre>typedef struct ZSTD_CCtx_s ZSTD_CCtx;
 ZSTD_CCtx* ZSTD_createCCtx(void);
 size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);
@@ -169,228 +180,7 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);
 
 </p></pre><BR>

-<a name="Chapter6"></a><h2>Simple dictionary API</h2><pre></pre>
-
-<pre><b>size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
-                               void* dst, size_t dstCapacity,
-                         const void* src, size_t srcSize,
-                         const void* dict,size_t dictSize,
-                               int compressionLevel);
-</b><p>  Compression at an explicit compression level using a Dictionary.
-  A dictionary can be any arbitrary data segment (also called a prefix),
-  or a buffer with specified information (see dictBuilder/zdict.h).
-  Note : This function loads the dictionary, resulting in significant startup delay.
-         It's intended for a dictionary used only once.
-  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
-                                 void* dst, size_t dstCapacity,
-                           const void* src, size_t srcSize,
-                           const void* dict,size_t dictSize);
-</b><p>  Decompression using a known Dictionary.
-  Dictionary must be identical to the one used during compression.
-  Note : This function loads the dictionary, resulting in significant startup delay.
-         It's intended for a dictionary used only once.
-  Note : When `dict == NULL || dictSize < 8` no dictionary is used. 
-</p></pre><BR>
-
-<a name="Chapter7"></a><h2>Bulk processing dictionary API</h2><pre></pre>
-
-<pre><b>ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
-                             int compressionLevel);
-</b><p>  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
-  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
-  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
- `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
-  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
-  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. 
-</p></pre><BR>
-
-<pre><b>size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
-</b><p>  Function frees memory allocated by ZSTD_createCDict(). 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
-                                void* dst, size_t dstCapacity,
-                          const void* src, size_t srcSize,
-                          const ZSTD_CDict* cdict);
-</b><p>  Compression using a digested Dictionary.
-  Recommended when same dictionary is used multiple times.
-  Note : compression level is _decided at dictionary creation time_,
-     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) 
-</p></pre><BR>
-
-<pre><b>ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
-</b><p>  Create a digested dictionary, ready to start decompression operation without startup delay.
-  dictBuffer can be released after DDict creation, as its content is copied inside DDict. 
-</p></pre><BR>
-
-<pre><b>size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
-</b><p>  Function frees memory allocated with ZSTD_createDDict() 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
-                                  void* dst, size_t dstCapacity,
-                            const void* src, size_t srcSize,
-                            const ZSTD_DDict* ddict);
-</b><p>  Decompression using a digested Dictionary.
-  Recommended when same dictionary is used multiple times. 
-</p></pre><BR>
-
-<a name="Chapter8"></a><h2>Streaming</h2><pre></pre>
-
-<pre><b>typedef struct ZSTD_inBuffer_s {
-  const void* src;    </b>/**< start of input buffer */<b>
-  size_t size;        </b>/**< size of input buffer */<b>
-  size_t pos;         </b>/**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
-} ZSTD_inBuffer;
-</b></pre><BR>
-<pre><b>typedef struct ZSTD_outBuffer_s {
-  void*  dst;         </b>/**< start of output buffer */<b>
-  size_t size;        </b>/**< size of output buffer */<b>
-  size_t pos;         </b>/**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
-} ZSTD_outBuffer;
-</b></pre><BR>
-<a name="Chapter9"></a><h2>Streaming compression - HowTo</h2><pre>
-  A ZSTD_CStream object is required to track streaming operation.
-  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
-  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
-  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
-
-  For parallel execution, use one separate ZSTD_CStream per thread.
-
-  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
-
-  Parameters are sticky : when starting a new compression on the same context,
-  it will re-use the same sticky parameters as previous compression session.
-  When in doubt, it's recommended to fully initialize the context before usage.
-  Use ZSTD_initCStream() to set the parameter to a selected compression level.
-  Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters.
-
-  Use ZSTD_compressStream() as many times as necessary to consume input stream.
-  The function will automatically update both `pos` fields within `input` and `output`.
-  Note that the function may not consume the entire input,
-  for example, because the output buffer is already full,
-  in which case `input.pos < input.size`.
-  The caller must check if input has been entirely consumed.
-  If not, the caller must make some room to receive more compressed data,
-  and then present again remaining input data.
- @return : a size hint, preferred nb of bytes to use as input for next function call
-           or an error code, which can be tested using ZSTD_isError().
-           Note 1 : it's just a hint, to help latency a little, any value will work fine.
-           Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize()
-
-  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
-  using ZSTD_flushStream(). `output->pos` will be updated.
-  Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0).
-  In which case, make some room to receive more compressed data, and call again ZSTD_flushStream().
-  @return : 0 if internal buffers are entirely flushed,
-            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-            or an error code, which can be tested using ZSTD_isError().
-
-  ZSTD_endStream() instructs to finish a frame.
-  It will perform a flush and write frame epilogue.
-  The epilogue is required for decoders to consider a frame completed.
-  flush() operation is the same, and follows same rules as ZSTD_flushStream().
-  @return : 0 if frame fully completed and fully flushed,
-            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-            or an error code, which can be tested using ZSTD_isError().
-
- 
-<BR></pre>
-
-<pre><b>typedef ZSTD_CCtx ZSTD_CStream;  </b>/**< CCtx and CStream are now effectively same object (>= v1.3.0) */<b>
-</b></pre><BR>
-<h3>ZSTD_CStream management functions</h3><pre></pre><b><pre>ZSTD_CStream* ZSTD_createCStream(void);
-size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
-</pre></b><BR>
-<h3>Streaming compression functions</h3><pre></pre><b><pre>size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
-size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-</pre></b><BR>
-<pre><b>size_t ZSTD_CStreamInSize(void);    </b>/**< recommended size for input buffer */<b>
-</b></pre><BR>
-<pre><b>size_t ZSTD_CStreamOutSize(void);   </b>/**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */<b>
-</b></pre><BR>
-<a name="Chapter10"></a><h2>Streaming decompression - HowTo</h2><pre>
-  A ZSTD_DStream object is required to track streaming operations.
-  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
-  ZSTD_DStream objects can be re-used multiple times.
-
-  Use ZSTD_initDStream() to start a new decompression operation.
- @return : recommended first input size
-  Alternatively, use advanced API to set specific properties.
-
-  Use ZSTD_decompressStream() repetitively to consume your input.
-  The function will update both `pos` fields.
-  If `input.pos < input.size`, some input has not been consumed.
-  It's up to the caller to present again remaining data.
-  The function tries to flush all data decoded immediately, respecting output buffer size.
-  If `output.pos < output.size`, decoder has flushed everything it could.
-  But if `output.pos == output.size`, there might be some data left within internal buffers.,
-  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
-  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
- @return : 0 when a frame is completely decoded and fully flushed,
-        or an error code, which can be tested using ZSTD_isError(),
-        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
-                                the return value is a suggested next input size (just a hint for better latency)
-                                that will never request more than the remaining frame size.
- 
-<BR></pre>
-
-<pre><b>typedef ZSTD_DCtx ZSTD_DStream;  </b>/**< DCtx and DStream are now effectively same object (>= v1.3.0) */<b>
-</b></pre><BR>
-<h3>ZSTD_DStream management functions</h3><pre></pre><b><pre>ZSTD_DStream* ZSTD_createDStream(void);
-size_t ZSTD_freeDStream(ZSTD_DStream* zds);
-</pre></b><BR>
-<h3>Streaming decompression functions</h3><pre></pre><b><pre>size_t ZSTD_initDStream(ZSTD_DStream* zds);
-size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-</pre></b><BR>
-<pre><b>size_t ZSTD_DStreamInSize(void);    </b>/*!< recommended size for input buffer */<b>
-</b></pre><BR>
-<pre><b>size_t ZSTD_DStreamOutSize(void);   </b>/*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */<b>
-</b></pre><BR>
-<a name="Chapter11"></a><h2>ADVANCED AND EXPERIMENTAL FUNCTIONS</h2><pre>
- The definitions in the following section are considered experimental.
- They are provided for advanced scenarios.
- They should never be used with a dynamic library, as prototypes may change in the future.
- Use them only in association with static linking.
- 
-<BR></pre>
-
-<a name="Chapter12"></a><h2>Candidate API for promotion to stable status</h2><pre>
- The following symbols and constants form the "staging area" :
- they are considered to join "stable API" by v1.4.0.
- The proposal is written so that it can be made stable "as is",
- though it's still possible to suggest improvements.
- Staging is in fact last chance for changes,
- the API is locked once reaching "stable" status.
- 
-<BR></pre>
-
-<pre><b>int ZSTD_minCLevel(void);  </b>/*!< minimum negative compression level allowed */<b>
-</b></pre><BR>
-<pre><b>size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
-</b><p> `src` should point to the start of a ZSTD frame or skippable frame.
- `srcSize` must be >= first frame size
- @return : the compressed size of the first frame starting at `src`,
-           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
-        or an error code if input is invalid 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
-size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
-size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
-size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
-size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
-size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
-</b><p>  These functions give the _current_ memory usage of selected object.
-  Note that object memory usage can evolve (increase or decrease) over time. 
-</p></pre><BR>
-
-<a name="Chapter13"></a><h2>Advanced compression API</h2><pre></pre>
+<a name="Chapter5"></a><h2>Advanced compression API</h2><pre></pre>

 <pre><b>typedef enum { ZSTD_fast=1,
               ZSTD_dfast=2,
@@ -407,7 +197,10 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 </b></pre><BR>
 <pre><b>typedef enum {

-    </b>/* compression parameters */<b>
+    </b>/* compression parameters<b>
+     * Note: When compressing with a ZSTD_CDict these parameters are superseded
+     * by the parameters used to construct the ZSTD_CDict. See ZSTD_CCtx_refCDict()
+     * for more info (superseded-by-cdict). */
    ZSTD_c_compressionLevel=100, </b>/* Update all compression parameters according to pre-defined cLevel table<b>
                              * Default level is ZSTD_CLEVEL_DEFAULT==3.
                              * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT.
@@ -529,6 +322,8 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
     * ZSTD_c_format
     * ZSTD_c_forceMaxWindow
     * ZSTD_c_forceAttachDict
+     * ZSTD_c_literalCompressionMode
+     * ZSTD_c_targetCBlockSize
     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
     * note : never ever use experimentalParam? names directly;
     *        also, the enums values themselves are unstable and can still change.
@@ -536,7 +331,9 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
     ZSTD_c_experimentalParam1=500,
     ZSTD_c_experimentalParam2=10,
     ZSTD_c_experimentalParam3=1000,
-     ZSTD_c_experimentalParam4=1001
+     ZSTD_c_experimentalParam4=1001,
+     ZSTD_c_experimentalParam5=1002,
+     ZSTD_c_experimentalParam6=1003,
 } ZSTD_cParameter;
 </b></pre><BR>
 <pre><b>typedef struct {
@@ -580,62 +377,10 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
  Note 3 : Whenever all input data is provided and consumed in a single round,
           for example with ZSTD_compress2(),
           or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end),
-           this value is automatically overriden by srcSize instead.
+           this value is automatically overridden by srcSize instead.
 
 </p></pre><BR>

-<pre><b>size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
-</b><p>  Create an internal CDict from `dict` buffer.
-  Decompression will have to use same dictionary.
- @result : 0, or an error code (which can be tested with ZSTD_isError()).
-  Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary,
-           meaning "return to no-dictionary mode".
-  Note 1 : Dictionary is sticky, it will be used for all future compressed frames.
-           To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters).
-  Note 2 : Loading a dictionary involves building tables.
-           It's also a CPU consuming operation, with non-negligible impact on latency.
-           Tables are dependent on compression parameters, and for this reason,
-           compression parameters can no longer be changed after loading a dictionary.
-  Note 3 :`dict` content will be copied internally.
-           Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead.
-           In such a case, dictionary buffer must outlive its users.
-  Note 4 : Use ZSTD_CCtx_loadDictionary_advanced()
-           to precisely select how dictionary content must be interpreted. 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
-</b><p>  Reference a prepared dictionary, to be used for all next compressed frames.
-  Note that compression parameters are enforced from within CDict,
-  and supercede any compression parameter previously set within CCtx.
-  The dictionary will remain valid for future compressed frames using same CCtx.
- @result : 0, or an error code (which can be tested with ZSTD_isError()).
-  Special : Referencing a NULL CDict means "return to no-dictionary mode".
-  Note 1 : Currently, only one dictionary can be managed.
-           Referencing a new dictionary effectively "discards" any previous one.
-  Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. 
-</p></pre><BR>
-
-<pre><b>size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
-                     const void* prefix, size_t prefixSize);
-</b><p>  Reference a prefix (single-usage dictionary) for next compressed frame.
-  A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end).
-  Decompression will need same prefix to properly regenerate data.
-  Compressing with a prefix is similar in outcome as performing a diff and compressing it,
-  but performs much faster, especially during decompression (compression speed is tunable with compression level).
- @result : 0, or an error code (which can be tested with ZSTD_isError()).
-  Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary
-  Note 1 : Prefix buffer is referenced. It **must** outlive compression.
-           Its content must remain unmodified during compression.
-  Note 2 : If the intention is to diff some large src data blob with some prior version of itself,
-           ensure that the window size is large enough to contain the entire source.
-           See ZSTD_c_windowLog.
-  Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters.
-           It's a CPU consuming operation, with non-negligible impact on latency.
-           If there is a need to use the same prefix multiple times, consider loadDictionary instead.
-  Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent).
-           Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. 
-</p></pre><BR>
-
 <pre><b>typedef enum {
    ZSTD_reset_session_only = 1,
    ZSTD_reset_parameters = 2,
@@ -672,42 +417,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 
 </p></pre><BR>

-<pre><b>typedef enum {
-    ZSTD_e_continue=0, </b>/* collect more data, encoder decides when to output compressed result, for optimal compression ratio */<b>
-    ZSTD_e_flush=1,    </b>/* flush any data provided so far,<b>
-                        * it creates (at least) one new block, that can be decoded immediately on reception;
-                        * frame will continue: any future data can still reference previously compressed data, improving compression. */
-    ZSTD_e_end=2       </b>/* flush any remaining data _and_ close current frame.<b>
-                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
-                        * After that point, any additional data starts a new frame.
-                        * note : each frame is independent (does not reference any content from previous frame). */
-} ZSTD_EndDirective;
-</b></pre><BR>
-<pre><b>size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
-                             ZSTD_outBuffer* output,
-                             ZSTD_inBuffer* input,
-                             ZSTD_EndDirective endOp);
-</b><p>  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
-  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
-  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
-  - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize
-  - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
-  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
-  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
-                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
-                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
-  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
-  - @return provides a minimum amount of data remaining to be flushed from internal buffers
-            or an error code, which can be tested using ZSTD_isError().
-            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
-            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
-            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
-  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
-            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
-            Before starting a new compression job, or changing compression parameters,
-            it is required to fully flush internal buffers.
- 
-</p></pre><BR>
+<a name="Chapter6"></a><h2>Advanced decompression API</h2><pre></pre>

 <pre><b>typedef enum {

@@ -715,7 +425,8 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
                              * the streaming API will refuse to allocate memory buffer
                              * in order to protect the host from unreasonable memory requirements.
                              * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
-                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) */
+                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT).
+                              * Special: value 0 means "use default maximum windowLog". */

    </b>/* note : additional experimental parameters are also available<b>
     * within the experimental section of the API.
@@ -746,6 +457,347 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 
 </p></pre><BR>

+<pre><b>size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+</b><p>  Return a DCtx to clean state.
+  Session and parameters can be reset jointly or separately.
+  Parameters can only be reset when no active frame is being decompressed.
+ @return : 0, or an error code, which can be tested with ZSTD_isError()
+ 
+</p></pre><BR>
+
+<a name="Chapter7"></a><h2>Streaming</h2><pre></pre>
+
+<pre><b>typedef struct ZSTD_inBuffer_s {
+  const void* src;    </b>/**< start of input buffer */<b>
+  size_t size;        </b>/**< size of input buffer */<b>
+  size_t pos;         </b>/**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
+} ZSTD_inBuffer;
+</b></pre><BR>
+<pre><b>typedef struct ZSTD_outBuffer_s {
+  void*  dst;         </b>/**< start of output buffer */<b>
+  size_t size;        </b>/**< size of output buffer */<b>
+  size_t pos;         </b>/**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
+} ZSTD_outBuffer;
+</b></pre><BR>
+<a name="Chapter8"></a><h2>Streaming compression - HowTo</h2><pre>
+  A ZSTD_CStream object is required to track streaming operation.
+  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
+  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
+  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
+
+  For parallel execution, use one separate ZSTD_CStream per thread.
+
+  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
+
+  Parameters are sticky : when starting a new compression on the same context,
+  it will re-use the same sticky parameters as previous compression session.
+  When in doubt, it's recommended to fully initialize the context before usage.
+  Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(),
+  ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to
+  set more specific parameters, the pledged source size, or load a dictionary.
+
+  Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to
+  consume input stream. The function will automatically update both `pos`
+  fields within `input` and `output`.
+  Note that the function may not consume the entire input, for example, because
+  the output buffer is already full, in which case `input.pos < input.size`.
+  The caller must check if input has been entirely consumed.
+  If not, the caller must make some room to receive more compressed data,
+  and then present again remaining input data.
+  note: ZSTD_e_continue is guaranteed to make some forward progress when called,
+        but doesn't guarantee maximal forward progress. This is especially relevant
+        when compressing with multiple threads. The call won't block if it can
+        consume some input, but if it can't it will wait for some, but not all,
+        output to be flushed.
+ @return : provides a minimum amount of data remaining to be flushed from internal buffers
+           or an error code, which can be tested using ZSTD_isError().
+
+  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
+  using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated.
+  Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0).
+  In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush.
+  You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the
+  operation.
+  note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will
+        block until the flush is complete or the output buffer is full.
+  @return : 0 if internal buffers are entirely flushed,
+            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+            or an error code, which can be tested using ZSTD_isError().
+
+  Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame.
+  It will perform a flush and write frame epilogue.
+  The epilogue is required for decoders to consider a frame completed.
+  flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush.
+  You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to
+  start a new frame.
+  note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will
+        block until the flush is complete or the output buffer is full.
+  @return : 0 if frame fully completed and fully flushed,
+            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+            or an error code, which can be tested using ZSTD_isError().
+
+ 
+<BR></pre>
+
+<pre><b>typedef ZSTD_CCtx ZSTD_CStream;  </b>/**< CCtx and CStream are now effectively same object (>= v1.3.0) */<b>
+</b></pre><BR>
+<h3>ZSTD_CStream management functions</h3><pre></pre><b><pre>ZSTD_CStream* ZSTD_createCStream(void);
+size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
+</pre></b><BR>
+<h3>Streaming compression functions</h3><pre></pre><b><pre>typedef enum {
+    ZSTD_e_continue=0, </b>/* collect more data, encoder decides when to output compressed result, for optimal compression ratio */<b>
+    ZSTD_e_flush=1,    </b>/* flush any data provided so far,<b>
+                        * it creates (at least) one new block, that can be decoded immediately on reception;
+                        * frame will continue: any future data can still reference previously compressed data, improving compression.
+                        * note : multithreaded compression will block to flush as much output as possible. */
+    ZSTD_e_end=2       </b>/* flush any remaining data _and_ close current frame.<b>
+                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
+                        * After that point, any additional data starts a new frame.
+                        * note : each frame is independent (does not reference any content from previous frame).
+                        : note : multithreaded compression will block to flush as much output as possible. */
+} ZSTD_EndDirective;
+</pre></b><BR>
+<pre><b>size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
+                             ZSTD_outBuffer* output,
+                             ZSTD_inBuffer* input,
+                             ZSTD_EndDirective endOp);
+</b><p>  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
+  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
+  - output->pos must be <= dstCapacity, input->pos must be <= srcSize
+  - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
+  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
+  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
+                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
+                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
+  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
+  - @return provides a minimum amount of data remaining to be flushed from internal buffers
+            or an error code, which can be tested using ZSTD_isError().
+            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
+            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
+            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
+  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
+            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+            Before starting a new compression job, or changing compression parameters,
+            it is required to fully flush internal buffers.
+ 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_CStreamInSize(void);    </b>/**< recommended size for input buffer */<b>
+</b></pre><BR>
+<pre><b>size_t ZSTD_CStreamOutSize(void);   </b>/**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */<b>
+</b></pre><BR>
+<pre><b>size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
+</b>/*!<b>
+ * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue).
+ * NOTE: The return value is different. ZSTD_compressStream() returns a hint for
+ * the next read size (if non-zero and not an error). ZSTD_compressStream2()
+ * returns the minimum nb of bytes left to flush (if non-zero and not an error).
+ */
+size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+</b>/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */<b>
+size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+</b>/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */<b>
+size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+</b><p>
+     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ 
+</p></pre><BR>
+
+<a name="Chapter9"></a><h2>Streaming decompression - HowTo</h2><pre>
+  A ZSTD_DStream object is required to track streaming operations.
+  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
+  ZSTD_DStream objects can be re-used multiple times.
+
+  Use ZSTD_initDStream() to start a new decompression operation.
+ @return : recommended first input size
+  Alternatively, use advanced API to set specific properties.
+
+  Use ZSTD_decompressStream() repetitively to consume your input.
+  The function will update both `pos` fields.
+  If `input.pos < input.size`, some input has not been consumed.
+  It's up to the caller to present again remaining data.
+  The function tries to flush all data decoded immediately, respecting output buffer size.
+  If `output.pos < output.size`, decoder has flushed everything it could.
+  But if `output.pos == output.size`, there might be some data left within internal buffers.,
+  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
+  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
+ @return : 0 when a frame is completely decoded and fully flushed,
+        or an error code, which can be tested using ZSTD_isError(),
+        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
+                                the return value is a suggested next input size (just a hint for better latency)
+                                that will never request more than the remaining frame size.
+ 
+<BR></pre>
+
+<pre><b>typedef ZSTD_DCtx ZSTD_DStream;  </b>/**< DCtx and DStream are now effectively same object (>= v1.3.0) */<b>
+</b></pre><BR>
+<h3>ZSTD_DStream management functions</h3><pre></pre><b><pre>ZSTD_DStream* ZSTD_createDStream(void);
+size_t ZSTD_freeDStream(ZSTD_DStream* zds);
+</pre></b><BR>
+<h3>Streaming decompression functions</h3><pre></pre><b><pre></pre></b><BR>
+<pre><b>size_t ZSTD_DStreamInSize(void);    </b>/*!< recommended size for input buffer */<b>
+</b></pre><BR>
+<pre><b>size_t ZSTD_DStreamOutSize(void);   </b>/*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */<b>
+</b></pre><BR>
+<a name="Chapter10"></a><h2>Simple dictionary API</h2><pre></pre>
+
+<pre><b>size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
+                               void* dst, size_t dstCapacity,
+                         const void* src, size_t srcSize,
+                         const void* dict,size_t dictSize,
+                               int compressionLevel);
+</b><p>  Compression at an explicit compression level using a Dictionary.
+  A dictionary can be any arbitrary data segment (also called a prefix),
+  or a buffer with specified information (see dictBuilder/zdict.h).
+  Note : This function loads the dictionary, resulting in significant startup delay.
+         It's intended for a dictionary used only once.
+  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                 void* dst, size_t dstCapacity,
+                           const void* src, size_t srcSize,
+                           const void* dict,size_t dictSize);
+</b><p>  Decompression using a known Dictionary.
+  Dictionary must be identical to the one used during compression.
+  Note : This function loads the dictionary, resulting in significant startup delay.
+         It's intended for a dictionary used only once.
+  Note : When `dict == NULL || dictSize < 8` no dictionary is used. 
+</p></pre><BR>
+
+<a name="Chapter11"></a><h2>Bulk processing dictionary API</h2><pre></pre>
+
+<pre><b>ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+                             int compressionLevel);
+</b><p>  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
+  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
+  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
+  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
+  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. 
+</p></pre><BR>
+
+<pre><b>size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
+</b><p>  Function frees memory allocated by ZSTD_createCDict(). 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                void* dst, size_t dstCapacity,
+                          const void* src, size_t srcSize,
+                          const ZSTD_CDict* cdict);
+</b><p>  Compression using a digested Dictionary.
+  Recommended when same dictionary is used multiple times.
+  Note : compression level is _decided at dictionary creation time_,
+     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) 
+</p></pre><BR>
+
+<pre><b>ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
+</b><p>  Create a digested dictionary, ready to start decompression operation without startup delay.
+  dictBuffer can be released after DDict creation, as its content is copied inside DDict. 
+</p></pre><BR>
+
+<pre><b>size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
+</b><p>  Function frees memory allocated with ZSTD_createDDict() 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                  void* dst, size_t dstCapacity,
+                            const void* src, size_t srcSize,
+                            const ZSTD_DDict* ddict);
+</b><p>  Decompression using a digested Dictionary.
+  Recommended when same dictionary is used multiple times. 
+</p></pre><BR>
+
+<a name="Chapter12"></a><h2>Dictionary helper functions</h2><pre></pre>
+
+<pre><b>unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+</b><p>  Provides the dictID stored within dictionary.
+  if @return == 0, the dictionary is not conformant with Zstandard specification.
+  It can still be loaded, but as a content-only dictionary. 
+</p></pre><BR>
+
+<pre><b>unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+</b><p>  Provides the dictID of the dictionary loaded into `ddict`.
+  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. 
+</p></pre><BR>
+
+<pre><b>unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+</b><p>  Provides the dictID required to decompressed the frame stored within `src`.
+  If @return == 0, the dictID could not be decoded.
+  This could for one of the following reasons :
+  - The frame does not require a dictionary to be decoded (most common case).
+  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+    Note : this use case also happens when using a non-conformant dictionary.
+  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+  - This is not a Zstandard frame.
+  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. 
+</p></pre><BR>
+
+<a name="Chapter13"></a><h2>Advanced dictionary and prefix API</h2><pre>
+ This API allows dictionaries to be used with ZSTD_compress2(),
+ ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and
+ only reset with the context is reset with ZSTD_reset_parameters or
+ ZSTD_reset_session_and_parameters. Prefixes are single-use.
+<BR></pre>
+
+<pre><b>size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+</b><p>  Create an internal CDict from `dict` buffer.
+  Decompression will have to use same dictionary.
+ @result : 0, or an error code (which can be tested with ZSTD_isError()).
+  Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary,
+           meaning "return to no-dictionary mode".
+  Note 1 : Dictionary is sticky, it will be used for all future compressed frames.
+           To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters).
+  Note 2 : Loading a dictionary involves building tables.
+           It's also a CPU consuming operation, with non-negligible impact on latency.
+           Tables are dependent on compression parameters, and for this reason,
+           compression parameters can no longer be changed after loading a dictionary.
+  Note 3 :`dict` content will be copied internally.
+           Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead.
+           In such a case, dictionary buffer must outlive its users.
+  Note 4 : Use ZSTD_CCtx_loadDictionary_advanced()
+           to precisely select how dictionary content must be interpreted. 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
+</b><p>  Reference a prepared dictionary, to be used for all next compressed frames.
+  Note that compression parameters are enforced from within CDict,
+  and supersede any compression parameter previously set within CCtx.
+  The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs.
+  The ignored parameters will be used again if the CCtx is returned to no-dictionary mode.
+  The dictionary will remain valid for future compressed frames using same CCtx.
+ @result : 0, or an error code (which can be tested with ZSTD_isError()).
+  Special : Referencing a NULL CDict means "return to no-dictionary mode".
+  Note 1 : Currently, only one dictionary can be managed.
+           Referencing a new dictionary effectively "discards" any previous one.
+  Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. 
+</p></pre><BR>
+
+<pre><b>size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
+                     const void* prefix, size_t prefixSize);
+</b><p>  Reference a prefix (single-usage dictionary) for next compressed frame.
+  A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end).
+  Decompression will need same prefix to properly regenerate data.
+  Compressing with a prefix is similar in outcome as performing a diff and compressing it,
+  but performs much faster, especially during decompression (compression speed is tunable with compression level).
+ @result : 0, or an error code (which can be tested with ZSTD_isError()).
+  Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary
+  Note 1 : Prefix buffer is referenced. It **must** outlive compression.
+           Its content must remain unmodified during compression.
+  Note 2 : If the intention is to diff some large src data blob with some prior version of itself,
+           ensure that the window size is large enough to contain the entire source.
+           See ZSTD_c_windowLog.
+  Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters.
+           It's a CPU consuming operation, with non-negligible impact on latency.
+           If there is a need to use the same prefix multiple times, consider loadDictionary instead.
+  Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent).
+           Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. 
+</p></pre><BR>
+
 <pre><b>size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
 </b><p>  Create an internal DDict from dict buffer,
  to be used to decompress next frames.
@@ -793,12 +845,14 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 
 </p></pre><BR>

-<pre><b>size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
-</b><p>  Return a DCtx to clean state.
-  Session and parameters can be reset jointly or separately.
-  Parameters can only be reset when no active frame is being decompressed.
- @return : 0, or an error code, which can be tested with ZSTD_isError()
- 
+<pre><b>size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+</b><p>  These functions give the _current_ memory usage of selected object.
+  Note that object memory usage can evolve (increase or decrease) over time. 
 </p></pre><BR>

 <a name="Chapter14"></a><h2>experimental API (static linking only)</h2><pre>
@@ -890,12 +944,21 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
    ZSTD_dictForceCopy     = 2, </b>/* Always copy the dictionary. */<b>
 } ZSTD_dictAttachPref_e;
 </b></pre><BR>
+<pre><b>typedef enum {
+  ZSTD_lcm_auto = 0,          </b>/**< Automatically determine the compression mode based on the compression level.<b>
+                               *   Negative compression levels will be uncompressed, and positive compression
+                               *   levels will be compressed. */
+  ZSTD_lcm_huffman = 1,       </b>/**< Always attempt Huffman compression. Uncompressed literals will still be<b>
+                               *   emitted if Huffman compression is not profitable. */
+  ZSTD_lcm_uncompressed = 2,  </b>/**< Always emit uncompressed literals. */<b>
+} ZSTD_literalCompressionMode_e;
+</b></pre><BR>
 <a name="Chapter15"></a><h2>Frame size functions</h2><pre></pre>

 <pre><b>unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
-</b><p>  `src` should point the start of a series of ZSTD encoded and/or skippable frames
+</b><p>  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
  `srcSize` must be the _exact_ size of this series
-       (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
+       (i.e. there should be a frame boundary at `src + srcSize`)
  @return : - decompressed size of all data in all successive frames
            - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
@@ -915,6 +978,21 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
            however it does mean that all frame data must be present and valid. 
 </p></pre><BR>

+<pre><b>unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize);
+</b><p>  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
+  `srcSize` must be the _exact_ size of this series
+       (i.e. there should be a frame boundary at `src + srcSize`)
+  @return : - upper-bound for the decompressed size of all data in all successive frames
+            - if an error occured: ZSTD_CONTENTSIZE_ERROR
+
+  note 1  : an error can occur if `src` contains an invalid or incorrectly formatted frame.
+  note 2  : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`.
+            in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value.
+  note 3  : when the decompressed size field isn't available, the upper-bound for that frame is calculated by:
+              upper-bound = # blocks * min(128 KB, Window_Size)
+ 
+</p></pre><BR>
+
 <pre><b>size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
 </b><p>  srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX.
 @return : size of the Frame Header,
@@ -933,7 +1011,7 @@ size_t ZSTD_estimateDCtxSize(void);
  It will also consider src size to be arbitrarily "large", which is worst case.
  If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation.
  ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
-  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
  Note : CCtx size estimation is only correct for single-threaded compression. 
 </p></pre><BR>

@@ -946,7 +1024,7 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize);
  It will also consider src size to be arbitrarily "large", which is worst case.
  If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation.
  ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
-  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
  Note : CStream size estimation is only correct for single-threaded compression.
  ZSTD_DStream memory budget depends on window Size.
  This information can be passed manually, using ZSTD_estimateDStreamSize,
@@ -1011,22 +1089,26 @@ static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL };  </b>/**< t
 </p></pre><BR>

 <pre><b>ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
-</b><p>   @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
-   `estimatedSrcSize` value is optional, select 0 if not known 
+</b><p> @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
+ `estimatedSrcSize` value is optional, select 0 if not known 
 </p></pre><BR>

 <pre><b>ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
-</b><p>   same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
-   All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 
+</b><p>  same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
+  All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 
 </p></pre><BR>

 <pre><b>size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
-</b><p>   Ensure param values remain within authorized range 
+</b><p>  Ensure param values remain within authorized range.
+ @return 0 on success, or an error code (can be checked with ZSTD_isError()) 
 </p></pre><BR>

 <pre><b>ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
 </b><p>  optimize params for a given `srcSize` and `dictSize`.
-  both values are optional, select `0` if unknown. 
+ `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN.
+ `dictSize` must be `0` when there is no dictionary.
+  cPar can be invalid : all parameters will be clamped within valid range in the @return struct.
+  This function never fails (wide contract) 
 </p></pre><BR>

 <pre><b>size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx,
@@ -1072,10 +1154,10 @@ static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL };  </b>/**< t
 size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
 </b><p>  Quick howto :
  - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure
-  - ZSTD_CCtxParam_setParameter() : Push parameters one by one into
-                                    an existing ZSTD_CCtx_params structure.
-                                    This is similar to
-                                    ZSTD_CCtx_setParameter().
+  - ZSTD_CCtxParams_setParameter() : Push parameters one by one into
+                                     an existing ZSTD_CCtx_params structure.
+                                     This is similar to
+                                     ZSTD_CCtx_setParameter().
  - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to
                                    an existing CCtx.
                                    These parameters will be applied to
@@ -1105,7 +1187,7 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
 
 </p></pre><BR>

-<pre><b>size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
+<pre><b>size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
 </b><p>  Similar to ZSTD_CCtx_setParameter.
  Set one compression parameter, selected by enum ZSTD_cParameter.
  Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams().
@@ -1113,7 +1195,7 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
 
 </p></pre><BR>

-<pre><b>size_t ZSTD_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
+<pre><b>size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
 </b><p> Similar to ZSTD_CCtx_getParameter.
 Get the requested value of one compression parameter, selected by enum ZSTD_cParameter.
 @result : 0, or an error code (which can be tested with ZSTD_isError()).
@@ -1158,30 +1240,6 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
  it must remain read accessible throughout the lifetime of DDict 
 </p></pre><BR>

-<pre><b>unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
-</b><p>  Provides the dictID stored within dictionary.
-  if @return == 0, the dictionary is not conformant with Zstandard specification.
-  It can still be loaded, but as a content-only dictionary. 
-</p></pre><BR>
-
-<pre><b>unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
-</b><p>  Provides the dictID of the dictionary loaded into `ddict`.
-  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
-  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. 
-</p></pre><BR>
-
-<pre><b>unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
-</b><p>  Provides the dictID required to decompressed the frame stored within `src`.
-  If @return == 0, the dictID could not be decoded.
-  This could for one of the following reasons :
-  - The frame does not require a dictionary to be decoded (most common case).
-  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
-    Note : this use case also happens when using a non-conformant dictionary.
-  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
-  - This is not a Zstandard frame.
-  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. 
-</p></pre><BR>
-
 <pre><b>size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
 </b><p>  Same as ZSTD_DCtx_loadDictionary(),
  but references `dict` content instead of copying it into `dctx`.
@@ -1233,15 +1291,69 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
  redundant functions will be deprecated, and then at some point removed.
 <BR></pre>

-<h3>Advanced Streaming compression functions</h3><pre></pre><b><pre>size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   </b>/**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */<b>
-size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); </b>/**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/<b>
+<h3>Advanced Streaming compression functions</h3><pre></pre><b><pre></b>/**! ZSTD_initCStream_srcSize() :<b>
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
+ * pledgedSrcSize must be correct. If it is not known at init time, use
+ * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs,
+ * "0" also disables frame content size field. It may be enabled in the future.
+ */
+size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);
+</b>/**! ZSTD_initCStream_usingDict() :<b>
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * Creates of an internal CDict (incompatible with static CCtx), except if
+ * dict == NULL or dictSize < 8, in which case no dict is used.
+ * Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if
+ * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.
+ */
+size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel);
+</b>/**! ZSTD_initCStream_advanced() :<b>
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdParams(zcs, params); // Set the zstd params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy.
+ */
 size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
-                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  </b>/**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */<b>
-size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  </b>/**< note : cdict will just be referenced, and must outlive compression session */<b>
-size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  </b>/**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */<b>
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);
+</b>/**! ZSTD_initCStream_usingCDict() :<b>
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * note : cdict will just be referenced, and must outlive compression session
+ */
+size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
+</b>/**! ZSTD_initCStream_usingCDict_advanced() :<b>
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdFrameParams(zcs, fParams); // Set the zstd frame params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * same as ZSTD_initCStream_usingCDict(), with control over frame parameters.
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN.
+ */
+size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);
 </pre></b><BR>
 <pre><b>size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
-</b><p>  start a new frame, using same parameters from previous frame.
+</b><p> This function is deprecated, and is equivalent to:
+     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+
+  start a new frame, using same parameters from previous frame.
  This is typically useful to skip dictionary loading stage, since it will re-use it in-place.
  Note that zcs must be init at least once before using ZSTD_resetCStream().
  If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN.
@@ -1276,9 +1388,32 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict*
 
 </p></pre><BR>

-<h3>Advanced Streaming decompression functions</h3><pre></pre><b><pre>size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); </b>/**< note: no dictionary will be used if dict == NULL or dictSize < 8 */<b>
-size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);  </b>/**< note : ddict is referenced, it must outlive decompression session */<b>
-size_t ZSTD_resetDStream(ZSTD_DStream* zds);  </b>/**< re-use decompression parameters from previous init; saves dictionary loading */<b>
+<h3>Advanced Streaming decompression functions</h3><pre></pre><b><pre></b>/**<b>
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_loadDictionary(zds, dict, dictSize);
+ *
+ * note: no dictionary will be used if dict == NULL or dictSize < 8
+ */
+size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize);
+</b>/**<b>
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_refDDict(zds, ddict);
+ *
+ * note : ddict is referenced, it must outlive decompression session
+ */
+size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);
+</b>/**<b>
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *
+ * re-use decompression parameters from previous init; saves dictionary loading
+ */
+size_t ZSTD_resetDStream(ZSTD_DStream* zds);
 </pre></b><BR>
 <a name="Chapter20"></a><h2>Buffer-less and synchronous inner streaming functions</h2><pre>
  This is an advanced API, giving full control over buffer management, for users which need direct control over memory.
@@ -1405,23 +1540,21 @@ typedef struct {
    unsigned checksumFlag;
 } ZSTD_frameHeader;
 </pre></b><BR>
-<a name="Chapter23"></a><h2>ZSTD_getFrameHeader() :</h2><pre>  decode Frame Header, or requires larger `srcSize`.
+<pre><b>size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize);   </b>/**< doesn't consume input */<b>
+</b>/*! ZSTD_getFrameHeader_advanced() :<b>
+ *  same as ZSTD_getFrameHeader(),
+ *  with added capability to select a format (like ZSTD_f_zstd1_magicless) */
+size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format);
+size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize);  </b>/**< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */<b>
+</b><p>  decode Frame Header, or requires larger `srcSize`.
 @return : 0, `zfhPtr` is correctly filled,
          >0, `srcSize` is too small, value is wanted `srcSize` amount,
           or an error code, which can be tested using ZSTD_isError() 
-<BR></pre>
-
-<pre><b>size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize);   </b>/**< doesn't consume input */<b>
-</b></pre><BR>
-<pre><b>size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format);
-size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize);  </b>/**< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */<b>
-</b><p>  same as ZSTD_getFrameHeader(),
-  with added capability to select a format (like ZSTD_f_zstd1_magicless) 
 </p></pre><BR>

 <pre><b>typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
 </b></pre><BR>
-<a name="Chapter24"></a><h2>Block level API</h2><pre></pre>
+<a name="Chapter23"></a><h2>Block level API</h2><pre></pre>

 <pre><b></b><p>    Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes).
    User will have to take in charge required information to regenerate data, such as compressed and content sizes.
@@ -25,28 +25,28 @@ all: simple_compression simple_decompression \
 $(LIB) :
 	$(MAKE) -C ../lib libzstd.a

-simple_compression : simple_compression.c utils.h $(LIB)
+simple_compression : simple_compression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-simple_decompression : simple_decompression.c utils.h $(LIB)
+simple_decompression : simple_decompression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-multiple_simple_compression : multiple_simple_compression.c utils.h $(LIB)
+multiple_simple_compression : multiple_simple_compression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-dictionary_compression : dictionary_compression.c utils.h $(LIB)
+dictionary_compression : dictionary_compression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-dictionary_decompression : dictionary_decompression.c utils.h $(LIB)
+dictionary_decompression : dictionary_decompression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-streaming_compression : streaming_compression.c utils.h $(LIB)
+streaming_compression : streaming_compression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-multiple_streaming_compression : multiple_streaming_compression.c utils.h $(LIB)
+multiple_streaming_compression : multiple_streaming_compression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

-streaming_decompression : streaming_decompression.c utils.h $(LIB)
+streaming_decompression : streaming_decompression.c common.h $(LIB)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@

 streaming_memory_usage : streaming_memory_usage.c $(LIB)
@@ -77,7 +77,6 @@ test: all
 	@echo -- Edge cases detection
 	! ./streaming_decompression tmp    # invalid input, must fail
 	! ./simple_decompression tmp       # invalid input, must fail
-	! ./simple_decompression tmp.zst   # unknown input size, must fail
 	touch tmpNull                      # create 0-size file
 	./simple_compression tmpNull
 	./simple_decompression tmpNull.zst # 0-size frame : must work
@@ -11,15 +11,15 @@
 /*
 * This header file has common utility functions used in examples.
 */
-#ifndef UTILS_H
-#define UTILS_H
+#ifndef COMMON_H
+#define COMMON_H

 #include <stdlib.h>    // malloc, free, exit
 #include <stdio.h>     // fprintf, perror, fopen, etc.
-#include <string.h>    // strlen, strcat, memset, strerror
+#include <string.h>    // strerror
 #include <errno.h>     // errno
-#include <assert.h>    // assert
 #include <sys/stat.h>  // stat
+#include <zstd.h>

 /*
 * Define the returned error code from utility functions.
@@ -34,7 +34,34 @@ typedef enum {
    ERROR_saveFile = 7,
    ERROR_malloc = 8,
    ERROR_largeFile = 9,
-} UTILS_ErrorCode;
+} COMMON_ErrorCode;
+
+/*! CHECK
+ * Check that the condition holds. If it doesn't print a message and die.
+ */
+#define CHECK(cond, ...)                        \
+    do {                                        \
+        if (!(cond)) {                          \
+            fprintf(stderr,                     \
+                    "%s:%d CHECK(%s) failed: ", \
+                    __FILE__,                   \
+                    __LINE__,                   \
+                    #cond);                     \
+            fprintf(stderr, "" __VA_ARGS__);    \
+            fprintf(stderr, "\n");              \
+            exit(1);                            \
+        }                                       \
+    } while (0)
+
+/*! CHECK_ZSTD
+ * Check the zstd error code and die if an error occurred after printing a
+ * message.
+ */
+#define CHECK_ZSTD(fn, ...)                                      \
+    do {                                                         \
+        size_t const err = (fn);                                 \
+        CHECK(!ZSTD_isError(err), "%s", ZSTD_getErrorName(err)); \
+    } while (0)

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

    FILE* const inFile = fopen_orDie(fileName, "rb");
    size_t const readSize = fread(buffer, 1, fileSize, inFile);
@@ -7,13 +7,11 @@
 * in the COPYING file in the root directory of this source tree).
 * You may select, at your option, one of the above-listed licenses.
 */
-#include <stdlib.h>    // malloc, exit
 #include <stdio.h>     // printf
-#include <string.h>    // strerror
-#include <errno.h>     // errno
-#include <sys/stat.h>  // stat
+#include <stdlib.h>    // free
+#include <string.h>    // memset, strcat
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 /* createDict() :
   `dictFileName` is supposed to have been created using `zstd --train` */
@@ -23,10 +21,7 @@ static ZSTD_CDict* createCDict_orDie(const char* dictFileName, int cLevel)
    printf("loading dictionary %s \n", dictFileName);
    void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize);
    ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, cLevel);
-    if (!cdict) {
-        fprintf(stderr, "ZSTD_createCDict error \n");
-        exit(7);
-    }
+    CHECK(cdict != NULL, "ZSTD_createCDict() failed!");
    free(dictBuffer);
    return cdict;
 }
@@ -39,13 +34,16 @@ static void compress(const char* fname, const char* oname, const ZSTD_CDict* cdi
    size_t const cBuffSize = ZSTD_compressBound(fSize);
    void* const cBuff = malloc_orDie(cBuffSize);

+    /* Compress using the dictionary.
+     * This function writes the dictionary id, and content size into the header.
+     * But, it doesn't use a checksum. You can control these options using the
+     * advanced API: ZSTD_CCtx_setParameter(), ZSTD_CCtx_refCDict(),
+     * and ZSTD_compress2().
+     */
    ZSTD_CCtx* const cctx = ZSTD_createCCtx();
-    if (cctx==NULL) { fprintf(stderr, "ZSTD_createCCtx() error \n"); exit(10); }
+    CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");
    size_t const cSize = ZSTD_compress_usingCDict(cctx, cBuff, cBuffSize, fBuff, fSize, cdict);
-    if (ZSTD_isError(cSize)) {
-        fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
-        exit(7);
-    }
+    CHECK_ZSTD(cSize);

    saveFile_orDie(oname, cBuff, cSize);

@@ -9,15 +9,10 @@
 */


-
-#include <stdlib.h>    // malloc, exit
 #include <stdio.h>     // printf
-#include <string.h>    // strerror
-#include <errno.h>     // errno
-#include <sys/stat.h>  // stat
-#define ZSTD_STATIC_LINKING_ONLY   // ZSTD_findDecompressedSize
+#include <stdlib.h>    // free
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 /* createDict() :
   `dictFileName` is supposed to have been created using `zstd --train` */
@@ -27,7 +22,7 @@ static ZSTD_DDict* createDict_orDie(const char* dictFileName)
    printf("loading dictionary %s \n", dictFileName);
    void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize);
    ZSTD_DDict* const ddict = ZSTD_createDDict(dictBuffer, dictSize);
-    if (ddict==NULL) { fprintf(stderr, "ZSTD_createDDict error \n"); exit(5); }
+    CHECK(ddict != NULL, "ZSTD_createDDict() failed!");
    free(dictBuffer);
    return ddict;
 }
@@ -36,24 +31,40 @@ static void decompress(const char* fname, const ZSTD_DDict* ddict)
 {
    size_t cSize;
    void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize);
-    unsigned long long const rSize = ZSTD_findDecompressedSize(cBuff, cSize);
-    if (rSize==ZSTD_CONTENTSIZE_ERROR) {
-        fprintf(stderr, "%s : it was not compressed by zstd.\n", fname);
-        exit(5);
-    } else if (rSize==ZSTD_CONTENTSIZE_UNKNOWN) {
-        fprintf(stderr, "%s : original size unknown \n", fname);
-        exit(6);
-    }
-
+    /* Read the content size from the frame header. For simplicity we require
+     * that it is always present. By default, zstd will write the content size
+     * in the header when it is known. If you can't guarantee that the frame
+     * content size is always written into the header, either use streaming
+     * decompression, or ZSTD_decompressBound().
+     */
+    unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize);
+    CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname);
+    CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname);
    void* const rBuff = malloc_orDie((size_t)rSize);

+    /* Check that the dictionary ID matches.
+     * If a non-zstd dictionary is used, then both will be zero.
+     * By default zstd always writes the dictionary ID into the frame.
+     * Zstd will check if there is a dictionary ID mismatch as well.
+     */
+    unsigned const expectedDictID = ZSTD_getDictID_fromDDict(ddict);
+    unsigned const actualDictID = ZSTD_getDictID_fromFrame(cBuff, cSize);
+    CHECK(actualDictID == expectedDictID,
+          "DictID mismatch: expected %u got %u",
+          expectedDictID,
+          actualDictID);
+
+    /* Decompress using the dictionary.
+     * If you need to control the decompression parameters, then use the
+     * advanced API: ZSTD_DCtx_setParameter(), ZSTD_DCtx_refDDict(), and
+     * ZSTD_decompressDCtx().
+     */
    ZSTD_DCtx* const dctx = ZSTD_createDCtx();
-    if (dctx==NULL) { fprintf(stderr, "ZSTD_createDCtx() error \n"); exit(10); }
+    CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");
    size_t const dSize = ZSTD_decompress_usingDDict(dctx, rBuff, rSize, cBuff, cSize, ddict);
-    if (dSize != rSize) {
-        fprintf(stderr, "error decoding %s : %s \n", fname, ZSTD_getErrorName(dSize));
-        exit(7);
-    }
+    CHECK_ZSTD(dSize);
+    /* When zstd knows the content size, it will error if it doesn't match. */
+    CHECK(dSize == rSize, "Impossible because zstd will check this condition!");

    /* success */
    printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize);
@@ -8,13 +8,11 @@
 * You may select, at your option, one of the above-listed licenses.
 */

-#include <stdlib.h>    // malloc, free, exit
-#include <stdio.h>     // fprintf, perror, fopen, etc.
-#include <string.h>    // strlen, strcat, memset, strerror
-#include <errno.h>     // errno
-#include <sys/stat.h>  // stat
+#include <stdio.h>     // printf
+#include <stdlib.h>    // free
+#include <string.h>    // memcpy, strlen
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 typedef struct {
    void* fBuffer;
@@ -28,7 +26,7 @@ typedef struct {
 * allocate memory for buffers big enough to compress all files
 * as well as memory for output file name (ofn)
 */
-static resources createResources_orDie(int argc, const char** argv, char **ofn, int* ofnBufferLen)
+static resources createResources_orDie(int argc, const char** argv, char **ofn, size_t* ofnBufferLen)
 {
    size_t maxFilenameLength=0;
    size_t maxFileSize = 0;
@@ -52,7 +50,7 @@ static resources createResources_orDie(int argc, const char** argv, char **ofn,
    ress.fBuffer = malloc_orDie(ress.fBufferSize);
    ress.cBuffer = malloc_orDie(ress.cBufferSize);
    ress.cctx = ZSTD_createCCtx();
-    if (ress.cctx==NULL) { fprintf(stderr, "ZSTD_createCCtx() error \n"); exit(10); }
+    CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!");
    return ress;
 }

@@ -69,16 +67,17 @@ static void compressFile_orDie(resources ress, const char* fname, const char* on
 {
    size_t fSize = loadFile_orDie(fname, ress.fBuffer, ress.fBufferSize);

+    /* Compress using the context.
+     * If you need more control over parameters, use the advanced API:
+     * ZSTD_CCtx_setParameter(), and ZSTD_compress2().
+     */
    size_t const cSize = ZSTD_compressCCtx(ress.cctx, ress.cBuffer, ress.cBufferSize, ress.fBuffer, fSize, 1);
-    if (ZSTD_isError(cSize)) {
-        fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
-        exit(8);
-    }
+    CHECK_ZSTD(cSize);

    saveFile_orDie(oname, ress.cBuffer, cSize);

    /* success */
-    // printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname);
+    printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname);
 }

 int main(int argc, const char** argv)
@@ -94,21 +93,21 @@ int main(int argc, const char** argv)

    /* memory allocation for outFilename and resources */
    char* outFilename;
-    int outFilenameBufferLen;
-    resources const ress = createResources_orDie(argc, argv, &outFilename, &outFilenameBufferLen); 
+    size_t outFilenameBufferLen;
+    resources const ress = createResources_orDie(argc, argv, &outFilename, &outFilenameBufferLen);

    /* compress files with shared context, input and output buffers */
    int argNb;
    for (argNb = 1; argNb < argc; argNb++) {
        const char* const inFilename = argv[argNb];
-        int inFilenameLen = strlen(inFilename);
-        assert(inFilenameLen + 5 <= outFilenameBufferLen);
+        size_t const inFilenameLen = strlen(inFilename);
+        CHECK(inFilenameLen + 5 <= outFilenameBufferLen, "File name too long!");
        memcpy(outFilename, inFilename, inFilenameLen);
        memcpy(outFilename+inFilenameLen, ".zst", 5);
        compressFile_orDie(ress, inFilename, outFilename);
    }

-    /* free momery */
+    /* free memory */
    freeResources(ress,outFilename);

    printf("compressed %i files \n", argc-1);
@@ -14,66 +14,80 @@
 *  All structures and buffers will be created only once,
 *  and shared across all compression operations */

-#include <stdlib.h>    // malloc, exit
-#include <stdio.h>     // fprintf, perror, feof
-#include <string.h>    // strerror
-#include <errno.h>     // errno
-#define ZSTD_STATIC_LINKING_ONLY  // streaming API defined as "experimental" for the time being
+#include <stdio.h>     // printf
+#include <stdlib.h>    // free
+#include <string.h>    // memset, strcat
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 typedef struct {
    void* buffIn;
    void* buffOut;
    size_t buffInSize;
    size_t buffOutSize;
-    ZSTD_CStream* cstream;
-} resources ;
+    ZSTD_CCtx* cctx;
+} resources;

-static resources createResources_orDie()
+static resources createResources_orDie(int cLevel)
 {
    resources ress;
    ress.buffInSize = ZSTD_CStreamInSize();   /* can always read one full block */
    ress.buffOutSize= ZSTD_CStreamOutSize();  /* can always flush a full block */
    ress.buffIn = malloc_orDie(ress.buffInSize);
    ress.buffOut= malloc_orDie(ress.buffOutSize);
-    ress.cstream = ZSTD_createCStream();
-    if (ress.cstream==NULL) { fprintf(stderr, "ZSTD_createCStream() error \n"); exit(10); }
+    ress.cctx = ZSTD_createCCtx();
+    CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!");
+
+    /* Set any compression parameters you want here.
+     * They will persist for every compression operation.
+     * Here we set the compression level, and enable the checksum.
+     */
+    CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, cLevel) );
+    CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, 1) );
    return ress;
 }

 static void freeResources(resources ress)
 {
-    ZSTD_freeCStream(ress.cstream);
+    ZSTD_freeCCtx(ress.cctx);
    free(ress.buffIn);
    free(ress.buffOut);
 }

-static void compressFile_orDie(resources ress, const char* fname, const char* outName, int cLevel)
+static void compressFile_orDie(resources ress, const char* fname, const char* outName)
 {
+    // Open the input and output files.
    FILE* const fin  = fopen_orDie(fname, "rb");
    FILE* const fout = fopen_orDie(outName, "wb");

-    size_t const initResult = ZSTD_initCStream(ress.cstream, cLevel);
-    if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_initCStream() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
+    /* Reset the context to a clean state to start a new compression operation.
+     * The parameters are sticky, so we keep the compression level and extra
+     * parameters that we set in createResources_orDie().
+     */
+    CHECK_ZSTD( ZSTD_CCtx_reset(ress.cctx, ZSTD_reset_session_only) );
+
+    size_t const toRead = ress.buffInSize;
+    size_t read;
+    while ( (read = fread_orDie(ress.buffIn, toRead, fin)) ) {
+        /* This loop is the same as streaming_compression.c.
+         * See that file for detailed comments.
+         */
+        int const lastChunk = (read < toRead);
+        ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue;

-    size_t read, toRead = ress.buffInSize;
-    while( (read = fread_orDie(ress.buffIn, toRead, fin)) ) {
        ZSTD_inBuffer input = { ress.buffIn, read, 0 };
-        while (input.pos < input.size) {
+        int finished;
+        do {
            ZSTD_outBuffer output = { ress.buffOut, ress.buffOutSize, 0 };
-            toRead = ZSTD_compressStream(ress.cstream, &output , &input);   /* toRead is guaranteed to be <= ZSTD_CStreamInSize() */
-            if (ZSTD_isError(toRead)) { fprintf(stderr, "ZSTD_compressStream() error : %s \n", ZSTD_getErrorName(toRead)); exit(12); }
-            if (toRead > ress.buffInSize) toRead = ress.buffInSize;   /* Safely handle when `buffInSize` is manually changed to a smaller value */
+            size_t const remaining = ZSTD_compressStream2(ress.cctx, &output, &input, mode);
+            CHECK_ZSTD(remaining);
            fwrite_orDie(ress.buffOut, output.pos, fout);
-        }
+            finished = lastChunk ? (remaining == 0) : (input.pos == input.size);
+        } while (!finished);
+        CHECK(input.pos == input.size,
+              "Impossible: zstd only returns 0 when the input is completely consumed!");
    }

-    ZSTD_outBuffer output = { ress.buffOut, ress.buffOutSize, 0 };
-    size_t const remainingToFlush = ZSTD_endStream(ress.cstream, &output);   /* close frame */
-    if (remainingToFlush) { fprintf(stderr, "not fully flushed"); exit(13); }
-    fwrite_orDie(ress.buffOut, output.pos, fout);
-
    fclose_orDie(fout);
    fclose_orDie(fin);
 }
@@ -89,7 +103,8 @@ int main(int argc, const char** argv)
        return 1;
    }

-    resources const ress = createResources_orDie();
+    int const cLevel = 7;
+    resources const ress = createResources_orDie(cLevel);
    void* ofnBuffer = NULL;
    size_t ofnbSize = 0;

@@ -106,7 +121,7 @@ int main(int argc, const char** argv)
        memset(ofnBuffer, 0, ofnSize);
        strcat(ofnBuffer, ifn);
        strcat(ofnBuffer, ".zst");
-        compressFile_orDie(ress, ifn, ofnBuffer, 7);
+        compressFile_orDie(ress, ifn, ofnBuffer);
    }

    freeResources(ress);
@@ -8,13 +8,11 @@
 * You may select, at your option, one of the above-listed licenses.
 */

-#include <stdlib.h>    // malloc, free, exit
-#include <stdio.h>     // fprintf, perror, fopen, etc.
-#include <string.h>    // strlen, strcat, memset, strerror
-#include <errno.h>     // errno
-#include <sys/stat.h>  // stat
+#include <stdio.h>     // printf
+#include <stdlib.h>    // free
+#include <string.h>    // strlen, strcat, memset
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 static void compress_orDie(const char* fname, const char* oname)
 {
@@ -23,11 +21,12 @@ static void compress_orDie(const char* fname, const char* oname)
    size_t const cBuffSize = ZSTD_compressBound(fSize);
    void* const cBuff = malloc_orDie(cBuffSize);

+    /* Compress.
+     * If you are doing many compressions, you may want to reuse the context.
+     * See the multiple_simple_compression.c example.
+     */
    size_t const cSize = ZSTD_compress(cBuff, cBuffSize, fBuff, fSize, 1);
-    if (ZSTD_isError(cSize)) {
-        fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
-        exit(8);
-    }
+    CHECK_ZSTD(cSize);

    saveFile_orDie(oname, cBuff, cSize);

@@ -8,37 +8,36 @@
 * You may select, at your option, one of the above-listed licenses.
 */

-#include <stdlib.h>    // malloc, exit
 #include <stdio.h>     // printf
-#include <string.h>    // strerror
-#include <errno.h>     // errno
-#include <sys/stat.h>  // stat
-#define ZSTD_STATIC_LINKING_ONLY   // ZSTD_findDecompressedSize
+#include <stdlib.h>    // free
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 static void decompress(const char* fname)
 {
    size_t cSize;
    void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize);
-    unsigned long long const rSize = ZSTD_findDecompressedSize(cBuff, cSize);
-    if (rSize==ZSTD_CONTENTSIZE_ERROR) {
-        fprintf(stderr, "%s : it was not compressed by zstd.\n", fname);
-        exit(5);
-    } else if (rSize==ZSTD_CONTENTSIZE_UNKNOWN) {
-        fprintf(stderr,
-                "%s : original size unknown. Use streaming decompression instead.\n", fname);
-        exit(6);
-    }
+    /* Read the content size from the frame header. For simplicity we require
+     * that it is always present. By default, zstd will write the content size
+     * in the header when it is known. If you can't guarantee that the frame
+     * content size is always written into the header, either use streaming
+     * decompression, or ZSTD_decompressBound().
+     */
+    unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize);
+    CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname);
+    CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname);

    void* const rBuff = malloc_orDie((size_t)rSize);

+    /* Decompress.
+     * If you are doing many decompressions, you may want to reuse the context
+     * and use ZSTD_decompressDCtx(). If you want to set advanced parameters,
+     * use ZSTD_DCtx_setParameter().
+     */
    size_t const dSize = ZSTD_decompress(rBuff, rSize, cBuff, cSize);
-
-    if (dSize != rSize) {
-        fprintf(stderr, "error decoding %s : %s \n", fname, ZSTD_getErrorName(dSize));
-        exit(7);
-    }
+    CHECK_ZSTD(dSize);
+    /* When zstd knows the content size, it will error if it doesn't match. */
+    CHECK(dSize == rSize, "Impossible because zstd will check this condition!");

    /* success */
    printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize);
@@ -9,54 +9,79 @@
 */


-#include <stdlib.h>    // malloc, free, exit
-#include <stdio.h>     // fprintf, perror, feof, fopen, etc.
-#include <string.h>    // strlen, memset, strcat
+#include <stdio.h>     // printf
+#include <stdlib.h>    // free
+#include <string.h>    // memset, strcat, strlen
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()
+

 static void compressFile_orDie(const char* fname, const char* outName, int cLevel)
 {
+    /* Open the input and output files. */
    FILE* const fin  = fopen_orDie(fname, "rb");
    FILE* const fout = fopen_orDie(outName, "wb");
-    size_t const buffInSize = ZSTD_CStreamInSize();    /* can always read one full block */
+    /* Create the input and output buffers.
+     * They may be any size, but we recommend using these functions to size them.
+     * Performance will only suffer significantly for very tiny buffers.
+     */
+    size_t const buffInSize = ZSTD_CStreamInSize();
    void*  const buffIn  = malloc_orDie(buffInSize);
-    size_t const buffOutSize = ZSTD_CStreamOutSize();  /* can always flush a full block */
+    size_t const buffOutSize = ZSTD_CStreamOutSize();
    void*  const buffOut = malloc_orDie(buffOutSize);

-    ZSTD_CStream* const cstream = ZSTD_createCStream();
-    if (cstream==NULL) { fprintf(stderr, "ZSTD_createCStream() error \n"); exit(10); }
-    size_t const initResult = ZSTD_initCStream(cstream, cLevel);
-    if (ZSTD_isError(initResult)) {
-        fprintf(stderr, "ZSTD_initCStream() error : %s \n",
-                    ZSTD_getErrorName(initResult));
-        exit(11);
-    }
+    /* Create the context. */
+    ZSTD_CCtx* const cctx = ZSTD_createCCtx();
+    CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");

-    size_t read, toRead = buffInSize;
-    while( (read = fread_orDie(buffIn, toRead, fin)) ) {
+    /* Set any parameters you want.
+     * Here we set the compression level, and enable the checksum.
+     */
+    CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, cLevel) );
+    CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1) );
+
+    /* This loop read from the input file, compresses that entire chunk,
+     * and writes all output produced to the output file.
+     */
+    size_t const toRead = buffInSize;
+    size_t read;
+    while ((read = fread_orDie(buffIn, toRead, fin))) {
+        /* Select the flush mode.
+         * If the read may not be finished (read == toRead) we use
+         * ZSTD_e_continue. If this is the last chunk, we use ZSTD_e_end.
+         * Zstd optimizes the case where the first flush mode is ZSTD_e_end,
+         * since it knows it is compressing the entire source in one pass.
+         */
+        int const lastChunk = (read < toRead);
+        ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue;
+        /* Set the input buffer to what we just read.
+         * We compress until the input buffer is empty, each time flushing the
+         * output.
+         */
        ZSTD_inBuffer input = { buffIn, read, 0 };
-        while (input.pos < input.size) {
+        int finished;
+        do {
+            /* Compress into the output buffer and write all of the output to
+             * the file so we can reuse the buffer next iteration.
+             */
            ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
-            toRead = ZSTD_compressStream(cstream, &output , &input);   /* toRead is guaranteed to be <= ZSTD_CStreamInSize() */
-            if (ZSTD_isError(toRead)) {
-                fprintf(stderr, "ZSTD_compressStream() error : %s \n",
-                                ZSTD_getErrorName(toRead));
-                exit(12);
-            }
-            if (toRead > buffInSize) toRead = buffInSize;   /* Safely handle case when `buffInSize` is manually changed to a value < ZSTD_CStreamInSize()*/
+            size_t const remaining = ZSTD_compressStream2(cctx, &output , &input, mode);
+            CHECK_ZSTD(remaining);
            fwrite_orDie(buffOut, output.pos, fout);
-        }
+            /* If we're on the last chunk we're finished when zstd returns 0,
+             * which means its consumed all the input AND finished the frame.
+             * Otherwise, we're finished when we've consumed all the input.
+             */
+            finished = lastChunk ? (remaining == 0) : (input.pos == input.size);
+        } while (!finished);
+        CHECK(input.pos == input.size,
+              "Impossible: zstd only returns 0 when the input is completely consumed!");
    }

-    ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
-    size_t const remainingToFlush = ZSTD_endStream(cstream, &output);   /* close frame */
-    if (remainingToFlush) { fprintf(stderr, "not fully flushed"); exit(13); }
-    fwrite_orDie(buffOut, output.pos, fout);
-
-    ZSTD_freeCStream(cstream);
+    ZSTD_freeCCtx(cctx);
    fclose_orDie(fout);
-    fclose_orDie(fin);    free(buffIn);
+    fclose_orDie(fin);
+    free(buffIn);
    free(buffOut);
 }

@@ -9,12 +9,10 @@
 */


-#include <stdlib.h>    // malloc, exit
-#include <stdio.h>     // fprintf, perror, feof
-#include <string.h>    // strerror
-#include <errno.h>     // errno
+#include <stdio.h>     // fprintf
+#include <stdlib.h>    // free
 #include <zstd.h>      // presumes zstd library is installed
-#include "utils.h"
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

 static void decompressFile_orDie(const char* fname)
 {
@@ -25,26 +23,40 @@ static void decompressFile_orDie(const char* fname)
    size_t const buffOutSize = ZSTD_DStreamOutSize();  /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */
    void*  const buffOut = malloc_orDie(buffOutSize);

-    ZSTD_DStream* const dstream = ZSTD_createDStream();
-    if (dstream==NULL) { fprintf(stderr, "ZSTD_createDStream() error \n"); exit(10); }
+    ZSTD_DCtx* const dctx = ZSTD_createDCtx();
+    CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");

-    /* In more complex scenarios, a file may consist of multiple appended frames (ex : pzstd).
-    *  The following example decompresses only the first frame.
-    *  It is compatible with other provided streaming examples */
-    size_t const initResult = ZSTD_initDStream(dstream);
-    if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_initDStream() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
-    size_t read, toRead = initResult;
+    /* This loop assumes that the input file is one or more concatenated zstd
+     * streams. This example won't work if there is trailing non-zstd data at
+     * the end, but streaming decompression in general handles this case.
+     * ZSTD_decompressStream() returns 0 exactly when the frame is completed,
+     * and doesn't consume input after the frame.
+     */
+    size_t const toRead = buffInSize;
+    size_t read;
    while ( (read = fread_orDie(buffIn, toRead, fin)) ) {
        ZSTD_inBuffer input = { buffIn, read, 0 };
+        /* Given a valid frame, zstd won't consume the last byte of the frame
+         * until it has flushed all of the decompressed data of the frame.
+         * Therefore, instead of checking if the return code is 0, we can
+         * decompress just check if input.pos < input.size.
+         */
        while (input.pos < input.size) {
            ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
-            toRead = ZSTD_decompressStream(dstream, &output , &input);  /* toRead : size of next compressed block */
-            if (ZSTD_isError(toRead)) { fprintf(stderr, "ZSTD_decompressStream() error : %s \n", ZSTD_getErrorName(toRead)); exit(12); }
+            /* The return code is zero if the frame is complete, but there may
+             * be multiple frames concatenated together. Zstd will automatically
+             * reset the context when a frame is complete. Still, calling
+             * ZSTD_DCtx_reset() can be useful to reset the context to a clean
+             * state, for instance if the last decompression call returned an
+             * error.
+             */
+            size_t const ret = ZSTD_decompressStream(dctx, &output , &input);
+            CHECK_ZSTD(ret);
            fwrite_orDie(buffOut, output.pos, fout);
        }
    }

-    ZSTD_freeDStream(dstream);
+    ZSTD_freeDCtx(dctx);
    fclose_orDie(fin);
    fclose_orDie(fout);
    free(buffIn);
@@ -16,9 +16,10 @@


 /*===   Dependencies   ===*/
-#include <stdio.h>   /* printf */
+#include <stdio.h>     // printf
 #define ZSTD_STATIC_LINKING_ONLY
-#include "zstd.h"
+#include <zstd.h>      // presumes zstd library is installed
+#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()


 /*===   functions   ===*/
@@ -61,90 +62,75 @@ int main(int argc, char const *argv[]) {
        char const dataToCompress[INPUT_SIZE] = "abcde";
        char compressedData[COMPRESSED_SIZE];
        char decompressedData[INPUT_SIZE];
-        ZSTD_CStream* const cstream = ZSTD_createCStream();
-        if (cstream==NULL) {
-            printf("Level %i : ZSTD_CStream Memory allocation failure \n", compressionLevel);
-            return 1;
-        }
+        /* the ZSTD_CCtx_params structure is a way to save parameters and use
+         * them across multiple contexts. We use them here so we can call the
+         * function ZSTD_estimateCStreamSize_usingCCtxParams().
+         */
+        ZSTD_CCtx_params* const cctxParams = ZSTD_createCCtxParams();
+        CHECK(cctxParams != NULL, "ZSTD_createCCtxParams() failed!");

-        /* forces compressor to use maximum memory size for given compression level,
-         * by not providing any information on input size */
-        ZSTD_parameters params = ZSTD_getParams(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0);
-        if (wLog) { /* special mode : specific wLog */
-            printf("Using custom compression parameter : level 1 + wLog=%u \n", wLog);
-            params = ZSTD_getParams(1 /*compressionLevel*/,
-                                    1 << wLog /*estimatedSrcSize*/,
-                                    0 /*no dictionary*/);
-            size_t const error = ZSTD_initCStream_advanced(cstream, NULL, 0, params, ZSTD_CONTENTSIZE_UNKNOWN);
-            if (ZSTD_isError(error)) {
-                printf("ZSTD_initCStream_advanced error : %s \n", ZSTD_getErrorName(error));
-                return 1;
-            }
-        } else {
-            size_t const error = ZSTD_initCStream(cstream, compressionLevel);
-            if (ZSTD_isError(error)) {
-                printf("ZSTD_initCStream error : %s \n", ZSTD_getErrorName(error));
-                return 1;
-            }
-        }
+        /* Set the compression level. */
+        CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, compressionLevel) );
+        /* Set the window log.
+         * The value 0 means use the default window log, which is equivalent to
+         * not setting it.
+         */
+        CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_windowLog, wLog) );

+        /* Force the compressor to allocate the maximum memory size for a given
+         * level by not providing the pledged source size, or calling
+         * ZSTD_compressStream2() with ZSTD_e_end.
+         */
+        ZSTD_CCtx* const cctx = ZSTD_createCCtx();
+        CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");
+        CHECK_ZSTD( ZSTD_CCtx_setParametersUsingCCtxParams(cctx, cctxParams) );
        size_t compressedSize;
-        {   ZSTD_inBuffer inBuff = { dataToCompress, sizeof(dataToCompress), 0 };
+        {
+            ZSTD_inBuffer inBuff = { dataToCompress, sizeof(dataToCompress), 0 };
            ZSTD_outBuffer outBuff = { compressedData, sizeof(compressedData), 0 };
-            size_t const cError = ZSTD_compressStream(cstream, &outBuff, &inBuff);
-            if (ZSTD_isError(cError)) {
-                printf("ZSTD_compressStream error : %s \n", ZSTD_getErrorName(cError));
-                return 1;
-            }
-            size_t const fError = ZSTD_endStream(cstream, &outBuff);
-            if (ZSTD_isError(fError)) {
-                printf("ZSTD_endStream error : %s \n", ZSTD_getErrorName(fError));
-                return 1;
-            }
+            CHECK_ZSTD( ZSTD_compressStream(cctx, &outBuff, &inBuff) );
+            size_t const remaining = ZSTD_endStream(cctx, &outBuff);
+            CHECK_ZSTD(remaining);
+            CHECK(remaining == 0, "Frame not flushed!");
            compressedSize = outBuff.pos;
        }

-        ZSTD_DStream* dstream = ZSTD_createDStream();
-        if (dstream==NULL) {
-            printf("Level %i : ZSTD_DStream Memory allocation failure \n", compressionLevel);
-            return 1;
-        }
-        {   size_t const error = ZSTD_initDStream(dstream);
-            if (ZSTD_isError(error)) {
-                printf("ZSTD_initDStream error : %s \n", ZSTD_getErrorName(error));
-                return 1;
-            }
-        }
-        /* forces decompressor to use maximum memory size, as decompressed size is not known */
+        ZSTD_DCtx* const dctx = ZSTD_createDCtx();
+        CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");
+        /* Set the maximum allowed window log.
+         * The value 0 means use the default window log, which is equivalent to
+         * not setting it.
+         */
+        CHECK_ZSTD( ZSTD_DCtx_setParameter(dctx, ZSTD_d_windowLogMax, wLog) );
+        /* forces decompressor to use maximum memory size, since the
+         * decompressed size is not stored in the frame header.
+         */
        {   ZSTD_inBuffer inBuff = { compressedData, compressedSize, 0 };
            ZSTD_outBuffer outBuff = { decompressedData, sizeof(decompressedData), 0 };
-            size_t const dResult = ZSTD_decompressStream(dstream, &outBuff, &inBuff);
-            if (ZSTD_isError(dResult)) {
-                printf("ZSTD_decompressStream error : %s \n", ZSTD_getErrorName(dResult));
-                return 1;
-            }
-            if (dResult != 0) {
-                printf("ZSTD_decompressStream error : unfinished decompression \n");
-                return 1;
-            }
-            if (outBuff.pos != sizeof(dataToCompress)) {
-                printf("ZSTD_decompressStream error : incorrect decompression \n");
-                return 1;
-            }
+            size_t const remaining = ZSTD_decompressStream(dctx, &outBuff, &inBuff);
+            CHECK_ZSTD(remaining);
+            CHECK(remaining == 0, "Frame not complete!");
+            CHECK(outBuff.pos == sizeof(dataToCompress), "Bad decompression!");
        }

-        size_t const cstreamSize = ZSTD_sizeof_CStream(cstream);
-        size_t const cstreamEstimatedSize = wLog ?
-                ZSTD_estimateCStreamSize_usingCParams(params.cParams) :
-                ZSTD_estimateCStreamSize(compressionLevel);
-        size_t const dstreamSize = ZSTD_sizeof_DStream(dstream);
+        size_t const cstreamSize = ZSTD_sizeof_CStream(cctx);
+        size_t const cstreamEstimatedSize = ZSTD_estimateCStreamSize_usingCCtxParams(cctxParams);
+        size_t const dstreamSize = ZSTD_sizeof_DStream(dctx);
+        size_t const dstreamEstimatedSize = ZSTD_estimateDStreamSize_fromFrame(compressedData, compressedSize);

-        printf("Level %2i : Compression Mem = %5u KB (estimated : %5u KB) ; Decompression Mem = %4u KB \n",
+        CHECK(cstreamSize <= cstreamEstimatedSize, "Compression mem (%u) > estimated (%u)",
+                (unsigned)cstreamSize, (unsigned)cstreamEstimatedSize);
+        CHECK(dstreamSize <= dstreamEstimatedSize, "Decompression mem (%u) > estimated (%u)",
+                (unsigned)dstreamSize, (unsigned)dstreamEstimatedSize);
+
+        printf("Level %2i : Compression Mem = %5u KB (estimated : %5u KB) ; Decompression Mem = %4u KB (estimated : %5u KB)\n",
                compressionLevel,
-                (unsigned)(cstreamSize>>10), (unsigned)(cstreamEstimatedSize>>10), (unsigned)(dstreamSize>>10));
+                (unsigned)(cstreamSize>>10), (unsigned)(cstreamEstimatedSize>>10),
+                (unsigned)(dstreamSize>>10), (unsigned)(dstreamEstimatedSize>>10));

-        ZSTD_freeDStream(dstream);
-        ZSTD_freeCStream(cstream);
+        ZSTD_freeDCtx(dctx);
+        ZSTD_freeCCtx(cctx);
+        ZSTD_freeCCtxParams(cctxParams);
        if (wLog) break;  /* single test */
    }
    return 0;
@@ -17,6 +17,7 @@ LIBVER_MINOR := $(shell echo $(LIBVER_MINOR_SCRIPT))
 LIBVER_PATCH := $(shell echo $(LIBVER_PATCH_SCRIPT))
 LIBVER := $(shell echo $(LIBVER_SCRIPT))
 VERSION?= $(LIBVER)
+CCVER := $(shell $(CC) --version)

 CPPFLAGS+= -I. -I./common -DXXH_NAMESPACE=ZSTD_
 ifeq ($(OS),Windows_NT)   # MinGW assumed
@@ -25,7 +26,7 @@ endif
 CFLAGS  ?= -O3
 DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-            -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
+            -Wstrict-prototypes -Wundef -Wpointer-arith \
            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
            -Wredundant-decls -Wmissing-prototypes -Wc++-compat
 CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
@@ -45,6 +46,10 @@ ZDICT_FILES := $(sort $(wildcard dictBuilder/*.c))
 ZDEPR_FILES := $(sort $(wildcard deprecated/*.c))
 ZSTD_FILES := $(ZSTDCOMMON_FILES)

+ifeq ($(findstring GCC,$(CCVER)),GCC)
+decompress/zstd_decompress_block.o :	CFLAGS+=-fno-tree-vectorize
+endif
+
 ZSTD_LEGACY_SUPPORT ?= 5
 ZSTD_LIB_COMPRESSION ?= 1
 ZSTD_LIB_DECOMPRESSION ?= 1
@@ -56,6 +61,7 @@ ZSTD_FORCE_DECOMPRESS_SHORT ?= 0
 ZSTD_FORCE_DECOMPRESS_LONG ?= 0
 ZSTD_NO_INLINE ?= 0
 ZSTD_STRIP_ERROR_STRINGS ?= 0
+ZSTD_LEGACY_MULTITHREADED_API ?= 0

 ifeq ($(ZSTD_LIB_COMPRESSION), 0)
 	ZSTD_LIB_DICTBUILDER = 0
@@ -107,6 +113,10 @@ ifneq ($(ZSTD_STRIP_ERROR_STRINGS), 0)
 	CFLAGS += -DZSTD_STRIP_ERROR_STRINGS
 endif

+ifneq ($(ZSTD_LEGACY_MULTITHREADED_API), 0)
+	CFLAGS += -DZSTD_LEGACY_MULTITHREADED_API
+endif
+
 ifneq ($(ZSTD_LEGACY_SUPPORT), 0)
 ifeq ($(shell test $(ZSTD_LEGACY_SUPPORT) -lt 8; echo $$?), 0)
 	ZSTD_FILES += $(shell ls legacy/*.c | $(GREP) 'v0[$(ZSTD_LEGACY_SUPPORT)-7]')
@@ -151,8 +161,7 @@ ifneq (,$(filter Windows%,$(OS)))
 LIBZSTD = dll\libzstd.dll
 $(LIBZSTD): $(ZSTD_FILES)
 	@echo compiling dynamic library $(LIBVER)
-	@$(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -shared $^ -o $@
-	dlltool -D $@ -d dll\libzstd.def -l dll\libzstd.lib
+	$(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -Wl,--out-implib,dll\libzstd.lib -shared $^ -o $@

 else

@@ -31,8 +31,6 @@ note that it's necessary to request the `-pthread` flag during link stage.

 Multithreading capabilities are exposed
 via the [advanced API defined in `lib/zstd.h`](https://github.com/facebook/zstd/blob/v1.3.8/lib/zstd.h#L592).
-This API is still labelled experimental,
-but is expected to become "stable" in the near future.


 #### API
@@ -110,6 +108,10 @@ The file structure is designed to make this selection manually achievable for an
  which removes the error messages that are otherwise returned by
  `ZSTD_getErrorName`.

+- While invoking `make libzstd`, the build macro `ZSTD_LEGACY_MULTITHREADED_API=1`
+  will expose the deprecated `ZSTDMT` API exposed by `zstdmt_compress.h` in
+  the shared library, which is now hidden by default.
+

 #### Windows : using MinGW+MSYS to create DLL

@@ -40,7 +40,7 @@

 /**
 * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
- * parameters. They must be inlined for the compiler to elimininate the constant
+ * parameters. They must be inlined for the compiler to eliminate the constant
 * branches.
 */
 #define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
@@ -127,6 +127,13 @@
    }                                     \
 }

+/* vectorization */
+#if !defined(__clang__) && defined(__GNUC__)
+#  define DONT_VECTORIZE __attribute__((optimize("no-tree-vectorize")))
+#else
+#  define DONT_VECTORIZE
+#endif
+
 /* disable warnings */
 #ifdef _MSC_VER    /* Visual Studio */
 #  include <intrin.h>                    /* For Visual 2005 */
@@ -358,7 +358,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 typedef enum {
   FSE_repeat_none,  /**< Cannot use the previous table */
   FSE_repeat_check, /**< Can use the previous table but it must be checked */
-   FSE_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
+   FSE_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
 } FSE_repeat;

 /* *****************************************
@@ -14,8 +14,8 @@
 * This file will hold wrapper for systems, which do not support pthreads
 */

-/* create fake symbol to avoid empty trnaslation unit warning */
-int g_ZSTD_threading_useles_symbol;
+/* create fake symbol to avoid empty translation unit warning */
+int g_ZSTD_threading_useless_symbol;

 #if defined(ZSTD_MULTITHREAD) && defined(_WIN32)

@@ -66,10 +66,10 @@
 /* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */

 /*!XXH_FORCE_NATIVE_FORMAT :
- * By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
+ * By default, xxHash library provides endian-independent Hash values, based on little-endian convention.
 * Results are therefore identical for little-endian and big-endian CPU.
 * This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
- * Should endian-independance be of no importance for your application, you may set the #define below to 1,
+ * Should endian-independence be of no importance for your application, you may set the #define below to 1,
 * to improve speed for Big-endian CPU.
 * This option has no impact on Little_Endian CPU.
 */
@@ -34,7 +34,6 @@
 #endif
 #include "xxhash.h"                /* XXH_reset, update, digest */

-
 #if defined (__cplusplus)
 extern "C" {
 #endif
@@ -53,8 +52,50 @@ extern "C" {
 #undef MAX
 #define MIN(a,b) ((a)<(b) ? (a) : (b))
 #define MAX(a,b) ((a)>(b) ? (a) : (b))
-#define CHECK_F(f) { size_t const errcod = f; if (ERR_isError(errcod)) return errcod; }  /* check and Forward error code */
-#define CHECK_E(f, e) { size_t const errcod = f; if (ERR_isError(errcod)) return ERROR(e); }  /* check and send Error code */
+
+/**
+ * Return the specified error if the condition evaluates to true.
+ *
+ * In debug modes, prints additional information. In order to do that
+ * (particularly, printing the conditional that failed), this can't just wrap
+ * RETURN_ERROR().
+ */
+#define RETURN_ERROR_IF(cond, err, ...) \
+  if (cond) { \
+    RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  }
+
+/**
+ * Unconditionally return the specified error.
+ *
+ * In debug modes, prints additional information.
+ */
+#define RETURN_ERROR(err, ...) \
+  do { \
+    RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  } while(0);
+
+/**
+ * If the provided expression evaluates to an error code, returns that error code.
+ *
+ * In debug modes, prints additional information.
+ */
+#define FORWARD_IF_ERROR(err, ...) \
+  do { \
+    size_t const err_code = (err); \
+    if (ERR_isError(err_code)) { \
+      RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \
+      RAWLOG(3, ": " __VA_ARGS__); \
+      RAWLOG(3, "\n"); \
+      return err_code; \
+    } \
+  } while(0);


 /*-*************************************
@@ -151,19 +192,72 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
 *  Shared functions to include for inlining
 *********************************************/
 static void ZSTD_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
+
 #define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
+static void ZSTD_copy16(void* dst, const void* src) { memcpy(dst, src, 16); }
+#define COPY16(d,s) { ZSTD_copy16(d,s); d+=16; s+=16; }
+
+#define WILDCOPY_OVERLENGTH 8
+#define VECLEN 16
+
+typedef enum {
+    ZSTD_no_overlap,
+    ZSTD_overlap_src_before_dst,
+    /*  ZSTD_overlap_dst_before_src, */
+} ZSTD_overlap_e;

 /*! ZSTD_wildcopy() :
 *  custom version of memcpy(), can overwrite up to WILDCOPY_OVERLENGTH bytes (if length==0) */
-#define WILDCOPY_OVERLENGTH 8
-MEM_STATIC void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length)
+MEM_STATIC FORCE_INLINE_ATTR DONT_VECTORIZE
+void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e ovtype)
 {
+    ptrdiff_t diff = (BYTE*)dst - (const BYTE*)src;
    const BYTE* ip = (const BYTE*)src;
    BYTE* op = (BYTE*)dst;
    BYTE* const oend = op + length;
-    do
-        COPY8(op, ip)
-    while (op < oend);
+
+    assert(diff >= 8 || (ovtype == ZSTD_no_overlap && diff < -8));
+    if (length < VECLEN || (ovtype == ZSTD_overlap_src_before_dst && diff < VECLEN)) {
+      do
+          COPY8(op, ip)
+      while (op < oend);
+    }
+    else {
+      if ((length & 8) == 0)
+        COPY8(op, ip);
+      do {
+        COPY16(op, ip);
+      }
+      while (op < oend);
+    }
+}
+
+/*! ZSTD_wildcopy_16min() :
+ *  same semantics as ZSTD_wilcopy() except guaranteed to be able to copy 16 bytes at the start */
+MEM_STATIC FORCE_INLINE_ATTR DONT_VECTORIZE
+void ZSTD_wildcopy_16min(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e ovtype)
+{
+    ptrdiff_t diff = (BYTE*)dst - (const BYTE*)src;
+    const BYTE* ip = (const BYTE*)src;
+    BYTE* op = (BYTE*)dst;
+    BYTE* const oend = op + length;
+
+    assert(length >= 8);
+    assert(diff >= 8 || (ovtype == ZSTD_no_overlap && diff < -8));
+
+    if (ovtype == ZSTD_overlap_src_before_dst && diff < VECLEN) {
+      do
+          COPY8(op, ip)
+      while (op < oend);
+    }
+    else {
+      if ((length & 8) == 0)
+        COPY8(op, ip);
+      do {
+        COPY16(op, ip);
+      }
+      while (op < oend);
+    }
 }

 MEM_STATIC void ZSTD_wildcopy_e(void* dst, const void* src, void* dstEnd)   /* should be faster for decoding, but strangely, not verified on all platform */
@@ -200,6 +294,17 @@ typedef struct {
    U32   longLengthPos;
 } seqStore_t;

+/**
+ * Contains the compressed frame size and an upper-bound for the decompressed frame size.
+ * Note: before using `compressedSize`, check for errors using ZSTD_isError().
+ *       similarly, before using `decompressedBound`, check for errors using:
+ *          `decompressedBound != ZSTD_CONTENTSIZE_ERROR`
+ */
+typedef struct {
+    size_t compressedSize;
+    unsigned long long decompressedBound;
+} ZSTD_frameSizeInfo;   /* decompress & legacy */
+
 const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
 void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */

@@ -129,9 +129,9 @@ size_t FSE_buildCTable_wksp(FSE_CTable* ct,
    {   U32 position = 0;
        U32 symbol;
        for (symbol=0; symbol<=maxSymbolValue; symbol++) {
-            int nbOccurences;
+            int nbOccurrences;
            int const freq = normalizedCounter[symbol];
-            for (nbOccurences=0; nbOccurences<freq; nbOccurences++) {
+            for (nbOccurrences=0; nbOccurrences<freq; nbOccurrences++) {
                tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
                position = (position + step) & tableMask;
                while (position > highThreshold)
@@ -21,6 +21,8 @@
 #define HUF_STATIC_LINKING_ONLY
 #include "huf.h"
 #include "zstd_compress_internal.h"
+#include "zstd_compress_sequences.h"
+#include "zstd_compress_literals.h"
 #include "zstd_fast.h"
 #include "zstd_double_fast.h"
 #include "zstd_lazy.h"
@@ -103,12 +105,31 @@ ZSTD_CCtx* ZSTD_initStaticCCtx(void *workspace, size_t workspaceSize)
    return cctx;
 }

+/**
+ * Clears and frees all of the dictionaries in the CCtx.
+ */
+static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx)
+{
+    ZSTD_free(cctx->localDict.dictBuffer, cctx->customMem);
+    ZSTD_freeCDict(cctx->localDict.cdict);
+    memset(&cctx->localDict, 0, sizeof(cctx->localDict));
+    memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));
+    cctx->cdict = NULL;
+}
+
+static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict)
+{
+    size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0;
+    size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict);
+    return bufferSize + cdictSize;
+}
+
 static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx)
 {
    assert(cctx != NULL);
    assert(cctx->staticSize == 0);
    ZSTD_free(cctx->workSpace, cctx->customMem); cctx->workSpace = NULL;
-    ZSTD_freeCDict(cctx->cdictLocal); cctx->cdictLocal = NULL;
+    ZSTD_clearAllDicts(cctx);
 #ifdef ZSTD_MULTITHREAD
    ZSTDMT_freeCCtx(cctx->mtctx); cctx->mtctx = NULL;
 #endif
@@ -117,7 +138,8 @@ static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx)
 size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
 {
    if (cctx==NULL) return 0;   /* support free on NULL */
-    if (cctx->staticSize) return ERROR(memory_allocation);   /* not compatible with static CCtx */
+    RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                    "not compatible with static CCtx");
    ZSTD_freeCCtxContent(cctx);
    ZSTD_free(cctx, cctx->customMem);
    return 0;
@@ -139,7 +161,7 @@ size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx)
 {
    if (cctx==NULL) return 0;   /* support sizeof on NULL */
    return sizeof(*cctx) + cctx->workSpaceSize
-           + ZSTD_sizeof_CDict(cctx->cdictLocal)
+           + ZSTD_sizeof_localDict(cctx->localDict)
           + ZSTD_sizeof_mtctx(cctx);
 }

@@ -195,7 +217,7 @@ size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params)
 }

 size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) {
-    if (!cctxParams) { return ERROR(GENERIC); }
+    RETURN_ERROR_IF(!cctxParams, GENERIC);
    memset(cctxParams, 0, sizeof(*cctxParams));
    cctxParams->compressionLevel = compressionLevel;
    cctxParams->fParams.contentSizeFlag = 1;
@@ -204,8 +226,8 @@ size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel)

 size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params)
 {
-    if (!cctxParams) { return ERROR(GENERIC); }
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
+    RETURN_ERROR_IF(!cctxParams, GENERIC);
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
    memset(cctxParams, 0, sizeof(*cctxParams));
    cctxParams->cParams = params.cParams;
    cctxParams->fParams = params.fParams;
@@ -359,6 +381,17 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
        bounds.upperBound = ZSTD_dictForceCopy;       /* note : how to ensure at compile time that this is the highest value enum ? */
        return bounds;

+    case ZSTD_c_literalCompressionMode:
+        ZSTD_STATIC_ASSERT(ZSTD_lcm_auto < ZSTD_lcm_huffman && ZSTD_lcm_huffman < ZSTD_lcm_uncompressed);
+        bounds.lowerBound = ZSTD_lcm_auto;
+        bounds.upperBound = ZSTD_lcm_uncompressed;
+        return bounds;
+
+    case ZSTD_c_targetCBlockSize:
+        bounds.lowerBound = ZSTD_TARGETCBLOCKSIZE_MIN;
+        bounds.upperBound = ZSTD_TARGETCBLOCKSIZE_MAX;
+        return bounds;
+
    default:
        {   ZSTD_bounds const boundError = { ERROR(parameter_unsupported), 0, 0 };
            return boundError;
@@ -366,22 +399,22 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
    }
 }

-/* ZSTD_cParam_withinBounds:
- * @return 1 if value is within cParam bounds,
- * 0 otherwise */
-static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
+/* ZSTD_cParam_clampBounds:
+ * Clamps the value into the bounded range.
+ */
+static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value)
 {
    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
-    if (ZSTD_isError(bounds.error)) return 0;
-    if (value < bounds.lowerBound) return 0;
-    if (value > bounds.upperBound) return 0;
-    return 1;
+    if (ZSTD_isError(bounds.error)) return bounds.error;
+    if (*value < bounds.lowerBound) *value = bounds.lowerBound;
+    if (*value > bounds.upperBound) *value = bounds.upperBound;
+    return 0;
 }

-#define BOUNDCHECK(cParam, val) {                  \
-    if (!ZSTD_cParam_withinBounds(cParam,val)) {   \
-        return ERROR(parameter_outOfBound);        \
-}   }
+#define BOUNDCHECK(cParam, val) { \
+    RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \
+                    parameter_outOfBound); \
+}


 static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
@@ -413,6 +446,8 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
    case ZSTD_c_ldmBucketSizeLog:
    case ZSTD_c_ldmHashRateLog:
    case ZSTD_c_forceAttachDict:
+    case ZSTD_c_literalCompressionMode:
+    case ZSTD_c_targetCBlockSize:
    default:
        return 0;
    }
@@ -425,18 +460,17 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
        if (ZSTD_isUpdateAuthorized(param)) {
            cctx->cParamsChanged = 1;
        } else {
-            return ERROR(stage_wrong);
+            RETURN_ERROR(stage_wrong);
    }   }

    switch(param)
    {
-    case ZSTD_c_format :
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
+    case ZSTD_c_nbWorkers:
+        RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported,
+                        "MT not compatible with static alloc");
+        break;

    case ZSTD_c_compressionLevel:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
    case ZSTD_c_windowLog:
    case ZSTD_c_hashLog:
    case ZSTD_c_chainLog:
@@ -444,49 +478,33 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
    case ZSTD_c_minMatch:
    case ZSTD_c_targetLength:
    case ZSTD_c_strategy:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_ldmHashRateLog:
+    case ZSTD_c_format:
    case ZSTD_c_contentSizeFlag:
    case ZSTD_c_checksumFlag:
    case ZSTD_c_dictIDFlag:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
-    case ZSTD_c_forceMaxWindow :  /* Force back-references to remain < windowSize,
-                                   * even when referencing into Dictionary content.
-                                   * default : 0 when using a CDict, 1 when using a Prefix */
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_forceMaxWindow:
    case ZSTD_c_forceAttachDict:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
-    case ZSTD_c_nbWorkers:
-        if ((value!=0) && cctx->staticSize) {
-            return ERROR(parameter_unsupported);  /* MT not compatible with static alloc */
-        }
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_literalCompressionMode:
    case ZSTD_c_jobSize:
    case ZSTD_c_overlapLog:
    case ZSTD_c_rsyncable:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
    case ZSTD_c_enableLongDistanceMatching:
    case ZSTD_c_ldmHashLog:
    case ZSTD_c_ldmMinMatch:
    case ZSTD_c_ldmBucketSizeLog:
-    case ZSTD_c_ldmHashRateLog:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
+    case ZSTD_c_targetCBlockSize:
+        break;

-    default: return ERROR(parameter_unsupported);
+    default: RETURN_ERROR(parameter_unsupported);
    }
+    return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value);
 }

-size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
-                                   ZSTD_cParameter param, int value)
+size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
+                                    ZSTD_cParameter param, int value)
 {
-    DEBUGLOG(4, "ZSTD_CCtxParam_setParameter (%i, %i)", (int)param, value);
+    DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value);
    switch(param)
    {
    case ZSTD_c_format :
@@ -495,11 +513,9 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
        return (size_t)CCtxParams->format;

    case ZSTD_c_compressionLevel : {
-        int cLevel = value;
-        if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel();
-        if (cLevel < ZSTD_minCLevel()) cLevel = ZSTD_minCLevel();
-        if (cLevel) {  /* 0 : does not change current level */
-            CCtxParams->compressionLevel = cLevel;
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        if (value) {  /* 0 : does not change current level */
+            CCtxParams->compressionLevel = value;
        }
        if (CCtxParams->compressionLevel >= 0) return CCtxParams->compressionLevel;
        return 0;  /* return type (size_t) cannot represent negative values */
@@ -573,33 +589,55 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
        return CCtxParams->attachDictPref;
    }

+    case ZSTD_c_literalCompressionMode : {
+        const ZSTD_literalCompressionMode_e lcm = (ZSTD_literalCompressionMode_e)value;
+        BOUNDCHECK(ZSTD_c_literalCompressionMode, lcm);
+        CCtxParams->literalCompressionMode = lcm;
+        return CCtxParams->literalCompressionMode;
+    }
+
    case ZSTD_c_nbWorkers :
 #ifndef ZSTD_MULTITHREAD
-        if (value!=0) return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
        return 0;
 #else
-        return ZSTDMT_CCtxParam_setNbWorkers(CCtxParams, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        CCtxParams->nbWorkers = value;
+        return CCtxParams->nbWorkers;
 #endif

    case ZSTD_c_jobSize :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_jobSize, value);
+        /* Adjust to the minimum non-default value. */
+        if (value != 0 && value < ZSTDMT_JOBSIZE_MIN)
+            value = ZSTDMT_JOBSIZE_MIN;
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        assert(value >= 0);
+        CCtxParams->jobSize = value;
+        return CCtxParams->jobSize;
 #endif

    case ZSTD_c_overlapLog :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_overlapLog, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value));
+        CCtxParams->overlapLog = value;
+        return CCtxParams->overlapLog;
 #endif

    case ZSTD_c_rsyncable :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_rsyncable, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value));
+        CCtxParams->rsyncable = value;
+        return CCtxParams->rsyncable;
 #endif

    case ZSTD_c_enableLongDistanceMatching :
@@ -625,21 +663,27 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
        return CCtxParams->ldmParams.bucketSizeLog;

    case ZSTD_c_ldmHashRateLog :
-        if (value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN)
-            return ERROR(parameter_outOfBound);
+        RETURN_ERROR_IF(value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN,
+                        parameter_outOfBound);
        CCtxParams->ldmParams.hashRateLog = value;
        return CCtxParams->ldmParams.hashRateLog;

-    default: return ERROR(parameter_unsupported);
+    case ZSTD_c_targetCBlockSize :
+        if (value!=0)   /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_targetCBlockSize, value);
+        CCtxParams->targetCBlockSize = value;
+        return CCtxParams->targetCBlockSize;
+
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
    }
 }

 size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value)
 {
-    return ZSTD_CCtxParam_getParameter(&cctx->requestedParams, param, value);
+    return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value);
 }

-size_t ZSTD_CCtxParam_getParameter(
+size_t ZSTD_CCtxParams_getParameter(
        ZSTD_CCtx_params* CCtxParams, ZSTD_cParameter param, int* value)
 {
    switch(param)
@@ -651,13 +695,13 @@ size_t ZSTD_CCtxParam_getParameter(
        *value = CCtxParams->compressionLevel;
        break;
    case ZSTD_c_windowLog :
-        *value = CCtxParams->cParams.windowLog;
+        *value = (int)CCtxParams->cParams.windowLog;
        break;
    case ZSTD_c_hashLog :
-        *value = CCtxParams->cParams.hashLog;
+        *value = (int)CCtxParams->cParams.hashLog;
        break;
    case ZSTD_c_chainLog :
-        *value = CCtxParams->cParams.chainLog;
+        *value = (int)CCtxParams->cParams.chainLog;
        break;
    case ZSTD_c_searchLog :
        *value = CCtxParams->cParams.searchLog;
@@ -686,6 +730,9 @@ size_t ZSTD_CCtxParam_getParameter(
    case ZSTD_c_forceAttachDict :
        *value = CCtxParams->attachDictPref;
        break;
+    case ZSTD_c_literalCompressionMode :
+        *value = CCtxParams->literalCompressionMode;
+        break;
    case ZSTD_c_nbWorkers :
 #ifndef ZSTD_MULTITHREAD
        assert(CCtxParams->nbWorkers == 0);
@@ -694,7 +741,7 @@ size_t ZSTD_CCtxParam_getParameter(
        break;
    case ZSTD_c_jobSize :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
        assert(CCtxParams->jobSize <= INT_MAX);
        *value = (int)CCtxParams->jobSize;
@@ -702,14 +749,14 @@ size_t ZSTD_CCtxParam_getParameter(
 #endif
    case ZSTD_c_overlapLog :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
        *value = CCtxParams->overlapLog;
        break;
 #endif
    case ZSTD_c_rsyncable :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
        *value = CCtxParams->rsyncable;
        break;
@@ -729,7 +776,10 @@ size_t ZSTD_CCtxParam_getParameter(
    case ZSTD_c_ldmHashRateLog :
        *value = CCtxParams->ldmParams.hashRateLog;
        break;
-    default: return ERROR(parameter_unsupported);
+    case ZSTD_c_targetCBlockSize :
+        *value = (int)CCtxParams->targetCBlockSize;
+        break;
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
    }
    return 0;
 }
@@ -745,8 +795,8 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams(
        ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params)
 {
    DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams");
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    if (cctx->cdict) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->cdict, stage_wrong);

    cctx->requestedParams = *params;
    return 0;
@@ -755,33 +805,71 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams(
 ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize)
 {
    DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize);
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
    cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
    return 0;
 }

+/**
+ * Initializes the local dict using the requested parameters.
+ * NOTE: This does not use the pledged src size, because it may be used for more
+ * than one compression.
+ */
+static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx)
+{
+    ZSTD_localDict* const dl = &cctx->localDict;
+    ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(
+            &cctx->requestedParams, 0, dl->dictSize);
+    if (dl->dict == NULL) {
+        /* No local dictionary. */
+        assert(dl->dictBuffer == NULL);
+        assert(dl->cdict == NULL);
+        assert(dl->dictSize == 0);
+        return 0;
+    }
+    if (dl->cdict != NULL) {
+        assert(cctx->cdict == dl->cdict);
+        /* Local dictionary already initialized. */
+        return 0;
+    }
+    assert(dl->dictSize > 0);
+    assert(cctx->cdict == NULL);
+    assert(cctx->prefixDict.dict == NULL);
+
+    dl->cdict = ZSTD_createCDict_advanced(
+            dl->dict,
+            dl->dictSize,
+            ZSTD_dlm_byRef,
+            dl->dictContentType,
+            cParams,
+            cctx->customMem);
+    RETURN_ERROR_IF(!dl->cdict, memory_allocation);
+    cctx->cdict = dl->cdict;
+    return 0;
+}
+
 size_t ZSTD_CCtx_loadDictionary_advanced(
        ZSTD_CCtx* cctx, const void* dict, size_t dictSize,
        ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    if (cctx->staticSize) return ERROR(memory_allocation);  /* no malloc for static CCtx */
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                    "no malloc for static CCtx");
    DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize);
-    ZSTD_freeCDict(cctx->cdictLocal);  /* in case one already exists */
-    if (dict==NULL || dictSize==0) {   /* no dictionary mode */
-        cctx->cdictLocal = NULL;
-        cctx->cdict = NULL;
+    ZSTD_clearAllDicts(cctx);  /* in case one already exists */
+    if (dict == NULL || dictSize == 0)  /* no dictionary mode */
+        return 0;
+    if (dictLoadMethod == ZSTD_dlm_byRef) {
+        cctx->localDict.dict = dict;
    } else {
-        ZSTD_compressionParameters const cParams =
-                ZSTD_getCParamsFromCCtxParams(&cctx->requestedParams, cctx->pledgedSrcSizePlusOne-1, dictSize);
-        cctx->cdictLocal = ZSTD_createCDict_advanced(
-                                dict, dictSize,
-                                dictLoadMethod, dictContentType,
-                                cParams, cctx->customMem);
-        cctx->cdict = cctx->cdictLocal;
-        if (cctx->cdictLocal == NULL)
-            return ERROR(memory_allocation);
+        void* dictBuffer = ZSTD_malloc(dictSize, cctx->customMem);
+        RETURN_ERROR_IF(!dictBuffer, memory_allocation);
+        memcpy(dictBuffer, dict, dictSize);
+        cctx->localDict.dictBuffer = dictBuffer;
+        cctx->localDict.dict = dictBuffer;
    }
+    cctx->localDict.dictSize = dictSize;
+    cctx->localDict.dictContentType = dictContentType;
    return 0;
 }

@@ -801,9 +889,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s

 size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    /* Free the existing local cdict (if any) to save memory. */
+    ZSTD_clearAllDicts(cctx);
    cctx->cdict = cdict;
-    memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));  /* exclusive */
    return 0;
 }

@@ -815,8 +904,8 @@ size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSiz
 size_t ZSTD_CCtx_refPrefix_advanced(
        ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    cctx->cdict = NULL;   /* prefix discards any prior cdict */
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    ZSTD_clearAllDicts(cctx);
    cctx->prefixDict.dict = prefix;
    cctx->prefixDict.dictSize = prefixSize;
    cctx->prefixDict.dictContentType = dictContentType;
@@ -834,8 +923,8 @@ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset)
    }
    if ( (reset == ZSTD_reset_parameters)
      || (reset == ZSTD_reset_session_and_parameters) ) {
-        if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-        cctx->cdict = NULL;
+        RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+        ZSTD_clearAllDicts(cctx);
        return ZSTD_CCtxParams_reset(&cctx->requestedParams);
    }
    return 0;
@@ -847,12 +936,12 @@ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset)
    @return : 0, or an error code if one value is beyond authorized range */
 size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
 {
-    BOUNDCHECK(ZSTD_c_windowLog, cParams.windowLog);
-    BOUNDCHECK(ZSTD_c_chainLog,  cParams.chainLog);
-    BOUNDCHECK(ZSTD_c_hashLog,   cParams.hashLog);
-    BOUNDCHECK(ZSTD_c_searchLog, cParams.searchLog);
-    BOUNDCHECK(ZSTD_c_minMatch,  cParams.minMatch);
-    BOUNDCHECK(ZSTD_c_targetLength,cParams.targetLength);
+    BOUNDCHECK(ZSTD_c_windowLog, (int)cParams.windowLog);
+    BOUNDCHECK(ZSTD_c_chainLog,  (int)cParams.chainLog);
+    BOUNDCHECK(ZSTD_c_hashLog,   (int)cParams.hashLog);
+    BOUNDCHECK(ZSTD_c_searchLog, (int)cParams.searchLog);
+    BOUNDCHECK(ZSTD_c_minMatch,  (int)cParams.minMatch);
+    BOUNDCHECK(ZSTD_c_targetLength,(int)cParams.targetLength);
    BOUNDCHECK(ZSTD_c_strategy,  cParams.strategy);
    return 0;
 }
@@ -868,7 +957,7 @@ ZSTD_clampCParams(ZSTD_compressionParameters cParams)
        if ((int)val<bounds.lowerBound) val=(type)bounds.lowerBound;      \
        else if ((int)val>bounds.upperBound) val=(type)bounds.upperBound; \
    }
-#   define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, int)
+#   define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, unsigned)
    CLAMP(ZSTD_c_windowLog, cParams.windowLog);
    CLAMP(ZSTD_c_chainLog,  cParams.chainLog);
    CLAMP(ZSTD_c_hashLog,   cParams.hashLog);
@@ -888,10 +977,11 @@ static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
 }

 /** ZSTD_adjustCParams_internal() :
-    optimize `cPar` for a given input (`srcSize` and `dictSize`).
-    mostly downsizing to reduce memory consumption and initialization latency.
-    Both `srcSize` and `dictSize` are optional (use 0 if unknown).
-    Note : cPar is assumed validated. Use ZSTD_checkCParams() to ensure this condition. */
+ *  optimize `cPar` for a specified input (`srcSize` and `dictSize`).
+ *  mostly downsize to reduce memory consumption and initialization latency.
+ * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known.
+ *  note : for the time being, `srcSize==0` means "unknown" too, for compatibility with older convention.
+ *  condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */
 static ZSTD_compressionParameters
 ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
                            unsigned long long srcSize,
@@ -901,7 +991,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
    static const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1);
    assert(ZSTD_checkCParams(cPar)==0);

-    if (dictSize && (srcSize+1<2) /* srcSize unknown */ )
+    if (dictSize && (srcSize+1<2) /* ZSTD_CONTENTSIZE_UNKNOWN and 0 mean "unknown" */ )
        srcSize = minSrcSize;  /* presumed small when there is a dictionary */
    else if (srcSize == 0)
        srcSize = ZSTD_CONTENTSIZE_UNKNOWN;  /* 0 == unknown : presumed large */
@@ -922,7 +1012,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
    }

    if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN)
-        cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN;  /* required for frame header */
+        cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN;  /* minimum wlog required for valid frame header */

    return cPar;
 }
@@ -932,7 +1022,7 @@ ZSTD_adjustCParams(ZSTD_compressionParameters cPar,
                   unsigned long long srcSize,
                   size_t dictSize)
 {
-    cPar = ZSTD_clampCParams(cPar);
+    cPar = ZSTD_clampCParams(cPar);   /* resulting cPar is necessarily valid (all parameters within range) */
    return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize);
 }

@@ -973,8 +1063,7 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams,

 size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params)
 {
-    /* Estimate CCtx size is supported for single-threaded compression only. */
-    if (params->nbWorkers > 0) { return ERROR(GENERIC); }
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
    {   ZSTD_compressionParameters const cParams =
                ZSTD_getCParamsFromCCtxParams(params, 0, 0);
        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
@@ -1022,10 +1111,12 @@ size_t ZSTD_estimateCCtxSize(int compressionLevel)

 size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params)
 {
-    if (params->nbWorkers > 0) { return ERROR(GENERIC); }
-    {   size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
-        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << params->cParams.windowLog);
-        size_t const inBuffSize = ((size_t)1 << params->cParams.windowLog) + blockSize;
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
+    {   ZSTD_compressionParameters const cParams =
+                ZSTD_getCParamsFromCCtxParams(params, 0, 0);
+        size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
+        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
+        size_t const inBuffSize = ((size_t)1 << cParams.windowLog) + blockSize;
        size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1;
        size_t const streamingSize = inBuffSize + outBuffSize;

@@ -1197,15 +1288,14 @@ static void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs)
 }

 /*! ZSTD_invalidateMatchState()
- * Invalidate all the matches in the match finder tables.
- * Requires nextSrc and base to be set (can be NULL).
+ *  Invalidate all the matches in the match finder tables.
+ *  Requires nextSrc and base to be set (can be NULL).
 */
 static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms)
 {
    ZSTD_window_clear(&ms->window);

    ms->nextToUpdate = ms->window.dictLimit;
-    ms->nextToUpdate3 = ms->window.dictLimit;
    ms->loadedDictEnd = 0;
    ms->opt.litLengthSum = 0;  /* force reset of btopt stats */
    ms->dictMatchState = NULL;
@@ -1242,15 +1332,17 @@ static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_CCtx_params params, U64 pl

 typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset } ZSTD_compResetPolicy_e;

+typedef enum { ZSTD_resetTarget_CDict, ZSTD_resetTarget_CCtx } ZSTD_resetTarget_e;
+
 static void*
 ZSTD_reset_matchState(ZSTD_matchState_t* ms,
                      void* ptr,
                const ZSTD_compressionParameters* cParams,
-                      ZSTD_compResetPolicy_e const crp, U32 const forCCtx)
+                      ZSTD_compResetPolicy_e const crp, ZSTD_resetTarget_e const forWho)
 {
    size_t const chainSize = (cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cParams->chainLog);
    size_t const hSize = ((size_t)1) << cParams->hashLog;
-    U32    const hashLog3 = (forCCtx && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0;
+    U32    const hashLog3 = ((forWho == ZSTD_resetTarget_CCtx) && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0;
    size_t const h3Size = ((size_t)1) << hashLog3;
    size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);

@@ -1264,7 +1356,7 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms,
    ZSTD_invalidateMatchState(ms);

    /* opt parser space */
-    if (forCCtx && (cParams->strategy >= ZSTD_btopt)) {
+    if ((forWho == ZSTD_resetTarget_CCtx) && (cParams->strategy >= ZSTD_btopt)) {
        DEBUGLOG(4, "reserving optimal parser space");
        ms->opt.litFreq = (unsigned*)ptr;
        ms->opt.litLengthFreq = ms->opt.litFreq + (1<<Litbits);
@@ -1292,6 +1384,19 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms,
    return ptr;
 }

+/* ZSTD_indexTooCloseToMax() :
+ * minor optimization : prefer memset() rather than reduceIndex()
+ * which is measurably slow in some circumstances (reported for Visual Studio).
+ * Works when re-using a context for a lot of smallish inputs :
+ * if all inputs are smaller than ZSTD_INDEXOVERFLOW_MARGIN,
+ * memset() will be triggered before reduceIndex().
+ */
+#define ZSTD_INDEXOVERFLOW_MARGIN (16 MB)
+static int ZSTD_indexTooCloseToMax(ZSTD_window_t w)
+{
+    return (size_t)(w.nextSrc - w.base) > (ZSTD_CURRENT_MAX - ZSTD_INDEXOVERFLOW_MARGIN);
+}
+
 #define ZSTD_WORKSPACETOOLARGE_FACTOR 3 /* define "workspace is too large" as this number of times larger than needed */
 #define ZSTD_WORKSPACETOOLARGE_MAXDURATION 128  /* when workspace is continuously too large
                                         * during at least this number of times,
@@ -1303,7 +1408,7 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms,
    note : `params` are assumed fully validated at this stage */
 static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
                                      ZSTD_CCtx_params params,
-                                      U64 pledgedSrcSize,
+                                      U64 const pledgedSrcSize,
                                      ZSTD_compResetPolicy_e const crp,
                                      ZSTD_buffered_policy_e const zbuff)
 {
@@ -1315,13 +1420,21 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
        if (ZSTD_equivalentParams(zc->appliedParams, params,
                                  zc->inBuffSize,
                                  zc->seqStore.maxNbSeq, zc->seqStore.maxNbLit,
-                                  zbuff, pledgedSrcSize)) {
-            DEBUGLOG(4, "ZSTD_equivalentParams()==1 -> continue mode (wLog1=%u, blockSize1=%zu)",
-                        zc->appliedParams.cParams.windowLog, zc->blockSize);
+                                  zbuff, pledgedSrcSize) ) {
+            DEBUGLOG(4, "ZSTD_equivalentParams()==1 -> consider continue mode");
            zc->workSpaceOversizedDuration += (zc->workSpaceOversizedDuration > 0);   /* if it was too large, it still is */
-            if (zc->workSpaceOversizedDuration <= ZSTD_WORKSPACETOOLARGE_MAXDURATION)
+            if (zc->workSpaceOversizedDuration <= ZSTD_WORKSPACETOOLARGE_MAXDURATION) {
+                DEBUGLOG(4, "continue mode confirmed (wLog1=%u, blockSize1=%zu)",
+                            zc->appliedParams.cParams.windowLog, zc->blockSize);
+                if (ZSTD_indexTooCloseToMax(zc->blockState.matchState.window)) {
+                    /* prefer a reset, faster than a rescale */
+                    ZSTD_reset_matchState(&zc->blockState.matchState,
+                                           zc->entropyWorkspace + HUF_WORKSPACE_SIZE_U32,
+                                          &params.cParams,
+                                           crp, ZSTD_resetTarget_CCtx);
+                }
                return ZSTD_continueCCtx(zc, params, pledgedSrcSize);
-    }   }
+    }   }   }
    DEBUGLOG(4, "ZSTD_equivalentParams()==0 -> reset CCtx");

    if (params.ldmParams.enableLdm) {
@@ -1364,16 +1477,16 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
            DEBUGLOG(4, "windowSize: %zu - blockSize: %zu", windowSize, blockSize);

            if (workSpaceTooSmall || workSpaceWasteful) {
-                DEBUGLOG(4, "Need to resize workSpaceSize from %zuKB to %zuKB",
+                DEBUGLOG(4, "Resize workSpaceSize from %zuKB to %zuKB",
                            zc->workSpaceSize >> 10,
                            neededSpace >> 10);
-                /* static cctx : no resize, error out */
-                if (zc->staticSize) return ERROR(memory_allocation);
+
+                RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize");

                zc->workSpaceSize = 0;
                ZSTD_free(zc->workSpace, zc->customMem);
                zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
-                if (zc->workSpace == NULL) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(zc->workSpace == NULL, memory_allocation);
                zc->workSpaceSize = neededSpace;
                zc->workSpaceOversizedDuration = 0;

@@ -1406,7 +1519,10 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,

        ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock);

-        ptr = zc->entropyWorkspace + HUF_WORKSPACE_SIZE_U32;
+        ptr = ZSTD_reset_matchState(&zc->blockState.matchState,
+                                     zc->entropyWorkspace + HUF_WORKSPACE_SIZE_U32,
+                                    &params.cParams,
+                                     crp, ZSTD_resetTarget_CCtx);

        /* ldm hash table */
        /* initialize bucketOffsets table later for pointer alignment */
@@ -1424,8 +1540,6 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
        }
        assert(((size_t)ptr & 3) == 0); /* ensure ptr is properly aligned */

-        ptr = ZSTD_reset_matchState(&zc->blockState.matchState, ptr, &params.cParams, crp, /* forCCtx */ 1);
-
        /* sequences storage */
        zc->seqStore.maxNbSeq = maxNbSeq;
        zc->seqStore.sequencesStart = (seqDef*)ptr;
@@ -1502,15 +1616,14 @@ static int ZSTD_shouldAttachDict(const ZSTD_CDict* cdict,
                                 * handled in _enforceMaxDist */
 }

-static size_t ZSTD_resetCCtx_byAttachingCDict(
-    ZSTD_CCtx* cctx,
-    const ZSTD_CDict* cdict,
-    ZSTD_CCtx_params params,
-    U64 pledgedSrcSize,
-    ZSTD_buffered_policy_e zbuff)
+static size_t
+ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx,
+                        const ZSTD_CDict* cdict,
+                        ZSTD_CCtx_params params,
+                        U64 pledgedSrcSize,
+                        ZSTD_buffered_policy_e zbuff)
 {
-    {
-        const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams;
+    {   const ZSTD_compressionParameters* const cdict_cParams = &cdict->matchState.cParams;
        unsigned const windowLog = params.cParams.windowLog;
        assert(windowLog != 0);
        /* Resize working context table params for input only, since the dict
@@ -1522,8 +1635,7 @@ static size_t ZSTD_resetCCtx_byAttachingCDict(
        assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy);
    }

-    {
-        const U32 cdictEnd = (U32)( cdict->matchState.window.nextSrc
+    {   const U32 cdictEnd = (U32)( cdict->matchState.window.nextSrc
                                  - cdict->matchState.window.base);
        const U32 cdictLen = cdictEnd - cdict->matchState.window.dictLimit;
        if (cdictLen == 0) {
@@ -1540,9 +1652,9 @@ static size_t ZSTD_resetCCtx_byAttachingCDict(
                    cctx->blockState.matchState.window.base + cdictEnd;
                ZSTD_window_clear(&cctx->blockState.matchState.window);
            }
+            /* loadedDictEnd is expressed within the referential of the active context */
            cctx->blockState.matchState.loadedDictEnd = cctx->blockState.matchState.window.dictLimit;
-        }
-    }
+    }   }

    cctx->dictID = cdict->dictID;

@@ -1596,7 +1708,6 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx,
        ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState;
        dstMatchState->window       = srcMatchState->window;
        dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
-        dstMatchState->nextToUpdate3= srcMatchState->nextToUpdate3;
        dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
    }

@@ -1644,7 +1755,7 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
                            ZSTD_buffered_policy_e zbuff)
 {
    DEBUGLOG(5, "ZSTD_copyCCtx_internal");
-    if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong);

    memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
    {   ZSTD_CCtx_params params = dstCCtx->requestedParams;
@@ -1676,7 +1787,6 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
        ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState;
        dstMatchState->window       = srcMatchState->window;
        dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
-        dstMatchState->nextToUpdate3= srcMatchState->nextToUpdate3;
        dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
    }
    dstCCtx->dictID = srcCCtx->dictID;
@@ -1746,16 +1856,15 @@ static void ZSTD_reduceTable_btlazy2(U32* const table, U32 const size, U32 const

 /*! ZSTD_reduceIndex() :
 *   rescale all indexes to avoid future overflow (indexes are U32) */
-static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue)
+static void ZSTD_reduceIndex (ZSTD_matchState_t* ms, ZSTD_CCtx_params const* params, const U32 reducerValue)
 {
-    ZSTD_matchState_t* const ms = &zc->blockState.matchState;
-    {   U32 const hSize = (U32)1 << zc->appliedParams.cParams.hashLog;
+    {   U32 const hSize = (U32)1 << params->cParams.hashLog;
        ZSTD_reduceTable(ms->hashTable, hSize, reducerValue);
    }

-    if (zc->appliedParams.cParams.strategy != ZSTD_fast) {
-        U32 const chainSize = (U32)1 << zc->appliedParams.cParams.chainLog;
-        if (zc->appliedParams.cParams.strategy == ZSTD_btlazy2)
+    if (params->cParams.strategy != ZSTD_fast) {
+        U32 const chainSize = (U32)1 << params->cParams.chainLog;
+        if (params->cParams.strategy == ZSTD_btlazy2)
            ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue);
        else
            ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue);
@@ -1777,161 +1886,13 @@ static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue)
 static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize, U32 lastBlock)
 {
    U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw)<<1) + (U32)(srcSize << 3);
-    if (srcSize + ZSTD_blockHeaderSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(srcSize + ZSTD_blockHeaderSize > dstCapacity,
+                    dstSize_tooSmall);
    MEM_writeLE24(dst, cBlockHeader24);
    memcpy((BYTE*)dst + ZSTD_blockHeaderSize, src, srcSize);
    return ZSTD_blockHeaderSize + srcSize;
 }

-static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
-    BYTE* const ostart = (BYTE* const)dst;
-    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
-    if (srcSize + flSize > dstCapacity) return ERROR(dstSize_tooSmall);
-
-    switch(flSize)
-    {
-        case 1: /* 2 - 1 - 5 */
-            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
-            break;
-        case 2: /* 2 - 2 - 12 */
-            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
-            break;
-        case 3: /* 2 - 2 - 20 */
-            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
-            break;
-        default:   /* not necessary : flSize is {1,2,3} */
-            assert(0);
-    }
-
-    memcpy(ostart + flSize, src, srcSize);
-    return srcSize + flSize;
-}
-
-static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
-    BYTE* const ostart = (BYTE* const)dst;
-    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
-    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
-
-    switch(flSize)
-    {
-        case 1: /* 2 - 1 - 5 */
-            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
-            break;
-        case 2: /* 2 - 2 - 12 */
-            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
-            break;
-        case 3: /* 2 - 2 - 20 */
-            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
-            break;
-        default:   /* not necessary : flSize is {1,2,3} */
-            assert(0);
-    }
-
-    ostart[flSize] = *(const BYTE*)src;
-    return flSize+1;
-}
-
-
-/* ZSTD_minGain() :
- * minimum compression required
- * to generate a compress block or a compressed literals section.
- * note : use same formula for both situations */
-static size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
-{
-    U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
-    ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
-    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
-    return (srcSize >> minlog) + 2;
-}
-
-static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
-                                     ZSTD_hufCTables_t* nextHuf,
-                                     ZSTD_strategy strategy, int disableLiteralCompression,
-                                     void* dst, size_t dstCapacity,
-                               const void* src, size_t srcSize,
-                                     void* workspace, size_t wkspSize,
-                               const int bmi2)
-{
-    size_t const minGain = ZSTD_minGain(srcSize, strategy);
-    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
-    BYTE*  const ostart = (BYTE*)dst;
-    U32 singleStream = srcSize < 256;
-    symbolEncodingType_e hType = set_compressed;
-    size_t cLitSize;
-
-    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
-                disableLiteralCompression);
-
-    /* Prepare nextEntropy assuming reusing the existing table */
-    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-
-    if (disableLiteralCompression)
-        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-
-    /* small ? don't even attempt compression (speed opt) */
-#   define COMPRESS_LITERALS_SIZE_MIN 63
-    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
-        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
-
-    if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall);   /* not enough space for compression */
-    {   HUF_repeat repeat = prevHuf->repeatMode;
-        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
-        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
-        cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
-                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
-                                : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
-                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
-        if (repeat != HUF_repeat_none) {
-            /* reused the existing table */
-            hType = set_repeat;
-        }
-    }
-
-    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
-    if (cLitSize==1) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
-    }
-
-    if (hType == set_compressed) {
-        /* using a newly constructed table */
-        nextHuf->repeatMode = HUF_repeat_check;
-    }
-
-    /* Build header */
-    switch(lhSize)
-    {
-    case 3: /* 2 - 2 - 10 - 10 */
-        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
-            MEM_writeLE24(ostart, lhc);
-            break;
-        }
-    case 4: /* 2 - 2 - 14 - 14 */
-        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
-            MEM_writeLE32(ostart, lhc);
-            break;
-        }
-    case 5: /* 2 - 2 - 18 - 18 */
-        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
-            MEM_writeLE32(ostart, lhc);
-            ostart[4] = (BYTE)(cLitSize >> 10);
-            break;
-        }
-    default:  /* not possible : lhSize is {3,4,5} */
-        assert(0);
-    }
-    return lhSize+cLitSize;
-}
-
-
 void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
 {
    const seqDef* const sequences = seqStorePtr->sequencesStart;
@@ -1954,418 +1915,19 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
        mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
 }

-
-/**
- * -log2(x / 256) lookup table for x in [0, 256).
- * If x == 0: Return 0
- * Else: Return floor(-log2(x / 256) * 256)
- */
-static unsigned const kInverseProbabiltyLog256[256] = {
-    0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
-    1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
-    874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
-    724,  714,  704,  694,  685,  676,  667,  658,  650,  642,  633,  626,
-    618,  610,  603,  595,  588,  581,  574,  567,  561,  554,  548,  542,
-    535,  529,  523,  517,  512,  506,  500,  495,  489,  484,  478,  473,
-    468,  463,  458,  453,  448,  443,  438,  434,  429,  424,  420,  415,
-    411,  407,  402,  398,  394,  390,  386,  382,  377,  373,  370,  366,
-    362,  358,  354,  350,  347,  343,  339,  336,  332,  329,  325,  322,
-    318,  315,  311,  308,  305,  302,  298,  295,  292,  289,  286,  282,
-    279,  276,  273,  270,  267,  264,  261,  258,  256,  253,  250,  247,
-    244,  241,  239,  236,  233,  230,  228,  225,  222,  220,  217,  215,
-    212,  209,  207,  204,  202,  199,  197,  194,  192,  190,  187,  185,
-    182,  180,  178,  175,  173,  171,  168,  166,  164,  162,  159,  157,
-    155,  153,  151,  149,  146,  144,  142,  140,  138,  136,  134,  132,
-    130,  128,  126,  123,  121,  119,  117,  115,  114,  112,  110,  108,
-    106,  104,  102,  100,  98,   96,   94,   93,   91,   89,   87,   85,
-    83,   82,   80,   78,   76,   74,   73,   71,   69,   67,   66,   64,
-    62,   61,   59,   57,   55,   54,   52,   50,   49,   47,   46,   44,
-    42,   41,   39,   37,   36,   34,   33,   31,   30,   28,   26,   25,
-    23,   22,   20,   19,   17,   16,   14,   13,   11,   10,   8,    7,
-    5,    4,    2,    1,
-};
-
-
-/**
- * Returns the cost in bits of encoding the distribution described by count
- * using the entropy bound.
- */
-static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
+static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
 {
-    unsigned cost = 0;
-    unsigned s;
-    for (s = 0; s <= max; ++s) {
-        unsigned norm = (unsigned)((256 * count[s]) / total);
-        if (count[s] != 0 && norm == 0)
-            norm = 1;
-        assert(count[s] < total);
-        cost += count[s] * kInverseProbabiltyLog256[norm];
-    }
-    return cost >> 8;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using the
- * table described by norm. The max symbol support by norm is assumed >= max.
- * norm must be valid for every symbol with non-zero probability in count.
- */
-static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
-                                    unsigned const* count, unsigned const max)
-{
-    unsigned const shift = 8 - accuracyLog;
-    size_t cost = 0;
-    unsigned s;
-    assert(accuracyLog <= 8);
-    for (s = 0; s <= max; ++s) {
-        unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
-        unsigned const norm256 = normAcc << shift;
-        assert(norm256 > 0);
-        assert(norm256 < 256);
-        cost += count[s] * kInverseProbabiltyLog256[norm256];
-    }
-    return cost >> 8;
-}
-
-
-static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
-  void const* ptr = ctable;
-  U16 const* u16ptr = (U16 const*)ptr;
-  U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
-  return maxSymbolValue;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using ctable.
- * Returns an error if ctable cannot represent all the symbols in count.
- */
-static size_t ZSTD_fseBitCost(
-    FSE_CTable const* ctable,
-    unsigned const* count,
-    unsigned const max)
-{
-    unsigned const kAccuracyLog = 8;
-    size_t cost = 0;
-    unsigned s;
-    FSE_CState_t cstate;
-    FSE_initCState(&cstate, ctable);
-    if (ZSTD_getFSEMaxSymbolValue(ctable) < max) {
-        DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u",
-                    ZSTD_getFSEMaxSymbolValue(ctable), max);
-        return ERROR(GENERIC);
-    }
-    for (s = 0; s <= max; ++s) {
-        unsigned const tableLog = cstate.stateLog;
-        unsigned const badCost = (tableLog + 1) << kAccuracyLog;
-        unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
-        if (count[s] == 0)
-            continue;
-        if (bitCost >= badCost) {
-            DEBUGLOG(5, "Repeat FSE_CTable has Prob[%u] == 0", s);
-            return ERROR(GENERIC);
-        }
-        cost += count[s] * bitCost;
-    }
-    return cost >> kAccuracyLog;
-}
-
-/**
- * Returns the cost in bytes of encoding the normalized count header.
- * Returns an error if any of the helper functions return an error.
- */
-static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
-                              size_t const nbSeq, unsigned const FSELog)
-{
-    BYTE wksp[FSE_NCOUNTBOUND];
-    S16 norm[MaxSeq + 1];
-    const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-    CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
-    return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
-}
-
-
-typedef enum {
-    ZSTD_defaultDisallowed = 0,
-    ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
-
-MEM_STATIC symbolEncodingType_e
-ZSTD_selectEncodingType(
-        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
-        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
-        FSE_CTable const* prevCTable,
-        short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
-        ZSTD_strategy const strategy)
-{
-    ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
-    if (mostFrequent == nbSeq) {
-        *repeatMode = FSE_repeat_none;
-        if (isDefaultAllowed && nbSeq <= 2) {
-            /* Prefer set_basic over set_rle when there are 2 or less symbols,
-             * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
-             * If basic encoding isn't possible, always choose RLE.
-             */
-            DEBUGLOG(5, "Selected set_basic");
-            return set_basic;
-        }
-        DEBUGLOG(5, "Selected set_rle");
-        return set_rle;
-    }
-    if (strategy < ZSTD_lazy) {
-        if (isDefaultAllowed) {
-            size_t const staticFse_nbSeq_max = 1000;
-            size_t const mult = 10 - strategy;
-            size_t const baseLog = 3;
-            size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog;  /* 28-36 for offset, 56-72 for lengths */
-            assert(defaultNormLog >= 5 && defaultNormLog <= 6);  /* xx_DEFAULTNORMLOG */
-            assert(mult <= 9 && mult >= 7);
-            if ( (*repeatMode == FSE_repeat_valid)
-              && (nbSeq < staticFse_nbSeq_max) ) {
-                DEBUGLOG(5, "Selected set_repeat");
-                return set_repeat;
-            }
-            if ( (nbSeq < dynamicFse_nbSeq_min)
-              || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
-                DEBUGLOG(5, "Selected set_basic");
-                /* The format allows default tables to be repeated, but it isn't useful.
-                 * When using simple heuristics to select encoding type, we don't want
-                 * to confuse these tables with dictionaries. When running more careful
-                 * analysis, we don't need to waste time checking both repeating tables
-                 * and default tables.
-                 */
-                *repeatMode = FSE_repeat_none;
-                return set_basic;
-            }
-        }
-    } else {
-        size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
-        size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
-        size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
-        size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
-
-        if (isDefaultAllowed) {
-            assert(!ZSTD_isError(basicCost));
-            assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
-        }
-        assert(!ZSTD_isError(NCountCost));
-        assert(compressedCost < ERROR(maxCode));
-        DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
-                    (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
-        if (basicCost <= repeatCost && basicCost <= compressedCost) {
-            DEBUGLOG(5, "Selected set_basic");
-            assert(isDefaultAllowed);
-            *repeatMode = FSE_repeat_none;
-            return set_basic;
-        }
-        if (repeatCost <= compressedCost) {
-            DEBUGLOG(5, "Selected set_repeat");
-            assert(!ZSTD_isError(repeatCost));
-            return set_repeat;
-        }
-        assert(compressedCost < basicCost && compressedCost < repeatCost);
-    }
-    DEBUGLOG(5, "Selected set_compressed");
-    *repeatMode = FSE_repeat_check;
-    return set_compressed;
-}
-
-MEM_STATIC size_t
-ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
-                unsigned* count, U32 max,
-                const BYTE* codeTable, size_t nbSeq,
-                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
-                const FSE_CTable* prevCTable, size_t prevCTableSize,
-                void* workspace, size_t workspaceSize)
-{
-    BYTE* op = (BYTE*)dst;
-    const BYTE* const oend = op + dstCapacity;
-    DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
-
-    switch (type) {
-    case set_rle:
-        CHECK_F(FSE_buildCTable_rle(nextCTable, (BYTE)max));
-        if (dstCapacity==0) return ERROR(dstSize_tooSmall);
-        *op = codeTable[0];
+    switch (cctxParams->literalCompressionMode) {
+    case ZSTD_lcm_huffman:
+        return 0;
+    case ZSTD_lcm_uncompressed:
        return 1;
-    case set_repeat:
-        memcpy(nextCTable, prevCTable, prevCTableSize);
-        return 0;
-    case set_basic:
-        CHECK_F(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
-        return 0;
-    case set_compressed: {
-        S16 norm[MaxSeq + 1];
-        size_t nbSeq_1 = nbSeq;
-        const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-        if (count[codeTable[nbSeq-1]] > 1) {
-            count[codeTable[nbSeq-1]]--;
-            nbSeq_1--;
-        }
-        assert(nbSeq_1 > 1);
-        CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
-        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
-            if (FSE_isError(NCountSize)) return NCountSize;
-            CHECK_F(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
-            return NCountSize;
-        }
+    default:
+        assert(0 /* impossible: pre-validated */);
+        /* fall-through */
+    case ZSTD_lcm_auto:
+        return (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0);
    }
-    default: return assert(0), ERROR(GENERIC);
-    }
-}
-
-FORCE_INLINE_TEMPLATE size_t
-ZSTD_encodeSequences_body(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    BIT_CStream_t blockStream;
-    FSE_CState_t  stateMatchLength;
-    FSE_CState_t  stateOffsetBits;
-    FSE_CState_t  stateLitLength;
-
-    CHECK_E(BIT_initCStream(&blockStream, dst, dstCapacity), dstSize_tooSmall); /* not enough space remaining */
-    DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
-                (int)(blockStream.endPtr - blockStream.startPtr),
-                (unsigned)dstCapacity);
-
-    /* first symbols */
-    FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
-    FSE_initCState2(&stateOffsetBits,  CTable_OffsetBits,  ofCodeTable[nbSeq-1]);
-    FSE_initCState2(&stateLitLength,   CTable_LitLength,   llCodeTable[nbSeq-1]);
-    BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
-    if (MEM_32bits()) BIT_flushBits(&blockStream);
-    BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
-    if (MEM_32bits()) BIT_flushBits(&blockStream);
-    if (longOffsets) {
-        U32 const ofBits = ofCodeTable[nbSeq-1];
-        int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
-        if (extraBits) {
-            BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
-            BIT_flushBits(&blockStream);
-        }
-        BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
-                    ofBits - extraBits);
-    } else {
-        BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
-    }
-    BIT_flushBits(&blockStream);
-
-    {   size_t n;
-        for (n=nbSeq-2 ; n<nbSeq ; n--) {      /* intentional underflow */
-            BYTE const llCode = llCodeTable[n];
-            BYTE const ofCode = ofCodeTable[n];
-            BYTE const mlCode = mlCodeTable[n];
-            U32  const llBits = LL_bits[llCode];
-            U32  const ofBits = ofCode;
-            U32  const mlBits = ML_bits[mlCode];
-            DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
-                        (unsigned)sequences[n].litLength,
-                        (unsigned)sequences[n].matchLength + MINMATCH,
-                        (unsigned)sequences[n].offset);
-                                                                            /* 32b*/  /* 64b*/
-                                                                            /* (7)*/  /* (7)*/
-            FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode);       /* 15 */  /* 15 */
-            FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode);      /* 24 */  /* 24 */
-            if (MEM_32bits()) BIT_flushBits(&blockStream);                  /* (7)*/
-            FSE_encodeSymbol(&blockStream, &stateLitLength, llCode);        /* 16 */  /* 33 */
-            if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
-                BIT_flushBits(&blockStream);                                /* (7)*/
-            BIT_addBits(&blockStream, sequences[n].litLength, llBits);
-            if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
-            BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
-            if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
-            if (longOffsets) {
-                int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
-                if (extraBits) {
-                    BIT_addBits(&blockStream, sequences[n].offset, extraBits);
-                    BIT_flushBits(&blockStream);                            /* (7)*/
-                }
-                BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
-                            ofBits - extraBits);                            /* 31 */
-            } else {
-                BIT_addBits(&blockStream, sequences[n].offset, ofBits);     /* 31 */
-            }
-            BIT_flushBits(&blockStream);                                    /* (7)*/
-            DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
-    }   }
-
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
-    FSE_flushCState(&blockStream, &stateMatchLength);
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
-    FSE_flushCState(&blockStream, &stateOffsetBits);
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
-    FSE_flushCState(&blockStream, &stateLitLength);
-
-    {   size_t const streamSize = BIT_closeCStream(&blockStream);
-        if (streamSize==0) return ERROR(dstSize_tooSmall);   /* not enough space */
-        return streamSize;
-    }
-}
-
-static size_t
-ZSTD_encodeSequences_default(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    return ZSTD_encodeSequences_body(dst, dstCapacity,
-                                    CTable_MatchLength, mlCodeTable,
-                                    CTable_OffsetBits, ofCodeTable,
-                                    CTable_LitLength, llCodeTable,
-                                    sequences, nbSeq, longOffsets);
-}
-
-
-#if DYNAMIC_BMI2
-
-static TARGET_ATTRIBUTE("bmi2") size_t
-ZSTD_encodeSequences_bmi2(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    return ZSTD_encodeSequences_body(dst, dstCapacity,
-                                    CTable_MatchLength, mlCodeTable,
-                                    CTable_OffsetBits, ofCodeTable,
-                                    CTable_LitLength, llCodeTable,
-                                    sequences, nbSeq, longOffsets);
-}
-
-#endif
-
-static size_t ZSTD_encodeSequences(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
-{
-    DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
-#if DYNAMIC_BMI2
-    if (bmi2) {
-        return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
-                                         CTable_MatchLength, mlCodeTable,
-                                         CTable_OffsetBits, ofCodeTable,
-                                         CTable_LitLength, llCodeTable,
-                                         sequences, nbSeq, longOffsets);
-    }
-#endif
-    (void)bmi2;
-    return ZSTD_encodeSequences_default(dst, dstCapacity,
-                                        CTable_MatchLength, mlCodeTable,
-                                        CTable_OffsetBits, ofCodeTable,
-                                        CTable_LitLength, llCodeTable,
-                                        sequences, nbSeq, longOffsets);
 }

 /* ZSTD_compressSequences_internal():
@@ -2397,34 +1959,35 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
    BYTE* seqHead;
    BYTE* lastNCount = NULL;

+    DEBUGLOG(5, "ZSTD_compressSequences_internal (nbSeq=%zu)", nbSeq);
    ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
-    DEBUGLOG(5, "ZSTD_compressSequences_internal");

    /* Compress literals */
    {   const BYTE* const literals = seqStorePtr->litStart;
        size_t const litSize = seqStorePtr->lit - literals;
-        int const disableLiteralCompression = (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0);
        size_t const cSize = ZSTD_compressLiterals(
                                    &prevEntropy->huf, &nextEntropy->huf,
-                                    cctxParams->cParams.strategy, disableLiteralCompression,
+                                    cctxParams->cParams.strategy,
+                                    ZSTD_disableLiteralsCompression(cctxParams),
                                    op, dstCapacity,
                                    literals, litSize,
                                    workspace, wkspSize,
                                    bmi2);
-        if (ZSTD_isError(cSize))
-          return cSize;
+        FORWARD_IF_ERROR(cSize);
        assert(cSize <= dstCapacity);
        op += cSize;
    }

    /* Sequences Header */
-    if ((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
+                    dstSize_tooSmall);
    if (nbSeq < 0x7F)
        *op++ = (BYTE)nbSeq;
    else if (nbSeq < LONGNBSEQ)
        op[0] = (BYTE)((nbSeq>>8) + 0x80), op[1] = (BYTE)nbSeq, op+=2;
    else
        op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3;
+    assert(op <= oend);
    if (nbSeq==0) {
        /* Copy the old tables over as if we repeated them */
        memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse));
@@ -2433,6 +1996,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,

    /* seqHead : flags for FSE encoding type */
    seqHead = op++;
+    assert(op <= oend);

    /* convert length/distances into codes */
    ZSTD_seqToCodes(seqStorePtr);
@@ -2452,10 +2016,11 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                    count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
                                                    prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable),
                                                    workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
            if (LLtype == set_compressed)
                lastNCount = op;
            op += countSize;
+            assert(op <= oend);
    }   }
    /* build CTable for Offsets */
    {   unsigned max = MaxOff;
@@ -2474,10 +2039,11 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                    count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
                                                    prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable),
                                                    workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
            if (Offtype == set_compressed)
                lastNCount = op;
            op += countSize;
+            assert(op <= oend);
    }   }
    /* build CTable for MatchLengths */
    {   unsigned max = MaxML;
@@ -2494,10 +2060,11 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                    count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
                                                    prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable),
                                                    workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
            if (MLtype == set_compressed)
                lastNCount = op;
            op += countSize;
+            assert(op <= oend);
    }   }

    *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2));
@@ -2509,10 +2076,11 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                        CTable_LitLength, llCodeTable,
                                        sequences, nbSeq,
                                        longOffsets, bmi2);
-        if (ZSTD_isError(bitstreamSize)) return bitstreamSize;
+        FORWARD_IF_ERROR(bitstreamSize);
        op += bitstreamSize;
+        assert(op <= oend);
        /* zstd versions <= 1.3.4 mistakenly report corruption when
-         * FSE_readNCount() recieves a buffer < 4 bytes.
+         * FSE_readNCount() receives a buffer < 4 bytes.
         * Fixed by https://github.com/facebook/zstd/pull/1146.
         * This can happen when the last set_compressed table present is 2
         * bytes and the bitstream is only one byte.
@@ -2552,7 +2120,7 @@ ZSTD_compressSequences(seqStore_t* seqStorePtr,
     */
    if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity))
        return 0;  /* block not compressed */
-    if (ZSTD_isError(cSize)) return cSize;
+    FORWARD_IF_ERROR(cSize);

    /* Check compressibility */
    {   size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy);
@@ -2622,27 +2190,24 @@ void ZSTD_resetSeqStore(seqStore_t* ssPtr)
    ssPtr->longLengthID = 0;
 }

-static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
-                                        void* dst, size_t dstCapacity,
-                                        const void* src, size_t srcSize)
+typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_buildSeqStore_e;
+
+static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize)
 {
    ZSTD_matchState_t* const ms = &zc->blockState.matchState;
-    size_t cSize;
-    DEBUGLOG(5, "ZSTD_compressBlock_internal (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u)",
-                (unsigned)dstCapacity, (unsigned)ms->window.dictLimit, (unsigned)ms->nextToUpdate);
+    DEBUGLOG(5, "ZSTD_buildSeqStore (srcSize=%zu)", srcSize);
    assert(srcSize <= ZSTD_BLOCKSIZE_MAX);
-
    /* Assert that we have correctly flushed the ctx params into the ms's copy */
    ZSTD_assertEqualCParams(zc->appliedParams.cParams, ms->cParams);
-
    if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) {
        ZSTD_ldm_skipSequences(&zc->externSeqStore, srcSize, zc->appliedParams.cParams.minMatch);
-        cSize = 0;
-        goto out;  /* don't even attempt compression below a certain srcSize */
+        return ZSTDbss_noCompress; /* don't even attempt compression below a certain srcSize */
    }
    ZSTD_resetSeqStore(&(zc->seqStore));
-    ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;   /* required for optimal parser to read stats from dictionary */
-
+    /* required for optimal parser to read stats from dictionary */
+    ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;
+    /* tell the optimal parser how we expect to compress literals */
+    ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode;
    /* a gap between an attached dict and the current window is not safe,
     * they must remain adjacent,
     * and when that stops being the case, the dict must be unset */
@@ -2679,7 +2244,7 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
            ldmSeqStore.seq = zc->ldmSequences;
            ldmSeqStore.capacity = zc->maxNbLdmSequences;
            /* Updates ldmSeqStore.size */
-            CHECK_F(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore,
+            FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore,
                                               &zc->appliedParams.ldmParams,
                                               src, srcSize));
            /* Updates ldmSeqStore.pos */
@@ -2696,6 +2261,21 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
        {   const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize;
            ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize);
    }   }
+    return ZSTDbss_compress;
+}
+
+static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
+                                        void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize)
+{
+    size_t cSize;
+    DEBUGLOG(5, "ZSTD_compressBlock_internal (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u)",
+                (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit, (unsigned)zc->blockState.matchState.nextToUpdate);
+
+    {   const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize);
+        FORWARD_IF_ERROR(bss);
+        if (bss == ZSTDbss_noCompress) { cSize = 0; goto out; }
+    }

    /* encode sequences and literals */
    cSize = ZSTD_compressSequences(&zc->seqStore,
@@ -2724,6 +2304,25 @@ out:
 }


+static void ZSTD_overflowCorrectIfNeeded(ZSTD_matchState_t* ms, ZSTD_CCtx_params const* params, void const* ip, void const* iend)
+{
+    if (ZSTD_window_needOverflowCorrection(ms->window, iend)) {
+        U32 const maxDist = (U32)1 << params->cParams.windowLog;
+        U32 const cycleLog = ZSTD_cycleLog(params->cParams.chainLog, params->cParams.strategy);
+        U32 const correction = ZSTD_window_correctOverflow(&ms->window, cycleLog, maxDist, ip);
+        ZSTD_STATIC_ASSERT(ZSTD_CHAINLOG_MAX <= 30);
+        ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_32 <= 30);
+        ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX <= 31);
+        ZSTD_reduceIndex(ms, params, correction);
+        if (ms->nextToUpdate < correction) ms->nextToUpdate = 0;
+        else ms->nextToUpdate -= correction;
+        /* invalidate dictionaries on overflow correction */
+        ms->loadedDictEnd = 0;
+        ms->dictMatchState = NULL;
+    }
+}
+
+
 /*! ZSTD_compress_frameChunk() :
 *   Compress a chunk of data into one or multiple blocks.
 *   All blocks will be terminated, all input will be consumed.
@@ -2742,7 +2341,7 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
    BYTE* const ostart = (BYTE*)dst;
    BYTE* op = ostart;
    U32 const maxDist = (U32)1 << cctx->appliedParams.cParams.windowLog;
-    assert(cctx->appliedParams.cParams.windowLog <= 31);
+    assert(cctx->appliedParams.cParams.windowLog <= ZSTD_WINDOWLOG_MAX);

    DEBUGLOG(5, "ZSTD_compress_frameChunk (blockSize=%u)", (unsigned)blockSize);
    if (cctx->appliedParams.fParams.checksumFlag && srcSize)
@@ -2752,33 +2351,25 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
        ZSTD_matchState_t* const ms = &cctx->blockState.matchState;
        U32 const lastBlock = lastFrameChunk & (blockSize >= remaining);

-        if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE)
-            return ERROR(dstSize_tooSmall);   /* not enough space to store compressed block */
+        RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE,
+                        dstSize_tooSmall,
+                        "not enough space to store compressed block");
        if (remaining < blockSize) blockSize = remaining;

-        if (ZSTD_window_needOverflowCorrection(ms->window, ip + blockSize)) {
-            U32 const cycleLog = ZSTD_cycleLog(cctx->appliedParams.cParams.chainLog, cctx->appliedParams.cParams.strategy);
-            U32 const correction = ZSTD_window_correctOverflow(&ms->window, cycleLog, maxDist, ip);
-            ZSTD_STATIC_ASSERT(ZSTD_CHAINLOG_MAX <= 30);
-            ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_32 <= 30);
-            ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX <= 31);
-            ZSTD_reduceIndex(cctx, correction);
-            if (ms->nextToUpdate < correction) ms->nextToUpdate = 0;
-            else ms->nextToUpdate -= correction;
-            ms->loadedDictEnd = 0;
-            ms->dictMatchState = NULL;
-        }
-        ZSTD_window_enforceMaxDist(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
+        ZSTD_overflowCorrectIfNeeded(ms, &cctx->appliedParams, ip, ip + blockSize);
+        ZSTD_checkDictValidity(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
+
+        /* Ensure hash/chain table insertion resumes no sooner than lowlimit */
        if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit;

        {   size_t cSize = ZSTD_compressBlock_internal(cctx,
                                op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize,
                                ip, blockSize);
-            if (ZSTD_isError(cSize)) return cSize;
+            FORWARD_IF_ERROR(cSize);

            if (cSize == 0) {  /* block is not compressible */
                cSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
            } else {
                U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3);
                MEM_writeLE24(op, cBlockHeader24);
@@ -2796,7 +2387,7 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
    }   }

    if (lastFrameChunk && (op>ostart)) cctx->stage = ZSTDcs_ending;
-    return op-ostart;
+    return (size_t)(op-ostart);
 }


@@ -2811,11 +2402,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
    BYTE  const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
    U32   const fcsCode = params.fParams.contentSizeFlag ?
                     (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0;  /* 0-3 */
-    BYTE  const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
+    BYTE  const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
    size_t pos=0;

    assert(!(params.fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN));
-    if (dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall);
    DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u",
                !params.fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode);

@@ -2823,7 +2414,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
        MEM_writeLE32(dst, ZSTD_MAGICNUMBER);
        pos = 4;
    }
-    op[pos++] = frameHeaderDecriptionByte;
+    op[pos++] = frameHeaderDescriptionByte;
    if (!singleSegment) op[pos++] = windowLogByte;
    switch(dictIDSizeCode)
    {
@@ -2847,11 +2438,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
 /* ZSTD_writeLastEmptyBlock() :
 * output an empty Block with end-of-frame mark to complete a frame
 * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
- *           or an error code if `dstCapcity` is too small (<ZSTD_blockHeaderSize)
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
 */
 size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity)
 {
-    if (dstCapacity < ZSTD_blockHeaderSize) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize, dstSize_tooSmall);
    {   U32 const cBlockHeader24 = 1 /*lastBlock*/ + (((U32)bt_raw)<<1);  /* 0 size */
        MEM_writeLE24(dst, cBlockHeader24);
        return ZSTD_blockHeaderSize;
@@ -2860,10 +2451,9 @@ size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity)

 size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq)
 {
-    if (cctx->stage != ZSTDcs_init)
-        return ERROR(stage_wrong);
-    if (cctx->appliedParams.ldmParams.enableLdm)
-        return ERROR(parameter_unsupported);
+    RETURN_ERROR_IF(cctx->stage != ZSTDcs_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm,
+                    parameter_unsupported);
    cctx->externSeqStore.seq = seq;
    cctx->externSeqStore.size = nbSeq;
    cctx->externSeqStore.capacity = nbSeq;
@@ -2882,12 +2472,14 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,

    DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u",
                cctx->stage, (unsigned)srcSize);
-    if (cctx->stage==ZSTDcs_created) return ERROR(stage_wrong);   /* missing init (ZSTD_compressBegin) */
+    RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong,
+                    "missing init (ZSTD_compressBegin)");

    if (frame && (cctx->stage==ZSTDcs_init)) {
        fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams,
                                       cctx->pledgedSrcSizePlusOne-1, cctx->dictID);
-        if (ZSTD_isError(fhSize)) return fhSize;
+        FORWARD_IF_ERROR(fhSize);
+        assert(fhSize <= dstCapacity);
        dstCapacity -= fhSize;
        dst = (char*)dst + fhSize;
        cctx->stage = ZSTDcs_ongoing;
@@ -2904,35 +2496,25 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,

    if (!frame) {
        /* overflow check and correction for block mode */
-        if (ZSTD_window_needOverflowCorrection(ms->window, (const char*)src + srcSize)) {
-            U32 const cycleLog = ZSTD_cycleLog(cctx->appliedParams.cParams.chainLog, cctx->appliedParams.cParams.strategy);
-            U32 const correction = ZSTD_window_correctOverflow(&ms->window, cycleLog, 1 << cctx->appliedParams.cParams.windowLog, src);
-            ZSTD_STATIC_ASSERT(ZSTD_CHAINLOG_MAX <= 30);
-            ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_32 <= 30);
-            ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX <= 31);
-            ZSTD_reduceIndex(cctx, correction);
-            if (ms->nextToUpdate < correction) ms->nextToUpdate = 0;
-            else ms->nextToUpdate -= correction;
-            ms->loadedDictEnd = 0;
-            ms->dictMatchState = NULL;
-        }
+        ZSTD_overflowCorrectIfNeeded(ms, &cctx->appliedParams, src, (BYTE const*)src + srcSize);
    }

    DEBUGLOG(5, "ZSTD_compressContinue_internal (blockSize=%u)", (unsigned)cctx->blockSize);
    {   size_t const cSize = frame ?
                             ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
                             ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize);
-        if (ZSTD_isError(cSize)) return cSize;
+        FORWARD_IF_ERROR(cSize);
        cctx->consumedSrcSize += srcSize;
        cctx->producedCSize += (cSize + fhSize);
        assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
        if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
            ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
-            if (cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne) {
-                DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize >= %u",
-                    (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize);
-                return ERROR(srcSize_wrong);
-            }
+            RETURN_ERROR_IF(
+                cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne,
+                srcSize_wrong,
+                "error : pledgedSrcSize = %u, while realSrcSize >= %u",
+                (unsigned)cctx->pledgedSrcSizePlusOne-1,
+                (unsigned)cctx->consumedSrcSize);
        }
        return cSize + fhSize;
    }
@@ -2957,7 +2539,7 @@ size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
 size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
    size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
-    if (srcSize > blockSizeMax) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong);

    return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
 }
@@ -2970,7 +2552,7 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
                                         const void* src, size_t srcSize,
                                         ZSTD_dictTableLoadMethod_e dtlm)
 {
-    const BYTE* const ip = (const BYTE*) src;
+    const BYTE* ip = (const BYTE*) src;
    const BYTE* const iend = ip + srcSize;

    ZSTD_window_update(&ms->window, src, srcSize);
@@ -2981,32 +2563,42 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,

    if (srcSize <= HASH_READ_SIZE) return 0;

-    switch(params->cParams.strategy)
-    {
-    case ZSTD_fast:
-        ZSTD_fillHashTable(ms, iend, dtlm);
-        break;
-    case ZSTD_dfast:
-        ZSTD_fillDoubleHashTable(ms, iend, dtlm);
-        break;
+    while (iend - ip > HASH_READ_SIZE) {
+        size_t const remaining = iend - ip;
+        size_t const chunk = MIN(remaining, ZSTD_CHUNKSIZE_MAX);
+        const BYTE* const ichunk = ip + chunk;

-    case ZSTD_greedy:
-    case ZSTD_lazy:
-    case ZSTD_lazy2:
-        if (srcSize >= HASH_READ_SIZE)
-            ZSTD_insertAndFindFirstIndex(ms, iend-HASH_READ_SIZE);
-        break;
+        ZSTD_overflowCorrectIfNeeded(ms, params, ip, ichunk);

-    case ZSTD_btlazy2:   /* we want the dictionary table fully sorted */
-    case ZSTD_btopt:
-    case ZSTD_btultra:
-    case ZSTD_btultra2:
-        if (srcSize >= HASH_READ_SIZE)
-            ZSTD_updateTree(ms, iend-HASH_READ_SIZE, iend);
-        break;
+        switch(params->cParams.strategy)
+        {
+        case ZSTD_fast:
+            ZSTD_fillHashTable(ms, ichunk, dtlm);
+            break;
+        case ZSTD_dfast:
+            ZSTD_fillDoubleHashTable(ms, ichunk, dtlm);
+            break;

-    default:
-        assert(0);  /* not possible : not a valid strategy id */
+        case ZSTD_greedy:
+        case ZSTD_lazy:
+        case ZSTD_lazy2:
+            if (chunk >= HASH_READ_SIZE)
+                ZSTD_insertAndFindFirstIndex(ms, ichunk-HASH_READ_SIZE);
+            break;
+
+        case ZSTD_btlazy2:   /* we want the dictionary table fully sorted */
+        case ZSTD_btopt:
+        case ZSTD_btultra:
+        case ZSTD_btultra2:
+            if (chunk >= HASH_READ_SIZE)
+                ZSTD_updateTree(ms, ichunk-HASH_READ_SIZE, ichunk);
+            break;
+
+        default:
+            assert(0);  /* not possible : not a valid strategy id */
+        }
+
+        ip = ichunk;
    }

    ms->nextToUpdate = (U32)(iend - ms->window.base);
@@ -3020,9 +2612,9 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
   NOTE: This behavior is not standard and could be improved in the future. */
 static size_t ZSTD_checkDictNCount(short* normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue) {
    U32 s;
-    if (dictMaxSymbolValue < maxSymbolValue) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictMaxSymbolValue < maxSymbolValue, dictionary_corrupted);
    for (s = 0; s <= maxSymbolValue; ++s) {
-        if (normalizedCounter[s] == 0) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(normalizedCounter[s] == 0, dictionary_corrupted);
    }
    return 0;
 }
@@ -3060,53 +2652,56 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,

    {   unsigned maxSymbolValue = 255;
        size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr);
-        if (HUF_isError(hufHeaderSize)) return ERROR(dictionary_corrupted);
-        if (maxSymbolValue < 255) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted);
        dictPtr += hufHeaderSize;
    }

    {   unsigned offcodeLog;
        size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted);
-        if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted);
        /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
        /* fill all offset symbols to avoid garbage at end of table */
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.offcodeCTable,
-                                    offcodeNCount, MaxOff, offcodeLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.offcodeCTable,
+                offcodeNCount, MaxOff, offcodeLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
        dictPtr += offcodeHeaderSize;
    }

    {   short matchlengthNCount[MaxML+1];
        unsigned matchlengthMaxValue = MaxML, matchlengthLog;
        size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted);
        /* Every match length code must have non-zero probability */
-        CHECK_F( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.matchlengthCTable,
-                                    matchlengthNCount, matchlengthMaxValue, matchlengthLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        FORWARD_IF_ERROR( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.matchlengthCTable,
+                matchlengthNCount, matchlengthMaxValue, matchlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
        dictPtr += matchlengthHeaderSize;
    }

    {   short litlengthNCount[MaxLL+1];
        unsigned litlengthMaxValue = MaxLL, litlengthLog;
        size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted);
        /* Every literal length code must have non-zero probability */
-        CHECK_F( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.litlengthCTable,
-                                    litlengthNCount, litlengthMaxValue, litlengthLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        FORWARD_IF_ERROR( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.litlengthCTable,
+                litlengthNCount, litlengthMaxValue, litlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
        dictPtr += litlengthHeaderSize;
    }

-    if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted);
    bs->rep[0] = MEM_readLE32(dictPtr+0);
    bs->rep[1] = MEM_readLE32(dictPtr+4);
    bs->rep[2] = MEM_readLE32(dictPtr+8);
@@ -3119,19 +2714,19 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
            offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */
        }
        /* All offset values <= dictContentSize + 128 KB must be representable */
-        CHECK_F (ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
+        FORWARD_IF_ERROR(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
        /* All repCodes must be <= dictContentSize and != 0*/
        {   U32 u;
            for (u=0; u<3; u++) {
-                if (bs->rep[u] == 0) return ERROR(dictionary_corrupted);
-                if (bs->rep[u] > dictContentSize) return ERROR(dictionary_corrupted);
+                RETURN_ERROR_IF(bs->rep[u] == 0, dictionary_corrupted);
+                RETURN_ERROR_IF(bs->rep[u] > dictContentSize, dictionary_corrupted);
        }   }

        bs->entropy.huf.repeatMode = HUF_repeat_valid;
        bs->entropy.fse.offcode_repeatMode = FSE_repeat_valid;
        bs->entropy.fse.matchlength_repeatMode = FSE_repeat_valid;
        bs->entropy.fse.litlength_repeatMode = FSE_repeat_valid;
-        CHECK_F(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm));
+        FORWARD_IF_ERROR(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm));
        return dictID;
    }
 }
@@ -3161,8 +2756,7 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
            DEBUGLOG(4, "raw content dictionary detected");
            return ZSTD_loadDictionaryContent(ms, params, dict, dictSize, dtlm);
        }
-        if (dictContentType == ZSTD_dct_fullDict)
-            return ERROR(dictionary_wrong);
+        RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong);
        assert(0);   /* impossible */
    }

@@ -3189,14 +2783,13 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
        return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff);
    }

-    CHECK_F( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
+    FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
                                     ZSTDcrp_continue, zbuff) );
-    {
-        size_t const dictID = ZSTD_compress_insertDictionary(
+    {   size_t const dictID = ZSTD_compress_insertDictionary(
                cctx->blockState.prevCBlock, &cctx->blockState.matchState,
                &params, dict, dictSize, dictContentType, dtlm, cctx->entropyWorkspace);
-        if (ZSTD_isError(dictID)) return dictID;
-        assert(dictID <= (size_t)(U32)-1);
+        FORWARD_IF_ERROR(dictID);
+        assert(dictID <= UINT_MAX);
        cctx->dictID = (U32)dictID;
    }
    return 0;
@@ -3212,7 +2805,7 @@ size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx,
 {
    DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params.cParams.windowLog);
    /* compression parameters verification and optimization */
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
    return ZSTD_compressBegin_internal(cctx,
                                       dict, dictSize, dictContentType, dtlm,
                                       cdict,
@@ -3260,12 +2853,12 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
    size_t fhSize = 0;

    DEBUGLOG(4, "ZSTD_writeEpilogue");
-    if (cctx->stage == ZSTDcs_created) return ERROR(stage_wrong);  /* init missing */
+    RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing");

    /* special case : empty frame */
    if (cctx->stage == ZSTDcs_init) {
        fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, 0, 0);
-        if (ZSTD_isError(fhSize)) return fhSize;
+        FORWARD_IF_ERROR(fhSize);
        dstCapacity -= fhSize;
        op += fhSize;
        cctx->stage = ZSTDcs_ongoing;
@@ -3274,7 +2867,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
    if (cctx->stage != ZSTDcs_ending) {
        /* write one last empty block, make it the "last" block */
        U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1) + 0;
-        if (dstCapacity<4) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall);
        MEM_writeLE32(op, cBlockHeader24);
        op += ZSTD_blockHeaderSize;
        dstCapacity -= ZSTD_blockHeaderSize;
@@ -3282,7 +2875,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)

    if (cctx->appliedParams.fParams.checksumFlag) {
        U32 const checksum = (U32) XXH64_digest(&cctx->xxhState);
-        if (dstCapacity<4) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall);
        DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum);
        MEM_writeLE32(op, checksum);
        op += 4;
@@ -3300,18 +2893,20 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx,
    size_t const cSize = ZSTD_compressContinue_internal(cctx,
                                dst, dstCapacity, src, srcSize,
                                1 /* frame mode */, 1 /* last chunk */);
-    if (ZSTD_isError(cSize)) return cSize;
+    FORWARD_IF_ERROR(cSize);
    endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize);
-    if (ZSTD_isError(endResult)) return endResult;
+    FORWARD_IF_ERROR(endResult);
    assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
    if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
        ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
        DEBUGLOG(4, "end of frame : controlling src size");
-        if (cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1) {
-            DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize = %u",
-                (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize);
-            return ERROR(srcSize_wrong);
-    }   }
+        RETURN_ERROR_IF(
+            cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1,
+            srcSize_wrong,
+             "error : pledgedSrcSize = %u, while realSrcSize = %u",
+            (unsigned)cctx->pledgedSrcSizePlusOne-1,
+            (unsigned)cctx->consumedSrcSize);
+    }
    return cSize + endResult;
 }

@@ -3339,7 +2934,7 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx,
                               ZSTD_parameters params)
 {
    DEBUGLOG(4, "ZSTD_compress_advanced");
-    CHECK_F(ZSTD_checkCParams(params.cParams));
+    FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams));
    return ZSTD_compress_internal(cctx,
                                  dst, dstCapacity,
                                  src, srcSize,
@@ -3356,7 +2951,7 @@ size_t ZSTD_compress_advanced_internal(
        ZSTD_CCtx_params params)
 {
    DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize);
-    CHECK_F( ZSTD_compressBegin_internal(cctx,
+    FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
                         dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL,
                         params, srcSize, ZSTDb_not_buffered) );
    return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
@@ -3440,17 +3035,17 @@ static size_t ZSTD_initCDict_internal(
        void* const internalBuffer = ZSTD_malloc(dictSize, cdict->customMem);
        cdict->dictBuffer = internalBuffer;
        cdict->dictContent = internalBuffer;
-        if (!internalBuffer) return ERROR(memory_allocation);
+        RETURN_ERROR_IF(!internalBuffer, memory_allocation);
        memcpy(internalBuffer, dictBuffer, dictSize);
    }
    cdict->dictContentSize = dictSize;

    /* Reset the state to no dictionary */
    ZSTD_reset_compressedBlockState(&cdict->cBlockState);
-    {   void* const end = ZSTD_reset_matchState(
-                &cdict->matchState,
-                (U32*)cdict->workspace + HUF_WORKSPACE_SIZE_U32,
-                &cParams, ZSTDcrp_continue, /* forCCtx */ 0);
+    {   void* const end = ZSTD_reset_matchState(&cdict->matchState,
+                            (U32*)cdict->workspace + HUF_WORKSPACE_SIZE_U32,
+                            &cParams,
+                             ZSTDcrp_continue, ZSTD_resetTarget_CDict);
        assert(end == (char*)cdict->workspace + cdict->workspaceSize);
        (void)end;
    }
@@ -3466,7 +3061,7 @@ static size_t ZSTD_initCDict_internal(
                    &cdict->cBlockState, &cdict->matchState, &params,
                    cdict->dictContent, cdict->dictContentSize,
                    dictContentType, ZSTD_dtlm_full, cdict->workspace);
-            if (ZSTD_isError(dictID)) return dictID;
+            FORWARD_IF_ERROR(dictID);
            assert(dictID <= (size_t)(U32)-1);
            cdict->dictID = (U32)dictID;
        }
@@ -3596,7 +3191,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
    ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
 {
    DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced");
-    if (cdict==NULL) return ERROR(dictionary_wrong);
+    RETURN_ERROR_IF(cdict==NULL, dictionary_wrong);
    {   ZSTD_CCtx_params params = cctx->requestedParams;
        params.cParams = ZSTD_getCParamsFromCDict(cdict);
        /* Increase window log to fit the entire dictionary and source if the
@@ -3632,7 +3227,7 @@ size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
                                const void* src, size_t srcSize,
                                const ZSTD_CDict* cdict, ZSTD_frameParameters fParams)
 {
-    CHECK_F (ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize));   /* will check if cdict != NULL */
+    FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize));   /* will check if cdict != NULL */
    return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
 }

@@ -3700,7 +3295,7 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx,
    assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
    assert(!((dict) && (cdict)));  /* either dict or cdict, not both */

-    CHECK_F( ZSTD_compressBegin_internal(cctx,
+    FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
                                         dict, dictSize, dictContentType, ZSTD_dtlm_fast,
                                         cdict,
                                         params, pledgedSrcSize,
@@ -3718,13 +3313,17 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx,

 /* ZSTD_resetCStream():
 * pledgedSrcSize == 0 means "unknown" */
-size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
+size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss)
 {
-    ZSTD_CCtx_params params = zcs->requestedParams;
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
    DEBUGLOG(4, "ZSTD_resetCStream: pledgedSrcSize = %u", (unsigned)pledgedSrcSize);
-    if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;
-    params.fParams.contentSizeFlag = 1;
-    return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    return 0;
 }

 /*! ZSTD_initCStream_internal() :
@@ -3736,32 +3335,18 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
                    ZSTD_CCtx_params params, unsigned long long pledgedSrcSize)
 {
    DEBUGLOG(4, "ZSTD_initCStream_internal");
-    params.cParams = ZSTD_getCParamsFromCCtxParams(&params, pledgedSrcSize, dictSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
    assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+    zcs->requestedParams = params;
    assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
-
-    if (dict && dictSize >= 8) {
-        DEBUGLOG(4, "loading dictionary of size %u", (unsigned)dictSize);
-        if (zcs->staticSize) {   /* static CCtx : never uses malloc */
-            /* incompatible with internal cdict creation */
-            return ERROR(memory_allocation);
-        }
-        ZSTD_freeCDict(zcs->cdictLocal);
-        zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
-                                            ZSTD_dlm_byCopy, ZSTD_dct_auto,
-                                            params.cParams, zcs->customMem);
-        zcs->cdict = zcs->cdictLocal;
-        if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
+    if (dict) {
+        FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
    } else {
-        if (cdict) {
-            params.cParams = ZSTD_getCParamsFromCDict(cdict);  /* cParams are enforced from cdict; it includes windowLog */
-        }
-        ZSTD_freeCDict(zcs->cdictLocal);
-        zcs->cdictLocal = NULL;
-        zcs->cdict = cdict;
+        /* Dictionary is cleared if !cdict */
+        FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
    }
-
-    return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize);
+    return 0;
 }

 /* ZSTD_initCStream_usingCDict_advanced() :
@@ -3772,22 +3357,20 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
                                            unsigned long long pledgedSrcSize)
 {
    DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced");
-    if (!cdict) return ERROR(dictionary_wrong); /* cannot handle NULL cdict (does not know what to do) */
-    {   ZSTD_CCtx_params params = zcs->requestedParams;
-        params.cParams = ZSTD_getCParamsFromCDict(cdict);
-        params.fParams = fParams;
-        return ZSTD_initCStream_internal(zcs,
-                                NULL, 0, cdict,
-                                params, pledgedSrcSize);
-    }
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    zcs->requestedParams.fParams = fParams;
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
+    return 0;
 }

 /* note : cdict must outlive compression session */
 size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
 {
-    ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */, 0 /* checksum */, 0 /* hideDictID */ };
    DEBUGLOG(4, "ZSTD_initCStream_usingCDict");
-    return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN);  /* note : will check that cdict != NULL */
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
+    return 0;
 }


@@ -3797,33 +3380,53 @@ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
 * dict is loaded with default parameters ZSTD_dm_auto and ZSTD_dlm_byCopy. */
 size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
                                 const void* dict, size_t dictSize,
-                                 ZSTD_parameters params, unsigned long long pledgedSrcSize)
+                                 ZSTD_parameters params, unsigned long long pss)
 {
-    DEBUGLOG(4, "ZSTD_initCStream_advanced: pledgedSrcSize=%u, flag=%u",
-                (unsigned)pledgedSrcSize, params.fParams.contentSizeFlag);
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
-    if ((pledgedSrcSize==0) && (params.fParams.contentSizeFlag==0)) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;  /* for compatibility with older programs relying on this behavior. Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. This line will be removed in the future. */
+    /* for compatibility with older programs relying on this behavior.
+     * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN.
+     * This line will be removed in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0 && params.fParams.contentSizeFlag==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_advanced");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
    zcs->requestedParams = ZSTD_assignParamsToCCtxParams(zcs->requestedParams, params);
-    return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL /*cdict*/, zcs->requestedParams, pledgedSrcSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
+    return 0;
 }

 size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel)
 {
-    ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel);
-    return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, zcs->requestedParams, ZSTD_CONTENTSIZE_UNKNOWN);
+    DEBUGLOG(4, "ZSTD_initCStream_usingDict");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
+    return 0;
 }

 size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss)
 {
-    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;  /* temporary : 0 interpreted as "unknown" during transition period. Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. `0` will be interpreted as "empty" in the future */
-    ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel);
-    return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, zcs->requestedParams, pledgedSrcSize);
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_srcSize");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    return 0;
 }

 size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel)
 {
    DEBUGLOG(4, "ZSTD_initCStream");
-    return ZSTD_initCStream_srcSize(zcs, compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    return 0;
 }

 /*======   Compression   ======*/
@@ -3847,10 +3450,10 @@ static size_t ZSTD_limitCopy(void* dst, size_t dstCapacity,
 *  internal function for all *compressStream*() variants
 *  non-static, because can be called from zstdmt_compress.c
 * @return : hint size for next input */
-size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
-                                   ZSTD_outBuffer* output,
-                                   ZSTD_inBuffer* input,
-                                   ZSTD_EndDirective const flushMode)
+static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
+                                          ZSTD_outBuffer* output,
+                                          ZSTD_inBuffer* input,
+                                          ZSTD_EndDirective const flushMode)
 {
    const char* const istart = (const char*)input->src;
    const char* const iend = istart + input->size;
@@ -3873,8 +3476,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
        switch(zcs->streamStage)
        {
        case zcss_init:
-            /* call ZSTD_initCStream() first ! */
-            return ERROR(init_missing);
+            RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!");

        case zcss_load:
            if ( (flushMode == ZSTD_e_end)
@@ -3884,7 +3486,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
                size_t const cSize = ZSTD_compressEnd(zcs,
                                                op, oend-op, ip, iend-ip);
                DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
                ip = iend;
                op += cSize;
                zcs->frameEnded = 1;
@@ -3925,7 +3527,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
                                    zcs->inBuff + zcs->inToCompress, iSize) :
                        ZSTD_compressContinue(zcs, cDst, oSize,
                                    zcs->inBuff + zcs->inToCompress, iSize);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
                zcs->frameEnded = lastBlock;
                /* prepare next block */
                zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
@@ -3953,7 +3555,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
        case zcss_flush:
            DEBUGLOG(5, "flush stage");
            {   size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
-                size_t const flushed = ZSTD_limitCopy(op, oend-op,
+                size_t const flushed = ZSTD_limitCopy(op, (size_t)(oend-op),
                            zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
                DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u",
                            (unsigned)toFlush, (unsigned)(oend-op), (unsigned)flushed);
@@ -4001,7 +3603,7 @@ static size_t ZSTD_nextInputSizeHint_MTorST(const ZSTD_CCtx* cctx)

 size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
 {
-    CHECK_F( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) );
+    FORWARD_IF_ERROR( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) );
    return ZSTD_nextInputSizeHint_MTorST(zcs);
 }

@@ -4013,14 +3615,15 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
 {
    DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp);
    /* check conditions */
-    if (output->pos > output->size) return ERROR(GENERIC);
-    if (input->pos  > input->size)  return ERROR(GENERIC);
+    RETURN_ERROR_IF(output->pos > output->size, GENERIC);
+    RETURN_ERROR_IF(input->pos  > input->size, GENERIC);
    assert(cctx!=NULL);

    /* transparent initialization stage */
    if (cctx->streamStage == zcss_init) {
        ZSTD_CCtx_params params = cctx->requestedParams;
        ZSTD_prefixDict const prefixDict = cctx->prefixDict;
+        FORWARD_IF_ERROR( ZSTD_initLocalDict(cctx) ); /* Init the local dict if present. */
        memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));   /* single usage */
        assert(prefixDict.dict==NULL || cctx->cdict==NULL);    /* only one can be set */
        DEBUGLOG(4, "ZSTD_compressStream2 : transparent init stage");
@@ -4039,11 +3642,11 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
                DEBUGLOG(4, "ZSTD_compressStream2: creating new mtctx for nbWorkers=%u",
                            params.nbWorkers);
                cctx->mtctx = ZSTDMT_createCCtx_advanced(params.nbWorkers, cctx->customMem);
-                if (cctx->mtctx == NULL) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(cctx->mtctx == NULL, memory_allocation);
            }
            /* mt compression */
            DEBUGLOG(4, "call ZSTDMT_initCStream_internal as nbWorkers=%u", params.nbWorkers);
-            CHECK_F( ZSTDMT_initCStream_internal(
+            FORWARD_IF_ERROR( ZSTDMT_initCStream_internal(
                        cctx->mtctx,
                        prefixDict.dict, prefixDict.dictSize, ZSTD_dct_rawContent,
                        cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
@@ -4051,7 +3654,7 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
            cctx->appliedParams.nbWorkers = params.nbWorkers;
        } else
 #endif
-        {   CHECK_F( ZSTD_resetCStream_internal(cctx,
+        {   FORWARD_IF_ERROR( ZSTD_resetCStream_internal(cctx,
                            prefixDict.dict, prefixDict.dictSize, prefixDict.dictContentType,
                            cctx->cdict,
                            params, cctx->pledgedSrcSizePlusOne-1) );
@@ -4063,20 +3666,30 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
    /* compression stage */
 #ifdef ZSTD_MULTITHREAD
    if (cctx->appliedParams.nbWorkers > 0) {
+        int const forceMaxProgress = (endOp == ZSTD_e_flush || endOp == ZSTD_e_end);
+        size_t flushMin;
+        assert(forceMaxProgress || endOp == ZSTD_e_continue /* Protection for a new flush type */);
        if (cctx->cParamsChanged) {
            ZSTDMT_updateCParams_whileCompressing(cctx->mtctx, &cctx->requestedParams);
            cctx->cParamsChanged = 0;
        }
-        {   size_t const flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
+        do {
+            flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
            if ( ZSTD_isError(flushMin)
              || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */
                ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
            }
-            DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic");
-            return flushMin;
-    }   }
+            FORWARD_IF_ERROR(flushMin);
+        } while (forceMaxProgress && flushMin != 0 && output->pos < output->size);
+        DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic");
+        /* Either we don't require maximum forward progress, we've finished the
+         * flush, or we are out of output space.
+         */
+        assert(!forceMaxProgress || flushMin == 0 || output->pos == output->size);
+        return flushMin;
+    }
 #endif
-    CHECK_F( ZSTD_compressStream_generic(cctx, output, input, endOp) );
+    FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) );
    DEBUGLOG(5, "completed ZSTD_compressStream2");
    return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */
 }
@@ -4107,10 +3720,10 @@ size_t ZSTD_compress2(ZSTD_CCtx* cctx,
                                        dst, dstCapacity, &oPos,
                                        src, srcSize, &iPos,
                                        ZSTD_e_end);
-        if (ZSTD_isError(result)) return result;
+        FORWARD_IF_ERROR(result);
        if (result != 0) {  /* compression not completed, due to lack of output space */
            assert(oPos == dstCapacity);
-            return ERROR(dstSize_tooSmall);
+            RETURN_ERROR(dstSize_tooSmall);
        }
        assert(iPos == srcSize);   /* all input is expected consumed */
        return oPos;
@@ -4132,11 +3745,11 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
 {
    ZSTD_inBuffer input = { NULL, 0, 0 };
    size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end);
-    CHECK_F( remainingToFlush );
+    FORWARD_IF_ERROR( remainingToFlush );
    if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush;   /* minimal estimation */
    /* single thread mode : attempt to calculate remaining to flush more precisely */
    {   size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE;
-        size_t const checksumSize = zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4;
+        size_t const checksumSize = (size_t)(zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4);
        size_t const toFlush = remainingToFlush + lastBlockSize + checksumSize;
        DEBUGLOG(4, "ZSTD_endStream : remaining to flush : %u", (unsigned)toFlush);
        return toFlush;
@@ -4151,7 +3764,7 @@ int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
 int ZSTD_minCLevel(void) { return (int)-ZSTD_TARGETLENGTH_MAX; }

 static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = {
-{   /* "default" - guarantees a monotonically increasing memory budget */
+{   /* "default" - for any srcSize > 256 KB */
    /* W,  C,  H,  S,  L, TL, strat */
    { 19, 12, 13,  1,  6,  1, ZSTD_fast    },  /* base for negative levels */
    { 19, 13, 14,  1,  7,  0, ZSTD_fast    },  /* level  1 */
@@ -4258,13 +3871,13 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV
 };

 /*! ZSTD_getCParams() :
-*  @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
-*   Size values are optional, provide 0 if not known or unused */
+ * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
+ *  Size values are optional, provide 0 if not known or unused */
 ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize)
 {
    size_t const addedSize = srcSizeHint ? 0 : 500;
-    U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : (U64)-1;
-    U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB);   /* intentional underflow for srcSizeHint == 0 */
+    U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : ZSTD_CONTENTSIZE_UNKNOWN;  /* intentional overflow for srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN */
+    U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB);
    int row = compressionLevel;
    DEBUGLOG(5, "ZSTD_getCParams (cLevel=%i)", compressionLevel);
    if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT;   /* 0 == default */
@@ -4272,13 +3885,14 @@ ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long l
    if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL;
    {   ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row];
        if (compressionLevel < 0) cp.targetLength = (unsigned)(-compressionLevel);   /* acceleration factor */
-        return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize);
+        return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize);               /* refine parameters based on srcSize & dictSize */
    }
 }

 /*! ZSTD_getParams() :
-*   same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`).
-*   All fields of `ZSTD_frameParameters` are set to default (0) */
+ *  same idea as ZSTD_getCParams()
+ * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`).
+ *  Fields of `ZSTD_frameParameters` are set to default values */
 ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) {
    ZSTD_parameters params;
    ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSizeHint, dictSize);
@@ -33,13 +33,13 @@ extern "C" {
 ***************************************/
 #define kSearchStrength      8
 #define HASH_READ_SIZE       8
-#define ZSTD_DUBT_UNSORTED_MARK 1   /* For btlazy2 strategy, index 1 now means "unsorted".
+#define ZSTD_DUBT_UNSORTED_MARK 1   /* For btlazy2 strategy, index ZSTD_DUBT_UNSORTED_MARK==1 means "unsorted".
                                       It could be confused for a real successor at index "1", if sorted as larger than its predecessor.
                                       It's not a big deal though : candidate will just be sorted again.
-                                       Additionnally, candidate position 1 will be lost.
+                                       Additionally, candidate position 1 will be lost.
                                       But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss.
-                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be misdhandled after table re-use with a different strategy
-                                       Constant required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */
+                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy.
+                                       This constant is required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */


 /*-*************************************
@@ -54,6 +54,14 @@ typedef struct ZSTD_prefixDict_s {
    ZSTD_dictContentType_e dictContentType;
 } ZSTD_prefixDict;

+typedef struct {
+    void* dictBuffer;
+    void const* dict;
+    size_t dictSize;
+    ZSTD_dictContentType_e dictContentType;
+    ZSTD_CDict* cdict;
+} ZSTD_localDict;
+
 typedef struct {
    U32 CTable[HUF_CTABLE_SIZE_U32(255)];
    HUF_repeat repeatMode;
@@ -107,6 +115,7 @@ typedef struct {
    U32  offCodeSumBasePrice;    /* to compare to log2(offreq)  */
    ZSTD_OptPrice_e priceType;   /* prices can be determined dynamically, or follow a pre-defined cost structure */
    const ZSTD_entropyCTables_t* symbolCosts;  /* pre-calculated dictionary statistics */
+    ZSTD_literalCompressionMode_e literalCompressionMode;
 } optState_t;

 typedef struct {
@@ -119,21 +128,20 @@ typedef struct {
    BYTE const* base;       /* All regular indexes relative to this position */
    BYTE const* dictBase;   /* extDict indexes relative to this position */
    U32 dictLimit;          /* below that point, need extDict */
-    U32 lowLimit;           /* below that point, no more data */
+    U32 lowLimit;           /* below that point, no more valid data */
 } ZSTD_window_t;

 typedef struct ZSTD_matchState_t ZSTD_matchState_t;
 struct ZSTD_matchState_t {
    ZSTD_window_t window;   /* State for window round buffer management */
-    U32 loadedDictEnd;      /* index of end of dictionary */
+    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential. When dict referential is copied into active context (i.e. not attached), effectively same value as dictSize, since referential starts from zero */
    U32 nextToUpdate;       /* index from which to continue table update */
-    U32 nextToUpdate3;      /* index from which to continue table update */
    U32 hashLog3;           /* dispatch table : larger == faster, more memory */
    U32* hashTable;
    U32* hashTable3;
    U32* chainTable;
    optState_t opt;         /* optimal parser state */
-    const ZSTD_matchState_t * dictMatchState;
+    const ZSTD_matchState_t* dictMatchState;
    ZSTD_compressionParameters cParams;
 };

@@ -186,8 +194,12 @@ struct ZSTD_CCtx_params_s {
    int compressionLevel;
    int forceWindow;           /* force back-references to respect limit of
                                * 1<<wLog, even for dictionary */
+    size_t targetCBlockSize;   /* Tries to fit compressed block size to be around targetCBlockSize.
+                                * No target when targetCBlockSize == 0.
+                                * There is no guarantee on compressed block size */

    ZSTD_dictAttachPref_e attachDictPref;
+    ZSTD_literalCompressionMode_e literalCompressionMode;

    /* Multithreading: used to pass parameters to mtctx */
    int nbWorkers;
@@ -243,7 +255,7 @@ struct ZSTD_CCtx_s {
    U32    frameEnded;

    /* Dictionary */
-    ZSTD_CDict* cdictLocal;
+    ZSTD_localDict localDict;
    const ZSTD_CDict* cdict;
    ZSTD_prefixDict prefixDict;   /* single-usage dictionary */

@@ -295,6 +307,30 @@ MEM_STATIC U32 ZSTD_MLcode(U32 mlBase)
    return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase];
 }

+/* ZSTD_cParam_withinBounds:
+ * @return 1 if value is within cParam bounds,
+ * 0 otherwise */
+MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
+{
+    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+    if (ZSTD_isError(bounds.error)) return 0;
+    if (value < bounds.lowerBound) return 0;
+    if (value > bounds.upperBound) return 0;
+    return 1;
+}
+
+/* ZSTD_minGain() :
+ * minimum compression required
+ * to generate a compress block or a compressed literals section.
+ * note : use same formula for both situations */
+MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
+{
+    U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
+    ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
+    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
+    return (srcSize >> minlog) + 2;
+}
+
 /*! ZSTD_storeSeq() :
 *  Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
 *  `offsetCode` : distance to match + 3 (values 1-3 are repCodes).
@@ -314,7 +350,7 @@ MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const v
    /* copy Literals */
    assert(seqStorePtr->maxNbLit <= 128 KB);
    assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + seqStorePtr->maxNbLit);
-    ZSTD_wildcopy(seqStorePtr->lit, literals, litLength);
+    ZSTD_wildcopy(seqStorePtr->lit, literals, litLength, ZSTD_no_overlap);
    seqStorePtr->lit += litLength;

    /* literal Length */
@@ -554,6 +590,9 @@ MEM_STATIC U64 ZSTD_rollingHash_rotate(U64 hash, BYTE toRemove, BYTE toAdd, U64
 /*-*************************************
 *  Round buffer management
 ***************************************/
+#if (ZSTD_WINDOWLOG_MAX_64 > 31)
+# error "ZSTD_WINDOWLOG_MAX is too large : would overflow ZSTD_CURRENT_MAX"
+#endif
 /* Max current allowed */
 #define ZSTD_CURRENT_MAX ((3U << 29) + (1U << ZSTD_WINDOWLOG_MAX))
 /* Maximum chunk size before overflow correction needs to be called again */
@@ -665,31 +704,49 @@ MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog,
 * Updates lowLimit so that:
 *    (srcEnd - base) - lowLimit == maxDist + loadedDictEnd
 *
- * This allows a simple check that index >= lowLimit to see if index is valid.
- * This must be called before a block compression call, with srcEnd as the block
- * source end.
+ * It ensures index is valid as long as index >= lowLimit.
+ * This must be called before a block compression call.
 *
- * If loadedDictEndPtr is not NULL, we set it to zero once we update lowLimit.
- * This is because dictionaries are allowed to be referenced as long as the last
- * byte of the dictionary is in the window, but once they are out of range,
- * they cannot be referenced. If loadedDictEndPtr is NULL, we use
- * loadedDictEnd == 0.
+ * loadedDictEnd is only defined if a dictionary is in use for current compression.
+ * As the name implies, loadedDictEnd represents the index at end of dictionary.
+ * The value lies within context's referential, it can be directly compared to blockEndIdx.
 *
- * In normal dict mode, the dict is between lowLimit and dictLimit. In
- * dictMatchState mode, lowLimit and dictLimit are the same, and the dictionary
- * is below them. forceWindow and dictMatchState are therefore incompatible.
+ * If loadedDictEndPtr is NULL, no dictionary is in use, and we use loadedDictEnd == 0.
+ * If loadedDictEndPtr is not NULL, we set it to zero after updating lowLimit.
+ * This is because dictionaries are allowed to be referenced fully
+ * as long as the last byte of the dictionary is in the window.
+ * Once input has progressed beyond window size, dictionary cannot be referenced anymore.
+ *
+ * In normal dict mode, the dictionary lies between lowLimit and dictLimit.
+ * In dictMatchState mode, lowLimit and dictLimit are the same,
+ * and the dictionary is below them.
+ * forceWindow and dictMatchState are therefore incompatible.
 */
 MEM_STATIC void
 ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
-                           void const* srcEnd,
-                           U32 maxDist,
-                           U32* loadedDictEndPtr,
+                     const void* blockEnd,
+                           U32   maxDist,
+                           U32*  loadedDictEndPtr,
                     const ZSTD_matchState_t** dictMatchStatePtr)
 {
-    U32 const blockEndIdx = (U32)((BYTE const*)srcEnd - window->base);
-    U32 loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
-    DEBUGLOG(5, "ZSTD_window_enforceMaxDist: blockEndIdx=%u, maxDist=%u",
-                (unsigned)blockEndIdx, (unsigned)maxDist);
+    U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+    U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
+    DEBUGLOG(5, "ZSTD_window_enforceMaxDist: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+
+    /* - When there is no dictionary : loadedDictEnd == 0.
+         In which case, the test (blockEndIdx > maxDist) is merely to avoid
+         overflowing next operation `newLowLimit = blockEndIdx - maxDist`.
+       - When there is a standard dictionary :
+         Index referential is copied from the dictionary,
+         which means it starts from 0.
+         In which case, loadedDictEnd == dictSize,
+         and it makes sense to compare `blockEndIdx > maxDist + dictSize`
+         since `blockEndIdx` also starts from zero.
+       - When there is an attached dictionary :
+         loadedDictEnd is expressed within the referential of the context,
+         so it can be directly compared against blockEndIdx.
+    */
    if (blockEndIdx > maxDist + loadedDictEnd) {
        U32 const newLowLimit = blockEndIdx - maxDist;
        if (window->lowLimit < newLowLimit) window->lowLimit = newLowLimit;
@@ -698,10 +755,31 @@ ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
                        (unsigned)window->dictLimit, (unsigned)window->lowLimit);
            window->dictLimit = window->lowLimit;
        }
-        if (loadedDictEndPtr)
-            *loadedDictEndPtr = 0;
-        if (dictMatchStatePtr)
-            *dictMatchStatePtr = NULL;
+        /* On reaching window size, dictionaries are invalidated */
+        if (loadedDictEndPtr) *loadedDictEndPtr = 0;
+        if (dictMatchStatePtr) *dictMatchStatePtr = NULL;
+    }
+}
+
+/* Similar to ZSTD_window_enforceMaxDist(),
+ * but only invalidates dictionary
+ * when input progresses beyond window size. */
+MEM_STATIC void
+ZSTD_checkDictValidity(ZSTD_window_t* window,
+                       const void* blockEnd,
+                             U32   maxDist,
+                             U32*  loadedDictEndPtr,
+                       const ZSTD_matchState_t** dictMatchStatePtr)
+{
+    U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+    U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
+    DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+
+    if (loadedDictEnd && (blockEndIdx > maxDist + loadedDictEnd)) {
+        /* On reaching window size, dictionaries are invalidated */
+        if (loadedDictEndPtr) *loadedDictEndPtr = 0;
+        if (dictMatchStatePtr) *dictMatchStatePtr = NULL;
    }
 }

@@ -806,13 +884,6 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,

 void ZSTD_resetSeqStore(seqStore_t* ssPtr);

-/*! ZSTD_compressStream_generic() :
- *  Private use only. To be called from zstdmt_compress.c in single-thread mode. */
-size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
-                                   ZSTD_outBuffer* output,
-                                   ZSTD_inBuffer* input,
-                                   ZSTD_EndDirective const flushMode);
-
 /*! ZSTD_getCParamsFromCDict() :
 *  as the name implies */
 ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict);
@@ -839,7 +910,7 @@ size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx,
 /* ZSTD_writeLastEmptyBlock() :
 * output an empty Block with end-of-frame mark to complete a frame
 * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
- *           or an error code if `dstCapcity` is too small (<ZSTD_blockHeaderSize)
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
 */
 size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity);

@@ -0,0 +1,149 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_literals.h"
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE* const)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    memcpy(ostart + flSize, src, srcSize);
+    return srcSize + flSize;
+}
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE* const)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    ostart[flSize] = *(const BYTE*)src;
+    return flSize+1;
+}
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* workspace, size_t wkspSize,
+                        const int bmi2)
+{
+    size_t const minGain = ZSTD_minGain(srcSize, strategy);
+    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
+    BYTE*  const ostart = (BYTE*)dst;
+    U32 singleStream = srcSize < 256;
+    symbolEncodingType_e hType = set_compressed;
+    size_t cLitSize;
+
+    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
+                disableLiteralCompression);
+
+    /* Prepare nextEntropy assuming reusing the existing table */
+    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+
+    if (disableLiteralCompression)
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+
+    /* small ? don't even attempt compression (speed opt) */
+#   define COMPRESS_LITERALS_SIZE_MIN 63
+    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
+        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+
+    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
+    {   HUF_repeat repeat = prevHuf->repeatMode;
+        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
+        cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
+                                : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
+        if (repeat != HUF_repeat_none) {
+            /* reused the existing table */
+            hType = set_repeat;
+        }
+    }
+
+    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
+        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+    if (cLitSize==1) {
+        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+    }
+
+    if (hType == set_compressed) {
+        /* using a newly constructed table */
+        nextHuf->repeatMode = HUF_repeat_check;
+    }
+
+    /* Build header */
+    switch(lhSize)
+    {
+    case 3: /* 2 - 2 - 10 - 10 */
+        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
+            MEM_writeLE24(ostart, lhc);
+            break;
+        }
+    case 4: /* 2 - 2 - 14 - 14 */
+        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
+            MEM_writeLE32(ostart, lhc);
+            break;
+        }
+    case 5: /* 2 - 2 - 18 - 18 */
+        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
+            MEM_writeLE32(ostart, lhc);
+            ostart[4] = (BYTE)(cLitSize >> 10);
+            break;
+        }
+    default:  /* not possible : lhSize is {3,4,5} */
+        assert(0);
+    }
+    return lhSize+cLitSize;
+}
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_LITERALS_H
+#define ZSTD_COMPRESS_LITERALS_H
+
+#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */
+
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* workspace, size_t wkspSize,
+                        const int bmi2);
+
+#endif /* ZSTD_COMPRESS_LITERALS_H */
@@ -0,0 +1,415 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_sequences.h"
+
+/**
+ * -log2(x / 256) lookup table for x in [0, 256).
+ * If x == 0: Return 0
+ * Else: Return floor(-log2(x / 256) * 256)
+ */
+static unsigned const kInverseProbabilityLog256[256] = {
+    0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
+    1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
+    874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
+    724,  714,  704,  694,  685,  676,  667,  658,  650,  642,  633,  626,
+    618,  610,  603,  595,  588,  581,  574,  567,  561,  554,  548,  542,
+    535,  529,  523,  517,  512,  506,  500,  495,  489,  484,  478,  473,
+    468,  463,  458,  453,  448,  443,  438,  434,  429,  424,  420,  415,
+    411,  407,  402,  398,  394,  390,  386,  382,  377,  373,  370,  366,
+    362,  358,  354,  350,  347,  343,  339,  336,  332,  329,  325,  322,
+    318,  315,  311,  308,  305,  302,  298,  295,  292,  289,  286,  282,
+    279,  276,  273,  270,  267,  264,  261,  258,  256,  253,  250,  247,
+    244,  241,  239,  236,  233,  230,  228,  225,  222,  220,  217,  215,
+    212,  209,  207,  204,  202,  199,  197,  194,  192,  190,  187,  185,
+    182,  180,  178,  175,  173,  171,  168,  166,  164,  162,  159,  157,
+    155,  153,  151,  149,  146,  144,  142,  140,  138,  136,  134,  132,
+    130,  128,  126,  123,  121,  119,  117,  115,  114,  112,  110,  108,
+    106,  104,  102,  100,  98,   96,   94,   93,   91,   89,   87,   85,
+    83,   82,   80,   78,   76,   74,   73,   71,   69,   67,   66,   64,
+    62,   61,   59,   57,   55,   54,   52,   50,   49,   47,   46,   44,
+    42,   41,   39,   37,   36,   34,   33,   31,   30,   28,   26,   25,
+    23,   22,   20,   19,   17,   16,   14,   13,   11,   10,   8,    7,
+    5,    4,    2,    1,
+};
+
+static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
+  void const* ptr = ctable;
+  U16 const* u16ptr = (U16 const*)ptr;
+  U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
+  return maxSymbolValue;
+}
+
+/**
+ * Returns the cost in bytes of encoding the normalized count header.
+ * Returns an error if any of the helper functions return an error.
+ */
+static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
+                              size_t const nbSeq, unsigned const FSELog)
+{
+    BYTE wksp[FSE_NCOUNTBOUND];
+    S16 norm[MaxSeq + 1];
+    const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
+    return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution described by count
+ * using the entropy bound.
+ */
+static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
+{
+    unsigned cost = 0;
+    unsigned s;
+    for (s = 0; s <= max; ++s) {
+        unsigned norm = (unsigned)((256 * count[s]) / total);
+        if (count[s] != 0 && norm == 0)
+            norm = 1;
+        assert(count[s] < total);
+        cost += count[s] * kInverseProbabilityLog256[norm];
+    }
+    return cost >> 8;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using ctable.
+ * Returns an error if ctable cannot represent all the symbols in count.
+ */
+static size_t ZSTD_fseBitCost(
+    FSE_CTable const* ctable,
+    unsigned const* count,
+    unsigned const max)
+{
+    unsigned const kAccuracyLog = 8;
+    size_t cost = 0;
+    unsigned s;
+    FSE_CState_t cstate;
+    FSE_initCState(&cstate, ctable);
+    RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
+                    "Repeat FSE_CTable has maxSymbolValue %u < %u",
+                    ZSTD_getFSEMaxSymbolValue(ctable), max);
+    for (s = 0; s <= max; ++s) {
+        unsigned const tableLog = cstate.stateLog;
+        unsigned const badCost = (tableLog + 1) << kAccuracyLog;
+        unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
+        if (count[s] == 0)
+            continue;
+        RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
+                        "Repeat FSE_CTable has Prob[%u] == 0", s);
+        cost += count[s] * bitCost;
+    }
+    return cost >> kAccuracyLog;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using the
+ * table described by norm. The max symbol support by norm is assumed >= max.
+ * norm must be valid for every symbol with non-zero probability in count.
+ */
+static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
+                                    unsigned const* count, unsigned const max)
+{
+    unsigned const shift = 8 - accuracyLog;
+    size_t cost = 0;
+    unsigned s;
+    assert(accuracyLog <= 8);
+    for (s = 0; s <= max; ++s) {
+        unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
+        unsigned const norm256 = normAcc << shift;
+        assert(norm256 > 0);
+        assert(norm256 < 256);
+        cost += count[s] * kInverseProbabilityLog256[norm256];
+    }
+    return cost >> 8;
+}
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy)
+{
+    ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
+    if (mostFrequent == nbSeq) {
+        *repeatMode = FSE_repeat_none;
+        if (isDefaultAllowed && nbSeq <= 2) {
+            /* Prefer set_basic over set_rle when there are 2 or less symbols,
+             * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
+             * If basic encoding isn't possible, always choose RLE.
+             */
+            DEBUGLOG(5, "Selected set_basic");
+            return set_basic;
+        }
+        DEBUGLOG(5, "Selected set_rle");
+        return set_rle;
+    }
+    if (strategy < ZSTD_lazy) {
+        if (isDefaultAllowed) {
+            size_t const staticFse_nbSeq_max = 1000;
+            size_t const mult = 10 - strategy;
+            size_t const baseLog = 3;
+            size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog;  /* 28-36 for offset, 56-72 for lengths */
+            assert(defaultNormLog >= 5 && defaultNormLog <= 6);  /* xx_DEFAULTNORMLOG */
+            assert(mult <= 9 && mult >= 7);
+            if ( (*repeatMode == FSE_repeat_valid)
+              && (nbSeq < staticFse_nbSeq_max) ) {
+                DEBUGLOG(5, "Selected set_repeat");
+                return set_repeat;
+            }
+            if ( (nbSeq < dynamicFse_nbSeq_min)
+              || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
+                DEBUGLOG(5, "Selected set_basic");
+                /* The format allows default tables to be repeated, but it isn't useful.
+                 * When using simple heuristics to select encoding type, we don't want
+                 * to confuse these tables with dictionaries. When running more careful
+                 * analysis, we don't need to waste time checking both repeating tables
+                 * and default tables.
+                 */
+                *repeatMode = FSE_repeat_none;
+                return set_basic;
+            }
+        }
+    } else {
+        size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
+        size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
+        size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
+        size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
+
+        if (isDefaultAllowed) {
+            assert(!ZSTD_isError(basicCost));
+            assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
+        }
+        assert(!ZSTD_isError(NCountCost));
+        assert(compressedCost < ERROR(maxCode));
+        DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
+                    (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
+        if (basicCost <= repeatCost && basicCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_basic");
+            assert(isDefaultAllowed);
+            *repeatMode = FSE_repeat_none;
+            return set_basic;
+        }
+        if (repeatCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_repeat");
+            assert(!ZSTD_isError(repeatCost));
+            return set_repeat;
+        }
+        assert(compressedCost < basicCost && compressedCost < repeatCost);
+    }
+    DEBUGLOG(5, "Selected set_compressed");
+    *repeatMode = FSE_repeat_check;
+    return set_compressed;
+}
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* workspace, size_t workspaceSize)
+{
+    BYTE* op = (BYTE*)dst;
+    const BYTE* const oend = op + dstCapacity;
+    DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
+
+    switch (type) {
+    case set_rle:
+        FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
+        RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
+        *op = codeTable[0];
+        return 1;
+    case set_repeat:
+        memcpy(nextCTable, prevCTable, prevCTableSize);
+        return 0;
+    case set_basic:
+        FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
+        return 0;
+    case set_compressed: {
+        S16 norm[MaxSeq + 1];
+        size_t nbSeq_1 = nbSeq;
+        const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+        if (count[codeTable[nbSeq-1]] > 1) {
+            count[codeTable[nbSeq-1]]--;
+            nbSeq_1--;
+        }
+        assert(nbSeq_1 > 1);
+        FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
+        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
+            FORWARD_IF_ERROR(NCountSize);
+            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
+            return NCountSize;
+        }
+    }
+    default: assert(0); RETURN_ERROR(GENERIC);
+    }
+}
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_encodeSequences_body(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    BIT_CStream_t blockStream;
+    FSE_CState_t  stateMatchLength;
+    FSE_CState_t  stateOffsetBits;
+    FSE_CState_t  stateLitLength;
+
+    RETURN_ERROR_IF(
+        ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
+        dstSize_tooSmall, "not enough space remaining");
+    DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
+                (int)(blockStream.endPtr - blockStream.startPtr),
+                (unsigned)dstCapacity);
+
+    /* first symbols */
+    FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateOffsetBits,  CTable_OffsetBits,  ofCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateLitLength,   CTable_LitLength,   llCodeTable[nbSeq-1]);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    if (longOffsets) {
+        U32 const ofBits = ofCodeTable[nbSeq-1];
+        int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+        if (extraBits) {
+            BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
+            BIT_flushBits(&blockStream);
+        }
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
+                    ofBits - extraBits);
+    } else {
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
+    }
+    BIT_flushBits(&blockStream);
+
+    {   size_t n;
+        for (n=nbSeq-2 ; n<nbSeq ; n--) {      /* intentional underflow */
+            BYTE const llCode = llCodeTable[n];
+            BYTE const ofCode = ofCodeTable[n];
+            BYTE const mlCode = mlCodeTable[n];
+            U32  const llBits = LL_bits[llCode];
+            U32  const ofBits = ofCode;
+            U32  const mlBits = ML_bits[mlCode];
+            DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
+                        (unsigned)sequences[n].litLength,
+                        (unsigned)sequences[n].matchLength + MINMATCH,
+                        (unsigned)sequences[n].offset);
+                                                                            /* 32b*/  /* 64b*/
+                                                                            /* (7)*/  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode);       /* 15 */  /* 15 */
+            FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode);      /* 24 */  /* 24 */
+            if (MEM_32bits()) BIT_flushBits(&blockStream);                  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateLitLength, llCode);        /* 16 */  /* 33 */
+            if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
+                BIT_flushBits(&blockStream);                                /* (7)*/
+            BIT_addBits(&blockStream, sequences[n].litLength, llBits);
+            if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
+            BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
+            if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
+            if (longOffsets) {
+                int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+                if (extraBits) {
+                    BIT_addBits(&blockStream, sequences[n].offset, extraBits);
+                    BIT_flushBits(&blockStream);                            /* (7)*/
+                }
+                BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
+                            ofBits - extraBits);                            /* 31 */
+            } else {
+                BIT_addBits(&blockStream, sequences[n].offset, ofBits);     /* 31 */
+            }
+            BIT_flushBits(&blockStream);                                    /* (7)*/
+            DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
+    }   }
+
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
+    FSE_flushCState(&blockStream, &stateMatchLength);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
+    FSE_flushCState(&blockStream, &stateOffsetBits);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
+    FSE_flushCState(&blockStream, &stateLitLength);
+
+    {   size_t const streamSize = BIT_closeCStream(&blockStream);
+        RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
+        return streamSize;
+    }
+}
+
+static size_t
+ZSTD_encodeSequences_default(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+
+#if DYNAMIC_BMI2
+
+static TARGET_ATTRIBUTE("bmi2") size_t
+ZSTD_encodeSequences_bmi2(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+#endif
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
+{
+    DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
+                                         CTable_MatchLength, mlCodeTable,
+                                         CTable_OffsetBits, ofCodeTable,
+                                         CTable_LitLength, llCodeTable,
+                                         sequences, nbSeq, longOffsets);
+    }
+#endif
+    (void)bmi2;
+    return ZSTD_encodeSequences_default(dst, dstCapacity,
+                                        CTable_MatchLength, mlCodeTable,
+                                        CTable_OffsetBits, ofCodeTable,
+                                        CTable_LitLength, llCodeTable,
+                                        sequences, nbSeq, longOffsets);
+}
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_SEQUENCES_H
+#define ZSTD_COMPRESS_SEQUENCES_H
+
+#include "fse.h" /* FSE_repeat, FSE_CTable */
+#include "zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+
+typedef enum {
+    ZSTD_defaultDisallowed = 0,
+    ZSTD_defaultAllowed = 1
+} ZSTD_defaultPolicy_e;
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy);
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* workspace, size_t workspaceSize);
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
+
+#endif /* ZSTD_COMPRESS_SEQUENCES_H */
@@ -43,8 +43,7 @@ void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
            /* Only load extra positions for ZSTD_dtlm_full */
            if (dtlm == ZSTD_dtlm_fast)
                break;
-        }
-    }
+    }   }
 }


@@ -63,7 +62,10 @@ size_t ZSTD_compressBlock_doubleFast_generic(
    const BYTE* const istart = (const BYTE*)src;
    const BYTE* ip = istart;
    const BYTE* anchor = istart;
-    const U32 prefixLowestIndex = ms->window.dictLimit;
+    const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32 lowestValid = ms->window.dictLimit;
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 prefixLowestIndex = (endIndex - lowestValid > maxDistance) ? endIndex - maxDistance : lowestValid;
    const BYTE* const prefixLowest = base + prefixLowestIndex;
    const BYTE* const iend = istart + srcSize;
    const BYTE* const ilimit = iend - HASH_READ_SIZE;
@@ -95,8 +97,15 @@ size_t ZSTD_compressBlock_doubleFast_generic(
                                     dictCParams->chainLog : hBitsS;
    const U32 dictAndPrefixLength  = (U32)(ip - prefixLowest + dictEnd - dictStart);

+    DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_generic");
+
    assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);

+    /* if a dictionary is attached, it must be within window range */
+    if (dictMode == ZSTD_dictMatchState) {
+        assert(lowestValid + maxDistance >= endIndex);
+    }
+
    /* init */
    ip += (dictAndPrefixLength == 0);
    if (dictMode == ZSTD_noDict) {
@@ -138,7 +147,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
            const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
            goto _match_stored;
        }

@@ -147,7 +156,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
          && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
            mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
            goto _match_stored;
        }

@@ -170,8 +179,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
                offset = (U32)(current - dictMatchIndexL - dictIndexDelta);
                while (((ip>anchor) & (dictMatchL>dictStart)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */
                goto _match_found;
-            }
-        }
+        }   }

        if (matchIndexS > prefixLowestIndex) {
            /* check prefix short match */
@@ -186,16 +194,14 @@ size_t ZSTD_compressBlock_doubleFast_generic(

            if (match > dictStart && MEM_read32(match) == MEM_read32(ip)) {
                goto _search_next_long;
-            }
-        }
+        }   }

        ip += ((ip-anchor) >> kSearchStrength) + 1;
        continue;

 _search_next_long:

-        {
-            size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
+        {   size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
            size_t const dictHLNext = ZSTD_hashPtr(ip+1, dictHBitsL, 8);
            U32 const matchIndexL3 = hashLong[hl3];
            const BYTE* matchL3 = base + matchIndexL3;
@@ -221,9 +227,7 @@ _search_next_long:
                    offset = (U32)(current + 1 - dictMatchIndexL3 - dictIndexDelta);
                    while (((ip>anchor) & (dictMatchL3>dictStart)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */
                    goto _match_found;
-                }
-            }
-        }
+        }   }   }

        /* if no long +1 match, explore the short match we found */
        if (dictMode == ZSTD_dictMatchState && matchIndexS < prefixLowestIndex) {
@@ -242,7 +246,7 @@ _match_found:
        offset_2 = offset_1;
        offset_1 = offset;

-        ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+        ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);

 _match_stored:
        /* match found */
@@ -250,11 +254,14 @@ _match_stored:
        anchor = ip;

        if (ip <= ilimit) {
-            /* Fill Table */
-            hashLong[ZSTD_hashPtr(base+current+2, hBitsL, 8)] =
-                hashSmall[ZSTD_hashPtr(base+current+2, hBitsS, mls)] = current+2;  /* here because current+2 could be > iend-8 */
-            hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] =
-                hashSmall[ZSTD_hashPtr(ip-2, hBitsS, mls)] = (U32)(ip-2-base);
+            /* Complementary insertion */
+            /* done after iLimit test, as candidates could be > iend-8 */
+            {   U32 const indexToInsert = current+2;
+                hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert;
+                hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
+                hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert;
+                hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base);
+            }

            /* check immediate repcode */
            if (dictMode == ZSTD_dictMatchState) {
@@ -278,8 +285,7 @@ _match_stored:
                        continue;
                    }
                    break;
-                }
-            }
+            }   }

            if (dictMode == ZSTD_noDict) {
                while ( (ip <= ilimit)
@@ -294,14 +300,15 @@ _match_stored:
                    ip += rLength;
                    anchor = ip;
                    continue;   /* faster when present ... (?) */
-    }   }   }   }
+        }   }   }
+    }   /* while (ip < ilimit) */

    /* save reps for next block */
    rep[0] = offset_1 ? offset_1 : offsetSaved;
    rep[1] = offset_2 ? offset_2 : offsetSaved;

    /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }


@@ -360,10 +367,15 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
    const BYTE* anchor = istart;
    const BYTE* const iend = istart + srcSize;
    const BYTE* const ilimit = iend - 8;
-    const U32   prefixStartIndex = ms->window.dictLimit;
    const BYTE* const base = ms->window.base;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   maxDistance = 1U << cParams->windowLog;
+    const U32   lowestValid = ms->window.lowLimit;
+    const U32   lowLimit = (endIndex - lowestValid > maxDistance) ? endIndex - maxDistance : lowestValid;
+    const U32   dictStartIndex = lowLimit;
+    const U32   dictLimit = ms->window.dictLimit;
+    const U32   prefixStartIndex = (dictLimit > lowLimit) ? dictLimit : lowLimit;
    const BYTE* const prefixStart = base + prefixStartIndex;
-    const U32   dictStartIndex = ms->window.lowLimit;
    const BYTE* const dictBase = ms->window.dictBase;
    const BYTE* const dictStart = dictBase + dictStartIndex;
    const BYTE* const dictEnd = dictBase + prefixStartIndex;
@@ -371,6 +383,10 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(

    DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize);

+    /* if extDict is invalidated due to maxDistance, switch to "regular" variant */
+    if (prefixStartIndex == dictStartIndex)
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, mls, ZSTD_noDict);
+
    /* Search Loop */
    while (ip < ilimit) {  /* < instead of <=, because (ip+1) */
        const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
@@ -396,7 +412,7 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
            const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
        } else {
            if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
                const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend;
@@ -407,7 +423,7 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
                while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; }   /* catch up */
                offset_2 = offset_1;
                offset_1 = offset;
-                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);

            } else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) {
                size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
@@ -432,23 +448,27 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
                }
                offset_2 = offset_1;
                offset_1 = offset;
-                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);

            } else {
                ip += ((ip-anchor) >> kSearchStrength) + 1;
                continue;
        }   }

-        /* found a match : store it */
+        /* move to next sequence start */
        ip += mLength;
        anchor = ip;

        if (ip <= ilimit) {
-            /* Fill Table */
-            hashSmall[ZSTD_hashPtr(base+current+2, hBitsS, mls)] = current+2;
-            hashLong[ZSTD_hashPtr(base+current+2, hBitsL, 8)] = current+2;
-            hashSmall[ZSTD_hashPtr(ip-2, hBitsS, mls)] = (U32)(ip-2-base);
-            hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
+            /* Complementary insertion */
+            /* done after iLimit test, as candidates could be > iend-8 */
+            {   U32 const indexToInsert = current+2;
+                hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert;
+                hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
+                hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert;
+                hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base);
+            }
+
            /* check immediate repcode */
            while (ip <= ilimit) {
                U32 const current2 = (U32)(ip-base);
@@ -475,7 +495,7 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
    rep[1] = offset_2;

    /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }


@@ -13,7 +13,8 @@


 void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
-                        void const* end, ZSTD_dictTableLoadMethod_e dtlm)
+                        const void* const end,
+                        ZSTD_dictTableLoadMethod_e dtlm)
 {
    const ZSTD_compressionParameters* const cParams = &ms->cParams;
    U32* const hashTable = ms->hashTable;
@@ -41,11 +42,163 @@ void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
    }   }   }   }
 }

+
 FORCE_INLINE_TEMPLATE
 size_t ZSTD_compressBlock_fast_generic(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        void const* src, size_t srcSize,
-        U32 const mls, ZSTD_dictMode_e const dictMode)
+        U32 const mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32 const hlog = cParams->hashLog;
+    /* support stepSize of 0 */
+    size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const istart = (const BYTE*)src;
+    /* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */
+    const BYTE* ip0 = istart;
+    const BYTE* ip1;
+    const BYTE* anchor = istart;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   maxDistance = 1U << cParams->windowLog;
+    const U32   validStartIndex = ms->window.dictLimit;
+    const U32   prefixStartIndex = (endIndex - validStartIndex > maxDistance) ? endIndex - maxDistance : validStartIndex;
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - HASH_READ_SIZE;
+    U32 offset_1=rep[0], offset_2=rep[1];
+    U32 offsetSaved = 0;
+
+    /* init */
+    ip0 += (ip0 == prefixStart);
+    ip1 = ip0 + 1;
+    {
+        U32 const maxRep = (U32)(ip0 - prefixStart);
+        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
+        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
+    }
+
+    /* Main Search Loop */
+    while (ip1 < ilimit) {   /* < instead of <=, because check at ip0+2 */
+        size_t mLength;
+        BYTE const* ip2 = ip0 + 2;
+        size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls);
+        U32 const val0 = MEM_read32(ip0);
+        size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls);
+        U32 const val1 = MEM_read32(ip1);
+        U32 const current0 = (U32)(ip0-base);
+        U32 const current1 = (U32)(ip1-base);
+        U32 const matchIndex0 = hashTable[h0];
+        U32 const matchIndex1 = hashTable[h1];
+        BYTE const* repMatch = ip2-offset_1;
+        const BYTE* match0 = base + matchIndex0;
+        const BYTE* match1 = base + matchIndex1;
+        U32 offcode;
+        hashTable[h0] = current0;   /* update hash table */
+        hashTable[h1] = current1;   /* update hash table */
+
+        assert(ip0 + 1 == ip1);
+
+        if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) {
+            mLength = ip2[-1] == repMatch[-1] ? 1 : 0;
+            ip0 = ip2 - mLength;
+            match0 = repMatch - mLength;
+            offcode = 0;
+            goto _match;
+        }
+        if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) {
+            /* found a regular match */
+            goto _offset;
+        }
+        if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) {
+            /* found a regular match after one literal */
+            ip0 = ip1;
+            match0 = match1;
+            goto _offset;
+        }
+        {
+            size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
+            assert(step >= 2);
+            ip0 += step;
+            ip1 += step;
+            continue;
+        }
+_offset: /* Requires: ip0, match0 */
+        /* Compute the offset code */
+        offset_2 = offset_1;
+        offset_1 = (U32)(ip0-match0);
+        offcode = offset_1 + ZSTD_REP_MOVE;
+        mLength = 0;
+        /* Count the backwards match length */
+        while (((ip0>anchor) & (match0>prefixStart))
+             && (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */
+
+_match: /* Requires: ip0, match0, offcode */
+        /* Count the forward length */
+        mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4;
+        ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH);
+        /* match found */
+        ip0 += mLength;
+        anchor = ip0;
+        ip1 = ip0 + 1;
+
+        if (ip0 <= ilimit) {
+            /* Fill Table */
+            assert(base+current0+2 > istart);  /* check base overflow */
+            hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2;  /* here because current+2 could be > iend-8 */
+            hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
+
+            while ( (ip0 <= ilimit)
+                 && ( (offset_2>0)
+                    & (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) {
+                /* store sequence */
+                size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
+                U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
+                hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
+                ip0 += rLength;
+                ip1 = ip0 + 1;
+                ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
+                anchor = ip0;
+                continue;   /* faster when present (confirmed on gcc-8) ... (?) */
+            }
+        }
+    }
+
+    /* save reps for next block */
+    rep[0] = offset_1 ? offset_1 : offsetSaved;
+    rep[1] = offset_2 ? offset_2 : offsetSaved;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_fast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    ZSTD_compressionParameters const* cParams = &ms->cParams;
+    U32 const mls = cParams->minMatch;
+    assert(ms->dictMatchState == NULL);
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
+
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_compressBlock_fast_dictMatchState_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize, U32 const mls)
 {
    const ZSTD_compressionParameters* const cParams = &ms->cParams;
    U32* const hashTable = ms->hashTable;
@@ -64,46 +217,33 @@ size_t ZSTD_compressBlock_fast_generic(
    U32 offsetSaved = 0;

    const ZSTD_matchState_t* const dms = ms->dictMatchState;
-    const ZSTD_compressionParameters* const dictCParams =
-                                     dictMode == ZSTD_dictMatchState ?
-                                     &dms->cParams : NULL;
-    const U32* const dictHashTable = dictMode == ZSTD_dictMatchState ?
-                                     dms->hashTable : NULL;
-    const U32 dictStartIndex       = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.dictLimit : 0;
-    const BYTE* const dictBase     = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.base : NULL;
-    const BYTE* const dictStart    = dictMode == ZSTD_dictMatchState ?
-                                     dictBase + dictStartIndex : NULL;
-    const BYTE* const dictEnd      = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.nextSrc : NULL;
-    const U32 dictIndexDelta       = dictMode == ZSTD_dictMatchState ?
-                                     prefixStartIndex - (U32)(dictEnd - dictBase) :
-                                     0;
+    const ZSTD_compressionParameters* const dictCParams = &dms->cParams ;
+    const U32* const dictHashTable = dms->hashTable;
+    const U32 dictStartIndex       = dms->window.dictLimit;
+    const BYTE* const dictBase     = dms->window.base;
+    const BYTE* const dictStart    = dictBase + dictStartIndex;
+    const BYTE* const dictEnd      = dms->window.nextSrc;
+    const U32 dictIndexDelta       = prefixStartIndex - (U32)(dictEnd - dictBase);
    const U32 dictAndPrefixLength  = (U32)(ip - prefixStart + dictEnd - dictStart);
-    const U32 dictHLog             = dictMode == ZSTD_dictMatchState ?
-                                     dictCParams->hashLog : hlog;
+    const U32 dictHLog             = dictCParams->hashLog;

-    assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
+    /* if a dictionary is still attached, it necessarily means that
+     * it is within window size. So we just check it. */
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 endIndex = (U32)((size_t)(ip - base) + srcSize);
+    assert(endIndex - prefixStartIndex <= maxDistance);
+    (void)maxDistance; (void)endIndex;   /* these variables are not used when assert() is disabled */

-    /* otherwise, we would get index underflow when translating a dict index
-     * into a local index */
-    assert(dictMode != ZSTD_dictMatchState
-        || prefixStartIndex >= (U32)(dictEnd - dictBase));
+    /* ensure there will be no no underflow
+     * when translating a dict index into a local index */
+    assert(prefixStartIndex >= (U32)(dictEnd - dictBase));

    /* init */
    ip += (dictAndPrefixLength == 0);
-    if (dictMode == ZSTD_noDict) {
-        U32 const maxRep = (U32)(ip - prefixStart);
-        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
-        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
-    }
-    if (dictMode == ZSTD_dictMatchState) {
-        /* dictMatchState repCode checks don't currently handle repCode == 0
-         * disabling. */
-        assert(offset_1 <= dictAndPrefixLength);
-        assert(offset_2 <= dictAndPrefixLength);
-    }
+    /* dictMatchState repCode checks don't currently handle repCode == 0
+     * disabling. */
+    assert(offset_1 <= dictAndPrefixLength);
+    assert(offset_2 <= dictAndPrefixLength);

    /* Main Search Loop */
    while (ip < ilimit) {   /* < instead of <=, because repcode check at (ip+1) */
@@ -113,50 +253,37 @@ size_t ZSTD_compressBlock_fast_generic(
        U32 const matchIndex = hashTable[h];
        const BYTE* match = base + matchIndex;
        const U32 repIndex = current + 1 - offset_1;
-        const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
-                            && repIndex < prefixStartIndex) ?
+        const BYTE* repMatch = (repIndex < prefixStartIndex) ?
                               dictBase + (repIndex - dictIndexDelta) :
                               base + repIndex;
        hashTable[h] = current;   /* update hash table */

-        if ( (dictMode == ZSTD_dictMatchState)
-          && ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
+        if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
          && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
            const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
-        } else if ( dictMode == ZSTD_noDict
-                 && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
-            mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
-            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
        } else if ( (matchIndex <= prefixStartIndex) ) {
-            if (dictMode == ZSTD_dictMatchState) {
-                size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
-                U32 const dictMatchIndex = dictHashTable[dictHash];
-                const BYTE* dictMatch = dictBase + dictMatchIndex;
-                if (dictMatchIndex <= dictStartIndex ||
-                    MEM_read32(dictMatch) != MEM_read32(ip)) {
-                    assert(stepSize >= 1);
-                    ip += ((ip-anchor) >> kSearchStrength) + stepSize;
-                    continue;
-                } else {
-                    /* found a dict match */
-                    U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
-                    mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
-                    while (((ip>anchor) & (dictMatch>dictStart))
-                         && (ip[-1] == dictMatch[-1])) {
-                        ip--; dictMatch--; mLength++;
-                    } /* catch up */
-                    offset_2 = offset_1;
-                    offset_1 = offset;
-                    ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
-                }
-            } else {
+            size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
+            U32 const dictMatchIndex = dictHashTable[dictHash];
+            const BYTE* dictMatch = dictBase + dictMatchIndex;
+            if (dictMatchIndex <= dictStartIndex ||
+                MEM_read32(dictMatch) != MEM_read32(ip)) {
                assert(stepSize >= 1);
                ip += ((ip-anchor) >> kSearchStrength) + stepSize;
                continue;
+            } else {
+                /* found a dict match */
+                U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
+                mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
+                while (((ip>anchor) & (dictMatch>dictStart))
+                     && (ip[-1] == dictMatch[-1])) {
+                    ip--; dictMatch--; mLength++;
+                } /* catch up */
+                offset_2 = offset_1;
+                offset_1 = offset;
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
            }
        } else if (MEM_read32(match) != MEM_read32(ip)) {
            /* it's not a match, and we're not going to check the dictionary */
@@ -171,7 +298,7 @@ size_t ZSTD_compressBlock_fast_generic(
                 && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
            offset_2 = offset_1;
            offset_1 = offset;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
        }

        /* match found */
@@ -185,70 +312,34 @@ size_t ZSTD_compressBlock_fast_generic(
            hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);

            /* check immediate repcode */
-            if (dictMode == ZSTD_dictMatchState) {
-                while (ip <= ilimit) {
-                    U32 const current2 = (U32)(ip-base);
-                    U32 const repIndex2 = current2 - offset_2;
-                    const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
-                            dictBase - dictIndexDelta + repIndex2 :
-                            base + repIndex2;
-                    if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
-                       && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
-                        const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
-                        size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
-                        U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
-                        ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
-                        hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
-                        ip += repLength2;
-                        anchor = ip;
-                        continue;
-                    }
-                    break;
-                }
-            }
-
-            if (dictMode == ZSTD_noDict) {
-                while ( (ip <= ilimit)
-                     && ( (offset_2>0)
-                        & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
-                    /* store sequence */
-                    size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
-                    U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
-                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = (U32)(ip-base);
-                    ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
-                    ip += rLength;
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex2 = current2 - offset_2;
+                const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
+                        dictBase - dictIndexDelta + repIndex2 :
+                        base + repIndex2;
+                if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
+                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
+                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
+                    U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
+                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
+                    ip += repLength2;
                    anchor = ip;
-                    continue;   /* faster when present ... (?) */
-    }   }   }   }
+                    continue;
+                }
+                break;
+            }
+        }
+    }

    /* save reps for next block */
    rep[0] = offset_1 ? offset_1 : offsetSaved;
    rep[1] = offset_2 ? offset_2 : offsetSaved;

    /* Return the last literals size */
-    return iend - anchor;
-}
-
-
-size_t ZSTD_compressBlock_fast(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
-        void const* src, size_t srcSize)
-{
-    ZSTD_compressionParameters const* cParams = &ms->cParams;
-    U32 const mls = cParams->minMatch;
-    assert(ms->dictMatchState == NULL);
-    switch(mls)
-    {
-    default: /* includes case 3 */
-    case 4 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict);
-    case 5 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict);
-    case 6 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict);
-    case 7 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict);
-    }
+    return (size_t)(iend - anchor);
 }

 size_t ZSTD_compressBlock_fast_dictMatchState(
@@ -262,13 +353,13 @@ size_t ZSTD_compressBlock_fast_dictMatchState(
    {
    default: /* includes case 3 */
    case 4 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
    case 5 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
    case 6 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
    case 7 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
    }
 }

@@ -287,15 +378,24 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
    const BYTE* const istart = (const BYTE*)src;
    const BYTE* ip = istart;
    const BYTE* anchor = istart;
-    const U32   dictStartIndex = ms->window.lowLimit;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   maxDistance = 1U << cParams->windowLog;
+    const U32   validLow = ms->window.lowLimit;
+    const U32   lowLimit = (endIndex - validLow > maxDistance) ? endIndex - maxDistance : validLow;
+    const U32   dictStartIndex = lowLimit;
    const BYTE* const dictStart = dictBase + dictStartIndex;
-    const U32   prefixStartIndex = ms->window.dictLimit;
+    const U32   dictLimit = ms->window.dictLimit;
+    const U32   prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit;
    const BYTE* const prefixStart = base + prefixStartIndex;
    const BYTE* const dictEnd = dictBase + prefixStartIndex;
    const BYTE* const iend = istart + srcSize;
    const BYTE* const ilimit = iend - 8;
    U32 offset_1=rep[0], offset_2=rep[1];

+    /* switch to "regular" variant if extDict is invalidated due to maxDistance */
+    if (prefixStartIndex == dictStartIndex)
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls);
+
    /* Search Loop */
    while (ip < ilimit) {  /* < instead of <=, because (ip+1) */
        const size_t h = ZSTD_hashPtr(ip, hlog, mls);
@@ -315,7 +415,7 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
            const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
        } else {
            if ( (matchIndex < dictStartIndex) ||
                 (MEM_read32(match) != MEM_read32(ip)) ) {
@@ -331,7 +431,7 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
                offset = current - matchIndex;
                offset_2 = offset_1;
                offset_1 = offset;
-                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
        }   }

        /* found a match : store it */
@@ -366,7 +466,7 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
    rep[1] = offset_2;

    /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }


@@ -83,7 +83,10 @@ ZSTD_insertDUBT1(ZSTD_matchState_t* ms,
    U32* largerPtr  = smallerPtr + 1;
    U32 matchIndex = *smallerPtr;   /* this candidate is unsorted : next sorted candidate is reached through *smallerPtr, while *largerPtr contains previous unsorted candidate (which is already saved and can be overwritten) */
    U32 dummy32;   /* to be nullified at the end */
-    U32 const windowLow = ms->window.lowLimit;
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const maxDistance = 1U << cParams->windowLog;
+    U32 const windowLow = (current - windowValid > maxDistance) ? current - maxDistance : windowValid;
+

    DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)",
                current, dictLimit, windowLow);
@@ -239,7 +242,9 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,

    const BYTE* const base = ms->window.base;
    U32    const current = (U32)(ip-base);
-    U32    const windowLow = ms->window.lowLimit;
+    U32    const maxDistance = 1U << cParams->windowLog;
+    U32    const windowValid = ms->window.lowLimit;
+    U32    const windowLow = (current - windowValid > maxDistance) ? current - maxDistance : windowValid;

    U32*   const bt = ms->chainTable;
    U32    const btLog  = cParams->chainLog - 1;
@@ -490,8 +495,10 @@ size_t ZSTD_HcFindBestMatch_generic (
    const U32 dictLimit = ms->window.dictLimit;
    const BYTE* const prefixStart = base + dictLimit;
    const BYTE* const dictEnd = dictBase + dictLimit;
-    const U32 lowLimit = ms->window.lowLimit;
    const U32 current = (U32)(ip-base);
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 lowValid = ms->window.lowLimit;
+    const U32 lowLimit = (current - lowValid > maxDistance) ? current - maxDistance : lowValid;
    const U32 minChain = current > chainSize ? current - chainSize : 0;
    U32 nbAttempts = 1U << cParams->searchLog;
    size_t ml=4-1;
@@ -653,7 +660,6 @@ size_t ZSTD_compressBlock_lazy_generic(

    /* init */
    ip += (dictAndPrefixLength == 0);
-    ms->nextToUpdate3 = ms->nextToUpdate;
    if (dictMode == ZSTD_noDict) {
        U32 const maxRep = (U32)(ip - prefixLowest);
        if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0;
@@ -933,7 +939,6 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
    U32 offset_1 = rep[0], offset_2 = rep[1];

    /* init */
-    ms->nextToUpdate3 = ms->nextToUpdate;
    ip += (ip == prefixStart);

    /* Match Loop */
@@ -19,7 +19,7 @@ extern "C" {

 U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);

-void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). pre-emptively increase value of ZSTD_DUBT_UNSORTED_MARK */
+void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */

 size_t ZSTD_compressBlock_btlazy2(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
@@ -429,7 +429,7 @@ size_t ZSTD_ldm_generateSequences(
     */
    assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize);
    /* The input could be very large (in zstdmt), so it must be broken up into
-     * chunks to enforce the maximmum distance and handle overflow correction.
+     * chunks to enforce the maximum distance and handle overflow correction.
     */
    assert(sequences->pos <= sequences->size);
    assert(sequences->size <= sequences->capacity);
@@ -447,7 +447,7 @@ size_t ZSTD_ldm_generateSequences(
        if (ZSTD_window_needOverflowCorrection(ldmState->window, chunkEnd)) {
            U32 const ldmHSize = 1U << params->hashLog;
            U32 const correction = ZSTD_window_correctOverflow(
-                &ldmState->window, /* cycleLog */ 0, maxDist, src);
+                &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart);
            ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction);
        }
        /* 2. We enforce the maximum offset allowed.
@@ -64,9 +64,15 @@ MEM_STATIC double ZSTD_fCost(U32 price)
 }
 #endif

+static int ZSTD_compressedLiterals(optState_t const* const optPtr)
+{
+    return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed;
+}
+
 static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel)
 {
-    optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
    optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel);
    optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel);
    optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel);
@@ -99,6 +105,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
            const BYTE* const src, size_t const srcSize,
                  int const optLevel)
 {
+    int const compressedLiterals = ZSTD_compressedLiterals(optPtr);
    DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize);
    optPtr->priceType = zop_dynamic;

@@ -113,9 +120,10 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
            /* huffman table presumed generated by dictionary */
            optPtr->priceType = zop_dynamic;

-            assert(optPtr->litFreq != NULL);
-            optPtr->litSum = 0;
-            {   unsigned lit;
+            if (compressedLiterals) {
+                unsigned lit;
+                assert(optPtr->litFreq != NULL);
+                optPtr->litSum = 0;
                for (lit=0; lit<=MaxLit; lit++) {
                    U32 const scaleLog = 11;   /* scale to 2K */
                    U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
@@ -163,10 +171,11 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
        } else {  /* not a dictionary */

            assert(optPtr->litFreq != NULL);
-            {   unsigned lit = MaxLit;
+            if (compressedLiterals) {
+                unsigned lit = MaxLit;
                HIST_count_simple(optPtr->litFreq, &lit, src, srcSize);   /* use raw first block to init statistics */
+                optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
            }
-            optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);

            {   unsigned ll;
                for (ll=0; ll<=MaxLL; ll++)
@@ -190,7 +199,8 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,

    } else {   /* new block : re-use previous statistics, scaled down */

-        optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
+        if (compressedLiterals)
+            optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
        optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0);
        optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0);
        optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0);
@@ -207,6 +217,10 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
                                int optLevel)
 {
    if (litLength == 0) return 0;
+
+    if (!ZSTD_compressedLiterals(optPtr))
+        return (litLength << 3) * BITCOST_MULTIPLIER;  /* Uncompressed - 8 bytes per literal. */
+
    if (optPtr->priceType == zop_predef)
        return (litLength*6) * BITCOST_MULTIPLIER;  /* 6 bit per literal - no statistic used */

@@ -241,13 +255,13 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP
 * to provide a cost which is directly comparable to a match ending at same position */
 static int ZSTD_litLengthContribution(U32 const litLength, const optState_t* const optPtr, int optLevel)
 {
-    if (optPtr->priceType >= zop_predef) return WEIGHT(litLength, optLevel);
+    if (optPtr->priceType >= zop_predef) return (int)WEIGHT(litLength, optLevel);

    /* dynamic statistics */
    {   U32 const llCode = ZSTD_LLcode(litLength);
-        int const contribution = (LL_bits[llCode] * BITCOST_MULTIPLIER)
-                               + WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
-                               - WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
+        int const contribution = (int)(LL_bits[llCode] * BITCOST_MULTIPLIER)
+                               + (int)WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
+                               - (int)WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
 #if 1
        return contribution;
 #else
@@ -264,7 +278,7 @@ static int ZSTD_literalsContribution(const BYTE* const literals, U32 const litLe
                                     const optState_t* const optPtr,
                                     int optLevel)
 {
-    int const contribution = ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
+    int const contribution = (int)ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
                           + ZSTD_litLengthContribution(litLength, optPtr, optLevel);
    return contribution;
 }
@@ -310,7 +324,8 @@ static void ZSTD_updateStats(optState_t* const optPtr,
                             U32 offsetCode, U32 matchLength)
 {
    /* literals */
-    {   U32 u;
+    if (ZSTD_compressedLiterals(optPtr)) {
+        U32 u;
        for (u=0; u < litLength; u++)
            optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
        optPtr->litSum += litLength*ZSTD_LITFREQ_ADD;
@@ -357,13 +372,15 @@ MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)

 /* Update hashTable3 up to ip (excluded)
   Assumption : always within prefix (i.e. not within extDict) */
-static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE* const ip)
+static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms,
+                                              U32* nextToUpdate3,
+                                              const BYTE* const ip)
 {
    U32* const hashTable3 = ms->hashTable3;
    U32 const hashLog3 = ms->hashLog3;
    const BYTE* const base = ms->window.base;
-    U32 idx = ms->nextToUpdate3;
-    U32 const target = ms->nextToUpdate3 = (U32)(ip - base);
+    U32 idx = *nextToUpdate3;
+    U32 const target = (U32)(ip - base);
    size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3);
    assert(hashLog3 > 0);

@@ -372,6 +389,7 @@ static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE*
        idx++;
    }

+    *nextToUpdate3 = target;
    return hashTable3[hash3];
 }

@@ -488,9 +506,11 @@ static U32 ZSTD_insertBt1(
    }   }

    *smallerPtr = *largerPtr = 0;
-    if (bestLength > 384) return MIN(192, (U32)(bestLength - 384));   /* speed optimization */
-    assert(matchEndIdx > current + 8);
-    return matchEndIdx - (current + 8);
+    {   U32 positions = 0;
+        if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384));   /* speed optimization */
+        assert(matchEndIdx > current + 8);
+        return MAX(positions, matchEndIdx - (current + 8));
+    }
 }

 FORCE_INLINE_TEMPLATE
@@ -505,8 +525,13 @@ void ZSTD_updateTree_internal(
    DEBUGLOG(6, "ZSTD_updateTree_internal, from %u to %u  (dictMode:%u)",
                idx, target, dictMode);

-    while(idx < target)
-        idx += ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict);
+    while(idx < target) {
+        U32 const forward = ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict);
+        assert(idx < (U32)(idx + forward));
+        idx += forward;
+    }
+    assert((size_t)(ip - base) <= (size_t)(U32)(-1));
+    assert((size_t)(iend - base) <= (size_t)(U32)(-1));
    ms->nextToUpdate = target;
 }

@@ -516,16 +541,18 @@ void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) {

 FORCE_INLINE_TEMPLATE
 U32 ZSTD_insertBtAndGetAllMatches (
+                    ZSTD_match_t* matches,   /* store result (found matches) in this table (presumed large enough) */
                    ZSTD_matchState_t* ms,
+                    U32* nextToUpdate3,
                    const BYTE* const ip, const BYTE* const iLimit, const ZSTD_dictMode_e dictMode,
-                    U32 rep[ZSTD_REP_NUM],
+                    const U32 rep[ZSTD_REP_NUM],
                    U32 const ll0,   /* tells if associated literal length is 0 or not. This value must be 0 or 1 */
-                    ZSTD_match_t* matches,
                    const U32 lengthToBeat,
                    U32 const mls /* template */)
 {
    const ZSTD_compressionParameters* const cParams = &ms->cParams;
    U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
+    U32 const maxDistance = 1U << cParams->windowLog;
    const BYTE* const base = ms->window.base;
    U32 const current = (U32)(ip-base);
    U32 const hashLog = cParams->hashLog;
@@ -541,8 +568,9 @@ U32 ZSTD_insertBtAndGetAllMatches (
    U32 const dictLimit = ms->window.dictLimit;
    const BYTE* const dictEnd = dictBase + dictLimit;
    const BYTE* const prefixStart = base + dictLimit;
-    U32 const btLow = btMask >= current ? 0 : current - btMask;
-    U32 const windowLow = ms->window.lowLimit;
+    U32 const btLow = (btMask >= current) ? 0 : current - btMask;
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const windowLow = ((current - windowValid) > maxDistance) ? current - maxDistance : windowValid;
    U32 const matchLow = windowLow ? windowLow : 1;
    U32* smallerPtr = bt + 2*(current&btMask);
    U32* largerPtr  = bt + 2*(current&btMask) + 1;
@@ -612,7 +640,7 @@ U32 ZSTD_insertBtAndGetAllMatches (

    /* HC3 match finder */
    if ((mls == 3) /*static*/ && (bestLength < mls)) {
-        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, ip);
+        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip);
        if ((matchIndex3 >= matchLow)
          & (current - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) {
            size_t mlen;
@@ -638,9 +666,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
                     (ip+mlen == iLimit) ) {  /* best possible length */
                    ms->nextToUpdate = current+1;  /* skip insertion */
                    return 1;
-                }
-            }
-        }
+        }   }   }
        /* no dictMatchState lookup: dicts don't have a populated HC3 table */
    }

@@ -745,10 +771,13 @@ U32 ZSTD_insertBtAndGetAllMatches (


 FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
+                        ZSTD_match_t* matches,   /* store result (match found, increasing size) in this table */
                        ZSTD_matchState_t* ms,
+                        U32* nextToUpdate3,
                        const BYTE* ip, const BYTE* const iHighLimit, const ZSTD_dictMode_e dictMode,
-                        U32 rep[ZSTD_REP_NUM], U32 const ll0,
-                        ZSTD_match_t* matches, U32 const lengthToBeat)
+                        const U32 rep[ZSTD_REP_NUM],
+                        U32 const ll0,
+                        U32 const lengthToBeat)
 {
    const ZSTD_compressionParameters* const cParams = &ms->cParams;
    U32 const matchLengthSearch = cParams->minMatch;
@@ -757,12 +786,12 @@ FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
    ZSTD_updateTree_internal(ms, ip, iHighLimit, matchLengthSearch, dictMode);
    switch(matchLengthSearch)
    {
-    case 3 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 3);
+    case 3 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 3);
    default :
-    case 4 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 4);
-    case 5 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 5);
+    case 4 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 4);
+    case 5 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 5);
    case 7 :
-    case 6 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 6);
+    case 6 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 6);
    }
 }

@@ -838,6 +867,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,

    U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
    U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4;
+    U32 nextToUpdate3 = ms->nextToUpdate;

    ZSTD_optimal_t* const opt = optStatePtr->priceTable;
    ZSTD_match_t* const matches = optStatePtr->matchTable;
@@ -847,7 +877,6 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
    DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u",
                (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate);
    assert(optLevel <= 2);
-    ms->nextToUpdate3 = ms->nextToUpdate;
    ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel);
    ip += (ip==prefixStart);

@@ -858,7 +887,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
        /* find first match */
        {   U32 const litlen = (U32)(ip - anchor);
            U32 const ll0 = !litlen;
-            U32 const nbMatches = ZSTD_BtGetAllMatches(ms, ip, iend, dictMode, rep, ll0, matches, minMatch);
+            U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, ip, iend, dictMode, rep, ll0, minMatch);
            if (!nbMatches) { ip++; continue; }

            /* initialize opt[0] */
@@ -870,7 +899,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
            /* large match -> immediate encoding */
            {   U32 const maxML = matches[nbMatches-1].len;
                U32 const maxOffset = matches[nbMatches-1].off;
-                DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new serie",
+                DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series",
                            nbMatches, maxML, maxOffset, (U32)(ip-prefixStart));

                if (maxML > sufficient_len) {
@@ -955,7 +984,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
                U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0;
                U32 const previousPrice = opt[cur].price;
                U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel);
-                U32 const nbMatches = ZSTD_BtGetAllMatches(ms, inr, iend, dictMode, opt[cur].rep, ll0, matches, minMatch);
+                U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, inr, iend, dictMode, opt[cur].rep, ll0, minMatch);
                U32 matchNb;
                if (!nbMatches) {
                    DEBUGLOG(7, "rPos:%u : no match found", cur);
@@ -1079,7 +1108,7 @@ _shortestPath:   /* cur, last_pos, best_mlen, best_off have to be set */
    }   /* while (ip < ilimit) */

    /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }


@@ -1108,7 +1137,8 @@ static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus)
 /* used in 2-pass strategy */
 MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
 {
-    optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
    optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0);
    optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0);
    optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0);
@@ -1117,7 +1147,7 @@ MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
 /* ZSTD_initStats_ultra():
 * make a first compression pass, just to seed stats with more accurate starting values.
 * only works on first block, with no dictionary and no ldm.
- * this function cannot error, hence its constract must be respected.
+ * this function cannot error, hence its contract must be respected.
 */
 static void
 ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
@@ -1142,7 +1172,6 @@ ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
    ms->window.dictLimit += (U32)srcSize;
    ms->window.lowLimit = ms->window.dictLimit;
    ms->nextToUpdate = ms->window.dictLimit;
-    ms->nextToUpdate3 = ms->window.dictLimit;

    /* re-inforce weight of collected statistics */
    ZSTD_upscaleStats(&ms->opt);
@@ -22,6 +22,7 @@
 /* ======   Dependencies   ====== */
 #include <string.h>      /* memcpy, memset */
 #include <limits.h>      /* INT_MAX, UINT_MAX */
+#include "mem.h"         /* MEM_STATIC */
 #include "pool.h"        /* threadpool */
 #include "threading.h"   /* mutex */
 #include "zstd_compress_internal.h"  /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
@@ -456,7 +457,7 @@ typedef struct {
     * Must be acquired after the main mutex when acquiring both.
     */
    ZSTD_pthread_mutex_t ldmWindowMutex;
-    ZSTD_pthread_cond_t ldmWindowCond;  /* Signaled when ldmWindow is udpated */
+    ZSTD_pthread_cond_t ldmWindowCond;  /* Signaled when ldmWindow is updated */
    ZSTD_window_t ldmWindow;  /* A thread-safe copy of ldmState.window */
 } serialState_t;

@@ -647,7 +648,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
    buffer_t dstBuff = job->dstBuff;
    size_t lastCBlockSize = 0;

-    /* ressources */
+    /* resources */
    if (cctx==NULL) JOB_ERROR(ERROR(memory_allocation));
    if (dstBuff.start == NULL) {   /* streaming job : doesn't provide a dstBuffer */
        dstBuff = ZSTDMT_getBuffer(job->bufPool);
@@ -672,7 +673,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
        if (ZSTD_isError(initError)) JOB_ERROR(initError);
    } else {  /* srcStart points at reloaded section */
        U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size;
-        {   size_t const forceWindowError = ZSTD_CCtxParam_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
+        {   size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
            if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError);
        }
        {   size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
@@ -864,14 +865,10 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) {
 * Internal use only */
 size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
 {
-    if (nbWorkers > ZSTDMT_NBWORKERS_MAX) nbWorkers = ZSTDMT_NBWORKERS_MAX;
-    params->nbWorkers = nbWorkers;
-    params->overlapLog = ZSTDMT_OVERLAPLOG_DEFAULT;
-    params->jobSize = 0;
-    return nbWorkers;
+    return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers);
 }

-ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
+MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, ZSTD_customMem cMem)
 {
    ZSTDMT_CCtx* mtctx;
    U32 nbJobs = nbWorkers + 2;
@@ -906,6 +903,17 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
    return mtctx;
 }

+ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
+{
+#ifdef ZSTD_MULTITHREAD
+    return ZSTDMT_createCCtx_advanced_internal(nbWorkers, cMem);
+#else
+    (void)nbWorkers;
+    (void)cMem;
+    return NULL;
+#endif
+}
+
 ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers)
 {
    return ZSTDMT_createCCtx_advanced(nbWorkers, ZSTD_defaultCMem);
@@ -986,26 +994,13 @@ ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params,
    {
    case ZSTDMT_p_jobSize :
        DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter : set jobSize to %i", value);
-        if ( value != 0  /* default */
-          && value < ZSTDMT_JOBSIZE_MIN)
-            value = ZSTDMT_JOBSIZE_MIN;
-        assert(value >= 0);
-        if (value > ZSTDMT_JOBSIZE_MAX) value = ZSTDMT_JOBSIZE_MAX;
-        params->jobSize = value;
-        return value;
-
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, value);
    case ZSTDMT_p_overlapLog :
        DEBUGLOG(4, "ZSTDMT_p_overlapLog : %i", value);
-        if (value < ZSTD_OVERLAPLOG_MIN) value = ZSTD_OVERLAPLOG_MIN;
-        if (value > ZSTD_OVERLAPLOG_MAX) value = ZSTD_OVERLAPLOG_MAX;
-        params->overlapLog = value;
-        return value;
-
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, value);
    case ZSTDMT_p_rsyncable :
-        value = (value != 0);
-        params->rsyncable = value;
-        return value;
-
+        DEBUGLOG(4, "ZSTD_p_rsyncable : %i", value);
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_rsyncable, value);
    default :
        return ERROR(parameter_unsupported);
    }
@@ -1021,32 +1016,29 @@ size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter,
 {
    switch (parameter) {
    case ZSTDMT_p_jobSize:
-        assert(mtctx->params.jobSize <= INT_MAX);
-        *value = (int)(mtctx->params.jobSize);
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_jobSize, value);
    case ZSTDMT_p_overlapLog:
-        *value = mtctx->params.overlapLog;
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_overlapLog, value);
    case ZSTDMT_p_rsyncable:
-        *value = mtctx->params.rsyncable;
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_rsyncable, value);
    default:
        return ERROR(parameter_unsupported);
    }
-    return 0;
 }

 /* Sets parameters relevant to the compression job,
 * initializing others to default values. */
 static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
 {
-    ZSTD_CCtx_params jobParams;
-    memset(&jobParams, 0, sizeof(jobParams));
-
-    jobParams.cParams = params.cParams;
-    jobParams.fParams = params.fParams;
-    jobParams.compressionLevel = params.compressionLevel;
-
+    ZSTD_CCtx_params jobParams = params;
+    /* Clear parameters related to multithreading */
+    jobParams.forceWindow = 0;
+    jobParams.nbWorkers = 0;
+    jobParams.jobSize = 0;
+    jobParams.overlapLog = 0;
+    jobParams.rsyncable = 0;
+    memset(&jobParams.ldmParams, 0, sizeof(ldmParams_t));
+    memset(&jobParams.customMem, 0, sizeof(ZSTD_customMem));
    return jobParams;
 }

@@ -1056,7 +1048,7 @@ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
 static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers)
 {
    if (POOL_resize(mtctx->factory, nbWorkers)) return ERROR(memory_allocation);
-    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
+    FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
    mtctx->bufPool = ZSTDMT_expandBufferPool(mtctx->bufPool, nbWorkers);
    if (mtctx->bufPool == NULL) return ERROR(memory_allocation);
    mtctx->cctxPool = ZSTDMT_expandCCtxPool(mtctx->cctxPool, nbWorkers);
@@ -1137,9 +1129,14 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx)
            size_t const produced = ZSTD_isError(cResult) ? 0 : cResult;
            size_t const flushed = ZSTD_isError(cResult) ? 0 : jobPtr->dstFlushed;
            assert(flushed <= produced);
+            assert(jobPtr->consumed <= jobPtr->src.size);
            toFlush = produced - flushed;
-            if (toFlush==0 && (jobPtr->consumed >= jobPtr->src.size)) {
-                /* doneJobID is not-fully-flushed, but toFlush==0 : doneJobID should be compressing some more data */
+            /* if toFlush==0, nothing is available to flush.
+             * However, jobID is expected to still be active:
+             * if jobID was already completed and fully flushed,
+             * ZSTDMT_flushProduced() should have already moved onto next job.
+             * Therefore, some input has not yet been consumed. */
+            if (toFlush==0) {
                assert(jobPtr->consumed < jobPtr->src.size);
            }
        }
@@ -1156,12 +1153,16 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx)

 static unsigned ZSTDMT_computeTargetJobLog(ZSTD_CCtx_params const params)
 {
-    if (params.ldmParams.enableLdm)
+    unsigned jobLog;
+    if (params.ldmParams.enableLdm) {
        /* In Long Range Mode, the windowLog is typically oversized.
         * In which case, it's preferable to determine the jobSize
         * based on chainLog instead. */
-        return MAX(21, params.cParams.chainLog + 4);
-    return MAX(20, params.cParams.windowLog + 2);
+        jobLog = MAX(21, params.cParams.chainLog + 4);
+    } else {
+        jobLog = MAX(20, params.cParams.windowLog + 2);
+    }
+    return MIN(jobLog, (unsigned)ZSTDMT_JOBLOG_MAX);
 }

 static int ZSTDMT_overlapLog_default(ZSTD_strategy strat)
@@ -1205,7 +1206,7 @@ static size_t ZSTDMT_computeOverlapSize(ZSTD_CCtx_params const params)
        ovLog = MIN(params.cParams.windowLog, ZSTDMT_computeTargetJobLog(params) - 2)
                - overlapRLog;
    }
-    assert(0 <= ovLog && ovLog <= 30);
+    assert(0 <= ovLog && ovLog <= ZSTD_WINDOWLOG_MAX);
    DEBUGLOG(4, "overlapLog : %i", params.overlapLog);
    DEBUGLOG(4, "overlap size : %i", 1 << ovLog);
    return (ovLog==0) ? 0 : (size_t)1 << ovLog;
@@ -1263,7 +1264,7 @@ static size_t ZSTDMT_compress_advanced_internal(
    if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize))
        return ERROR(memory_allocation);

-    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbJobs) );  /* only expands if necessary */
+    FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) );  /* only expands if necessary */

    {   unsigned u;
        for (u=0; u<nbJobs; u++) {
@@ -1396,10 +1397,10 @@ size_t ZSTDMT_initCStream_internal(

    /* init */
    if (params.nbWorkers != mtctx->params.nbWorkers)
-        CHECK_F( ZSTDMT_resize(mtctx, params.nbWorkers) );
+        FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) );

    if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN;
-    if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX;
+    if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = (size_t)ZSTDMT_JOBSIZE_MAX;

    mtctx->singleBlockingThread = (pledgedSrcSize <= ZSTDMT_JOBSIZE_MIN);  /* do not trigger multi-threading when srcSize is too small */
    if (mtctx->singleBlockingThread) {
@@ -1440,6 +1441,8 @@ size_t ZSTDMT_initCStream_internal(
    if (mtctx->targetSectionSize == 0) {
        mtctx->targetSectionSize = 1ULL << ZSTDMT_computeTargetJobLog(params);
    }
+    assert(mtctx->targetSectionSize <= (size_t)ZSTDMT_JOBSIZE_MAX);
+
    if (params.rsyncable) {
        /* Aim for the targetsectionSize as the average job size. */
        U32 const jobSizeMB = (U32)(mtctx->targetSectionSize >> 20);
@@ -1547,7 +1550,7 @@ size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel) {
 /* ZSTDMT_writeLastEmptyBlock()
 * Write a single empty block with an end-of-frame to finish a frame.
 * Job must be created from streaming variant.
- * This function is always successfull if expected conditions are fulfilled.
+ * This function is always successful if expected conditions are fulfilled.
 */
 static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job)
 {
@@ -1987,7 +1990,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
    assert(input->pos  <= input->size);

    if (mtctx->singleBlockingThread) {  /* delegate to single-thread (synchronous) */
-        return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp);
+        return ZSTD_compressStream2(mtctx->cctxPool->cctx[0], output, input, endOp);
    }

    if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) {
@@ -2051,7 +2054,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
      || ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) {   /* must finish the frame with a zero-size block */
        size_t const jobSize = mtctx->inBuff.filled;
        assert(mtctx->inBuff.filled <= mtctx->targetSectionSize);
-        CHECK_F( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
+        FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
    }

    /* check for potential compressed data ready to be flushed */
@@ -2065,7 +2068,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,

 size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
 {
-    CHECK_F( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );
+    FORWARD_IF_ERROR( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );

    /* recommended next input size : fill current input buffer */
    return mtctx->targetSectionSize - mtctx->inBuff.filled;   /* note : could be zero when input buffer is fully filled and no more availability to create new job */
@@ -2082,7 +2085,7 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* ou
      || ((endFrame==ZSTD_e_end) && !mtctx->frameEnded)) {  /* need a last 0-size block to end frame */
           DEBUGLOG(5, "ZSTDMT_flushStream_internal : create a new job (%u bytes, end:%u)",
                        (U32)srcSize, (U32)endFrame);
-        CHECK_F( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
+        FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
    }

    /* check if there is any data available to flush */
@@ -17,10 +17,25 @@


 /* Note : This is an internal API.
- *        Some methods are still exposed (ZSTDLIB_API),
+ *        These APIs used to be exposed with ZSTDLIB_API,
 *        because it used to be the only way to invoke MT compression.
- *        Now, it's recommended to use ZSTD_compress_generic() instead.
- *        These methods will stop being exposed in a future version */
+ *        Now, it's recommended to use ZSTD_compress2 and ZSTD_compressStream2()
+ *        instead.
+ *
+ *        If you depend on these APIs and can't switch, then define
+ *        ZSTD_LEGACY_MULTITHREADED_API when making the dynamic library.
+ *        However, we may completely remove these functions in a future
+ *        release, so please switch soon.
+ *
+ *        This API requires ZSTD_MULTITHREAD to be defined during compilation,
+ *        otherwise ZSTDMT_createCCtx*() will fail.
+ */
+
+#ifdef ZSTD_LEGACY_MULTITHREADED_API
+#  define ZSTDMT_API ZSTDLIB_API
+#else
+#  define ZSTDMT_API
+#endif

 /* ===   Dependencies   === */
 #include <stddef.h>                /* size_t */
@@ -35,22 +50,25 @@
 #ifndef ZSTDMT_JOBSIZE_MIN
 #  define ZSTDMT_JOBSIZE_MIN (1 MB)
 #endif
+#define ZSTDMT_JOBLOG_MAX   (MEM_32bits() ? 29 : 30)
 #define ZSTDMT_JOBSIZE_MAX  (MEM_32bits() ? (512 MB) : (1024 MB))


 /* ===   Memory management   === */
 typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
-ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
-ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
                                                    ZSTD_customMem cMem);
-ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);

-ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);


 /* ===   Simple one-pass compression function   === */

-ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
                                       void* dst, size_t dstCapacity,
                                 const void* src, size_t srcSize,
                                       int compressionLevel);
@@ -59,31 +77,31 @@ ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,

 /* ===   Streaming functions   === */

-ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
-ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
+ZSTDMT_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
+ZSTDMT_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */

-ZSTDLIB_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
-ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+ZSTDMT_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);

-ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);     /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);     /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */


 /* ===   Advanced functions and parameters  === */

-ZSTDLIB_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
-                                           void* dst, size_t dstCapacity,
-                                     const void* src, size_t srcSize,
-                                     const ZSTD_CDict* cdict,
-                                           ZSTD_parameters params,
-                                           int overlapLog);
+ZSTDMT_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
+                                          void* dst, size_t dstCapacity,
+                                    const void* src, size_t srcSize,
+                                    const ZSTD_CDict* cdict,
+                                          ZSTD_parameters params,
+                                          int overlapLog);

-ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
                                        const void* dict, size_t dictSize,   /* dict can be released after init, a local copy is preserved within zcs */
                                        ZSTD_parameters params,
                                        unsigned long long pledgedSrcSize);  /* pledgedSrcSize is optional and can be zero == unknown */

-ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
                                        const ZSTD_CDict* cdict,
                                        ZSTD_frameParameters fparams,
                                        unsigned long long pledgedSrcSize);  /* note : zero means empty */
@@ -92,7 +110,7 @@ ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
 * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
 typedef enum {
    ZSTDMT_p_jobSize,     /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */
-    ZSTDMT_p_overlapLog,  /* Each job may reload a part of previous job to enhance compressionr ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
+    ZSTDMT_p_overlapLog,  /* Each job may reload a part of previous job to enhance compression ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
    ZSTDMT_p_rsyncable    /* Enables rsyncable mode. */
 } ZSTDMT_parameter;

@@ -101,12 +119,12 @@ typedef enum {
 * The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__
 * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions.
 * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
+ZSTDMT_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);

 /* ZSTDMT_getMTCtxParameter() :
 * Query the ZSTDMT_CCtx for a parameter value.
 * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
+ZSTDMT_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);


 /*! ZSTDMT_compressStream_generic() :
@@ -116,7 +134,7 @@ ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter
 *           0 if fully flushed
 *           or an error code
 *  note : needs to be init using any ZSTD_initCStream*() variant */
-ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
                                                ZSTD_outBuffer* output,
                                                ZSTD_inBuffer* input,
                                                ZSTD_EndDirective endOp);
@@ -105,9 +105,9 @@ ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
    ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);

    /* load entropy tables */
-    CHECK_E( ZSTD_loadDEntropy(&ddict->entropy,
-                                ddict->dictContent, ddict->dictSize),
-             dictionary_corrupted );
+    RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy(
+            &ddict->entropy, ddict->dictContent, ddict->dictSize)),
+        dictionary_corrupted);
    ddict->entropyPresent = 1;
    return 0;
 }
@@ -133,7 +133,7 @@ static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
    ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */

    /* parse dictionary content */
-    CHECK_F( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );
+    FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );

    return 0;
 }
@@ -106,6 +106,7 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
    dctx->ddictLocal  = NULL;
    dctx->dictEnd     = NULL;
    dctx->ddictIsCold = 0;
+    dctx->dictUses = ZSTD_dont_use;
    dctx->inBuff      = NULL;
    dctx->inBuffSize  = 0;
    dctx->outBuffSize = 0;
@@ -147,13 +148,20 @@ ZSTD_DCtx* ZSTD_createDCtx(void)
    return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
 }

+static void ZSTD_clearDict(ZSTD_DCtx* dctx)
+{
+    ZSTD_freeDDict(dctx->ddictLocal);
+    dctx->ddictLocal = NULL;
+    dctx->ddict = NULL;
+    dctx->dictUses = ZSTD_dont_use;
+}
+
 size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
 {
    if (dctx==NULL) return 0;   /* support free on NULL */
-    if (dctx->staticSize) return ERROR(memory_allocation);   /* not compatible with static DCtx */
+    RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx");
    {   ZSTD_customMem const cMem = dctx->customMem;
-        ZSTD_freeDDict(dctx->ddictLocal);
-        dctx->ddictLocal = NULL;
+        ZSTD_clearDict(dctx);
        ZSTD_free(dctx->inBuff, cMem);
        dctx->inBuff = NULL;
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
@@ -203,7 +211,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size)
 static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format)
 {
    size_t const minInputSize = ZSTD_startingInputLength(format);
-    if (srcSize < minInputSize) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong);

    {   BYTE const fhd = ((const BYTE*)src)[minInputSize-1];
        U32 const dictID= fhd & 3;
@@ -238,7 +246,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s

    memset(zfhPtr, 0, sizeof(*zfhPtr));   /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */
    if (srcSize < minInputSize) return minInputSize;
-    if (src==NULL) return ERROR(GENERIC);   /* invalid parameter */
+    RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter");

    if ( (format != ZSTD_f_zstd1_magicless)
      && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) {
@@ -251,7 +259,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
            zfhPtr->frameType = ZSTD_skippableFrame;
            return 0;
        }
-        return ERROR(prefix_unknown);
+        RETURN_ERROR(prefix_unknown);
    }

    /* ensure there is enough `srcSize` to fully read/decode frame header */
@@ -269,14 +277,13 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
        U64 windowSize = 0;
        U32 dictID = 0;
        U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN;
-        if ((fhdByte & 0x08) != 0)
-            return ERROR(frameParameter_unsupported); /* reserved bits, must be zero */
+        RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported,
+                        "reserved bits, must be zero");

        if (!singleSegment) {
            BYTE const wlByte = ip[pos++];
            U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
-            if (windowLog > ZSTD_WINDOWLOG_MAX)
-                return ERROR(frameParameter_windowTooLarge);
+            RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge);
            windowSize = (1ULL << windowLog);
            windowSize += (windowSize >> 3) * (wlByte&7);
        }
@@ -348,14 +355,16 @@ static size_t readSkippableFrameSize(void const* src, size_t srcSize)
    size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE;
    U32 sizeU32;

-    if (srcSize < ZSTD_SKIPPABLEHEADERSIZE)
-        return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong);

    sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE);
-    if ((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32)
-        return ERROR(frameParameter_unsupported);
-
-    return skippableHeaderSize + sizeU32;
+    RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32,
+                    frameParameter_unsupported);
+    {
+        size_t const skippableSize = skippableHeaderSize + sizeU32;
+        RETURN_ERROR_IF(skippableSize > srcSize, srcSize_wrong);
+        return skippableSize;
+    }
 }

 /** ZSTD_findDecompressedSize() :
@@ -372,11 +381,10 @@ unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)

        if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
            size_t const skippableSize = readSkippableFrameSize(src, srcSize);
-            if (ZSTD_isError(skippableSize))
-                return skippableSize;
-            if (srcSize < skippableSize) {
+            if (ZSTD_isError(skippableSize)) {
                return ZSTD_CONTENTSIZE_ERROR;
            }
+            assert(skippableSize <= srcSize);

            src = (const BYTE *)src + skippableSize;
            srcSize -= skippableSize;
@@ -428,13 +436,91 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he
 {
    size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format);
    if (ZSTD_isError(result)) return result;    /* invalid header */
-    if (result>0) return ERROR(srcSize_wrong);  /* headerSize too small */
-    if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID))
-        return ERROR(dictionary_wrong);
+    RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small");
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    /* Skip the dictID check in fuzzing mode, because it makes the search
+     * harder.
+     */
+    RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID),
+                    dictionary_wrong);
+#endif
    if (dctx->fParams.checksumFlag) XXH64_reset(&dctx->xxhState, 0);
    return 0;
 }

+static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret)
+{
+    ZSTD_frameSizeInfo frameSizeInfo;
+    frameSizeInfo.compressedSize = ret;
+    frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+    return frameSizeInfo;
+}
+
+static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo frameSizeInfo;
+    memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo));
+
+#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
+    if (ZSTD_isLegacy(src, srcSize))
+        return ZSTD_findFrameSizeInfoLegacy(src, srcSize);
+#endif
+
+    if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
+        && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+        frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize);
+        assert(ZSTD_isError(frameSizeInfo.compressedSize) ||
+               frameSizeInfo.compressedSize <= srcSize);
+        return frameSizeInfo;
+    } else {
+        const BYTE* ip = (const BYTE*)src;
+        const BYTE* const ipstart = ip;
+        size_t remainingSize = srcSize;
+        size_t nbBlocks = 0;
+        ZSTD_frameHeader zfh;
+
+        /* Extract Frame Header */
+        {   size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
+            if (ZSTD_isError(ret))
+                return ZSTD_errorFrameSizeInfo(ret);
+            if (ret > 0)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+        }
+
+        ip += zfh.headerSize;
+        remainingSize -= zfh.headerSize;
+
+        /* Iterate over each block */
+        while (1) {
+            blockProperties_t blockProperties;
+            size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
+            if (ZSTD_isError(cBlockSize))
+                return ZSTD_errorFrameSizeInfo(cBlockSize);
+
+            if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+
+            ip += ZSTD_blockHeaderSize + cBlockSize;
+            remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
+            nbBlocks++;
+
+            if (blockProperties.lastBlock) break;
+        }
+
+        /* Final frame content checksum */
+        if (zfh.checksumFlag) {
+            if (remainingSize < 4)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+            ip += 4;
+        }
+
+        frameSizeInfo.compressedSize = ip - ipstart;
+        frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN)
+                                        ? zfh.frameContentSize
+                                        : nbBlocks * zfh.blockSizeMax;
+        return frameSizeInfo;
+    }
+}

 /** ZSTD_findFrameCompressedSize() :
 *  compatible with legacy mode
@@ -443,52 +529,33 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he
 *  @return : the compressed size of the frame starting at `src` */
 size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
 {
-#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
-    if (ZSTD_isLegacy(src, srcSize))
-        return ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
-#endif
-    if ( (srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
-      && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START ) {
-        return readSkippableFrameSize(src, srcSize);
-    } else {
-        const BYTE* ip = (const BYTE*)src;
-        const BYTE* const ipstart = ip;
-        size_t remainingSize = srcSize;
-        ZSTD_frameHeader zfh;
-
-        /* Extract Frame Header */
-        {   size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
-            if (ZSTD_isError(ret)) return ret;
-            if (ret > 0) return ERROR(srcSize_wrong);
-        }
-
-        ip += zfh.headerSize;
-        remainingSize -= zfh.headerSize;
-
-        /* Loop on each block */
-        while (1) {
-            blockProperties_t blockProperties;
-            size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-            if (ZSTD_isError(cBlockSize)) return cBlockSize;
-
-            if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
-                return ERROR(srcSize_wrong);
-
-            ip += ZSTD_blockHeaderSize + cBlockSize;
-            remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
-
-            if (blockProperties.lastBlock) break;
-        }
-
-        if (zfh.checksumFlag) {   /* Final frame content checksum */
-            if (remainingSize < 4) return ERROR(srcSize_wrong);
-            ip += 4;
-        }
-
-        return ip - ipstart;
-    }
+    ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+    return frameSizeInfo.compressedSize;
 }

+/** ZSTD_decompressBound() :
+ *  compatible with legacy mode
+ *  `src` must point to the start of a ZSTD frame or a skippeable frame
+ *  `srcSize` must be at least as large as the frame contained
+ *  @return : the maximum decompressed size of the compressed source
+ */
+unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
+{
+    unsigned long long bound = 0;
+    /* Iterate over each frame */
+    while (srcSize > 0) {
+        ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+        size_t const compressedSize = frameSizeInfo.compressedSize;
+        unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
+        if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
+            return ZSTD_CONTENTSIZE_ERROR;
+        assert(srcSize >= compressedSize);
+        src = (const BYTE*)src + compressedSize;
+        srcSize -= compressedSize;
+        bound += decompressedBound;
+    }
+    return bound;
+}


 /*-*************************************************************
@@ -522,9 +589,9 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity,
    DEBUGLOG(5, "ZSTD_copyRawBlock");
    if (dst == NULL) {
        if (srcSize == 0) return 0;
-        return ERROR(dstBuffer_null);
+        RETURN_ERROR(dstBuffer_null);
    }
-    if (srcSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall);
    memcpy(dst, src, srcSize);
    return srcSize;
 }
@@ -535,9 +602,9 @@ static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity,
 {
    if (dst == NULL) {
        if (regenSize == 0) return 0;
-        return ERROR(dstBuffer_null);
+        RETURN_ERROR(dstBuffer_null);
    }
-    if (regenSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall);
    memset(dst, b, regenSize);
    return regenSize;
 }
@@ -560,15 +627,16 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
    DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr);

    /* check */
-    if (remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize)
-        return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(
+        remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize,
+        srcSize_wrong);

    /* Frame Header */
    {   size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_FRAMEHEADERSIZE_PREFIX);
        if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize;
-        if (remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize)
-            return ERROR(srcSize_wrong);
-        CHECK_F( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
+        RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize,
+                        srcSize_wrong);
+        FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
        ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize;
    }

@@ -581,7 +649,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,

        ip += ZSTD_blockHeaderSize;
        remainingSrcSize -= ZSTD_blockHeaderSize;
-        if (cBlockSize > remainingSrcSize) return ERROR(srcSize_wrong);
+        RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong);

        switch(blockProperties.blockType)
        {
@@ -596,7 +664,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
            break;
        case bt_reserved :
        default:
-            return ERROR(corruption_detected);
+            RETURN_ERROR(corruption_detected);
        }

        if (ZSTD_isError(decodedSize)) return decodedSize;
@@ -609,15 +677,15 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
    }

    if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
-        if ((U64)(op-ostart) != dctx->fParams.frameContentSize) {
-            return ERROR(corruption_detected);
-    }   }
+        RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize,
+                        corruption_detected);
+    }
    if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
        U32 const checkCalc = (U32)XXH64_digest(&dctx->xxhState);
        U32 checkRead;
-        if (remainingSrcSize<4) return ERROR(checksum_wrong);
+        RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong);
        checkRead = MEM_readLE32(ip);
-        if (checkRead != checkCalc) return ERROR(checksum_wrong);
+        RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong);
        ip += 4;
        remainingSrcSize -= 4;
    }
@@ -652,8 +720,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
            size_t decodedSize;
            size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
            if (ZSTD_isError(frameSize)) return frameSize;
-            /* legacy support is not compatible with static dctx */
-            if (dctx->staticSize) return ERROR(memory_allocation);
+            RETURN_ERROR_IF(dctx->staticSize, memory_allocation,
+                "legacy support is not compatible with static dctx");

            decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
            if (ZSTD_isError(decodedSize)) return decodedSize;
@@ -674,9 +742,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
                        (unsigned)magicNumber, ZSTD_MAGICNUMBER);
            if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
                size_t const skippableSize = readSkippableFrameSize(src, srcSize);
-                if (ZSTD_isError(skippableSize))
-                    return skippableSize;
-                if (srcSize < skippableSize) return ERROR(srcSize_wrong);
+                FORWARD_IF_ERROR(skippableSize);
+                assert(skippableSize <= srcSize);

                src = (const BYTE *)src + skippableSize;
                srcSize -= skippableSize;
@@ -685,29 +752,29 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,

        if (ddict) {
            /* we were called from ZSTD_decompress_usingDDict */
-            CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict));
        } else {
            /* this will initialize correctly with no dict if dict == NULL, so
             * use this in all cases but ddict */
-            CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
        }
        ZSTD_checkContinuity(dctx, dst);

        {   const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity,
                                                    &src, &srcSize);
-            if ( (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
-              && (moreThan1Frame==1) ) {
-                /* at least one frame successfully completed,
-                 * but following bytes are garbage :
-                 * it's more likely to be a srcSize error,
-                 * specifying more bytes than compressed size of frame(s).
-                 * This error message replaces ERROR(prefix_unknown),
-                 * which would be confusing, as the first header is actually correct.
-                 * Note that one could be unlucky, it might be a corruption error instead,
-                 * happening right at the place where we expect zstd magic bytes.
-                 * But this is _much_ less likely than a srcSize field error. */
-                return ERROR(srcSize_wrong);
-            }
+            RETURN_ERROR_IF(
+                (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
+             && (moreThan1Frame==1),
+                srcSize_wrong,
+                "at least one frame successfully completed, but following "
+                "bytes are garbage: it's more likely to be a srcSize error, "
+                "specifying more bytes than compressed size of frame(s). This "
+                "error message replaces ERROR(prefix_unknown), which would be "
+                "confusing, as the first header is actually correct. Note that "
+                "one could be unlucky, it might be a corruption error instead, "
+                "happening right at the place where we expect zstd magic "
+                "bytes. But this is _much_ less likely than a srcSize field "
+                "error.");
            if (ZSTD_isError(res)) return res;
            assert(res <= dstCapacity);
            dst = (BYTE*)dst + res;
@@ -716,7 +783,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
        moreThan1Frame = 1;
    }  /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */

-    if (srcSize) return ERROR(srcSize_wrong); /* input not entirely consumed */
+    RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed");

    return (BYTE*)dst - (BYTE*)dststart;
 }
@@ -730,9 +797,26 @@ size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
 }


+static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx)
+{
+    switch (dctx->dictUses) {
+    default:
+        assert(0 /* Impossible */);
+        /* fall-through */
+    case ZSTD_dont_use:
+        ZSTD_clearDict(dctx);
+        return NULL;
+    case ZSTD_use_indefinitely:
+        return dctx->ddict;
+    case ZSTD_use_once:
+        dctx->dictUses = ZSTD_dont_use;
+        return dctx->ddict;
+    }
+}
+
 size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-    return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0);
+    return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, ZSTD_getDDict(dctx));
 }


@@ -741,7 +825,7 @@ size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t sr
 #if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
    size_t regenSize;
    ZSTD_DCtx* const dctx = ZSTD_createDCtx();
-    if (dctx==NULL) return ERROR(memory_allocation);
+    RETURN_ERROR_IF(dctx==NULL, memory_allocation);
    regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize);
    ZSTD_freeDCtx(dctx);
    return regenSize;
@@ -791,8 +875,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
 {
    DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize);
    /* Sanity check */
-    if (srcSize != dctx->expected)
-        return ERROR(srcSize_wrong);  /* not allowed */
+    RETURN_ERROR_IF(srcSize != dctx->expected, srcSize_wrong, "not allowed");
    if (dstCapacity) ZSTD_checkContinuity(dctx, dst);

    switch (dctx->stage)
@@ -817,7 +900,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
    case ZSTDds_decodeFrameHeader:
        assert(src != NULL);
        memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize);
-        CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
+        FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
        dctx->expected = ZSTD_blockHeaderSize;
        dctx->stage = ZSTDds_decodeBlockHeader;
        return 0;
@@ -826,6 +909,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
        {   blockProperties_t bp;
            size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
            if (ZSTD_isError(cBlockSize)) return cBlockSize;
+            RETURN_ERROR_IF(cBlockSize > dctx->fParams.blockSizeMax, corruption_detected, "Block Size Exceeds Maximum");
            dctx->expected = cBlockSize;
            dctx->bType = bp.blockType;
            dctx->rleSize = bp.origSize;
@@ -867,19 +951,20 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
                break;
            case bt_reserved :   /* should never happen */
            default:
-                return ERROR(corruption_detected);
+                RETURN_ERROR(corruption_detected);
            }
            if (ZSTD_isError(rSize)) return rSize;
+            RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum");
            DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
            dctx->decodedSize += rSize;
            if (dctx->fParams.checksumFlag) XXH64_update(&dctx->xxhState, dst, rSize);

            if (dctx->stage == ZSTDds_decompressLastBlock) {   /* end of frame */
                DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize);
-                if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
-                    if (dctx->decodedSize != dctx->fParams.frameContentSize) {
-                        return ERROR(corruption_detected);
-                }   }
+                RETURN_ERROR_IF(
+                    dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
+                 && dctx->decodedSize != dctx->fParams.frameContentSize,
+                    corruption_detected);
                if (dctx->fParams.checksumFlag) {  /* another round for frame checksum */
                    dctx->expected = 4;
                    dctx->stage = ZSTDds_checkChecksum;
@@ -900,7 +985,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
        {   U32 const h32 = (U32)XXH64_digest(&dctx->xxhState);
            U32 const check32 = MEM_readLE32(src);
            DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32);
-            if (check32 != h32) return ERROR(checksum_wrong);
+            RETURN_ERROR_IF(check32 != h32, checksum_wrong);
            dctx->expected = 0;
            dctx->stage = ZSTDds_getFrameHeaderSize;
            return 0;
@@ -921,7 +1006,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c

    default:
        assert(0);   /* impossible */
-        return ERROR(GENERIC);   /* some compiler require default to do something */
+        RETURN_ERROR(GENERIC);   /* some compiler require default to do something */
    }
 }

@@ -945,7 +1030,7 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
    const BYTE* dictPtr = (const BYTE*)dict;
    const BYTE* const dictEnd = dictPtr + dictSize;

-    if (dictSize <= 8) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted);
    assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY);   /* dict must be valid */
    dictPtr += 8;   /* skip header = magic + dictID */

@@ -964,16 +1049,16 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
                                                dictPtr, dictEnd - dictPtr,
                                                workspace, workspaceSize);
 #endif
-        if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted);
        dictPtr += hSize;
    }

    {   short offcodeNCount[MaxOff+1];
        unsigned offcodeMaxValue = MaxOff, offcodeLog;
        size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted);
-        if (offcodeMaxValue > MaxOff) return ERROR(dictionary_corrupted);
-        if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted);
        ZSTD_buildFSETable( entropy->OFTable,
                            offcodeNCount, offcodeMaxValue,
                            OF_base, OF_bits,
@@ -984,9 +1069,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
    {   short matchlengthNCount[MaxML+1];
        unsigned matchlengthMaxValue = MaxML, matchlengthLog;
        size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (matchlengthMaxValue > MaxML) return ERROR(dictionary_corrupted);
-        if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted);
        ZSTD_buildFSETable( entropy->MLTable,
                            matchlengthNCount, matchlengthMaxValue,
                            ML_base, ML_bits,
@@ -997,9 +1082,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
    {   short litlengthNCount[MaxLL+1];
        unsigned litlengthMaxValue = MaxLL, litlengthLog;
        size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (litlengthMaxValue > MaxLL) return ERROR(dictionary_corrupted);
-        if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted);
        ZSTD_buildFSETable( entropy->LLTable,
                            litlengthNCount, litlengthMaxValue,
                            LL_base, LL_bits,
@@ -1007,12 +1092,13 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
        dictPtr += litlengthHeaderSize;
    }

-    if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted);
    {   int i;
        size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12));
        for (i=0; i<3; i++) {
            U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4;
-            if (rep==0 || rep >= dictContentSize) return ERROR(dictionary_corrupted);
+            RETURN_ERROR_IF(rep==0 || rep >= dictContentSize,
+                            dictionary_corrupted);
            entropy->rep[i] = rep;
    }   }

@@ -1030,7 +1116,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict

    /* load entropy tables */
    {   size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize);
-        if (ZSTD_isError(eSize)) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted);
        dict = (const char*)dict + eSize;
        dictSize -= eSize;
    }
@@ -1064,9 +1150,11 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)

 size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
 {
-    CHECK_F( ZSTD_decompressBegin(dctx) );
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
    if (dict && dictSize)
-        CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted);
+        RETURN_ERROR_IF(
+            ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)),
+            dictionary_corrupted);
    return 0;
 }

@@ -1085,7 +1173,7 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
        DEBUGLOG(4, "DDict is %s",
                    dctx->ddictIsCold ? "~cold~" : "hot!");
    }
-    CHECK_F( ZSTD_decompressBegin(dctx) );
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
    if (ddict) {   /* NULL ddict is equivalent to no dictionary */
        ZSTD_copyDDictParameters(dctx, ddict);
    }
@@ -1104,7 +1192,7 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
 }

 /*! ZSTD_getDictID_fromFrame() :
- *  Provides the dictID required to decompresse frame stored within `src`.
+ *  Provides the dictID required to decompress frame stored within `src`.
 *  If @return == 0, the dictID could not be decoded.
 *  This could for one of the following reasons :
 *  - The frame does not require a dictionary (most common case).
@@ -1176,15 +1264,14 @@ size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx,
                                         ZSTD_dictLoadMethod_e dictLoadMethod,
                                         ZSTD_dictContentType_e dictContentType)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    ZSTD_freeDDict(dctx->ddictLocal);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    ZSTD_clearDict(dctx);
    if (dict && dictSize >= 8) {
        dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem);
-        if (dctx->ddictLocal == NULL) return ERROR(memory_allocation);
-    } else {
-        dctx->ddictLocal = NULL;
+        RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation);
+        dctx->ddict = dctx->ddictLocal;
+        dctx->dictUses = ZSTD_use_indefinitely;
    }
-    dctx->ddict = dctx->ddictLocal;
    return 0;
 }

@@ -1200,7 +1287,9 @@ size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSi

 size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
 {
-    return ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType);
+    FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType));
+    dctx->dictUses = ZSTD_use_once;
+    return 0;
 }

 size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize)
@@ -1215,9 +1304,8 @@ size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSiz
 size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
 {
    DEBUGLOG(4, "ZSTD_initDStream_usingDict");
-    zds->streamStage = zdss_init;
-    zds->noForwardProgress = 0;
-    CHECK_F( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
    return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }

@@ -1225,7 +1313,7 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di
 size_t ZSTD_initDStream(ZSTD_DStream* zds)
 {
    DEBUGLOG(4, "ZSTD_initDStream");
-    return ZSTD_initDStream_usingDict(zds, NULL, 0);
+    return ZSTD_initDStream_usingDDict(zds, NULL);
 }

 /* ZSTD_initDStream_usingDDict() :
@@ -1233,9 +1321,9 @@ size_t ZSTD_initDStream(ZSTD_DStream* zds)
 * this function cannot fail */
 size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
 {
-    size_t const initResult = ZSTD_initDStream(dctx);
-    dctx->ddict = ddict;
-    return initResult;
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) );
+    return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }

 /* ZSTD_resetDStream() :
@@ -1243,19 +1331,19 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
 * this function cannot fail */
 size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
 {
-    DEBUGLOG(4, "ZSTD_resetDStream");
-    dctx->streamStage = zdss_loadHeader;
-    dctx->lhSize = dctx->inPos = dctx->outStart = dctx->outEnd = 0;
-    dctx->legacyVersion = 0;
-    dctx->hostageByte = 0;
+    FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only));
    return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }


 size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    dctx->ddict = ddict;
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    ZSTD_clearDict(dctx);
+    if (ddict) {
+        dctx->ddict = ddict;
+        dctx->dictUses = ZSTD_use_indefinitely;
+    }
    return 0;
 }

@@ -1267,9 +1355,9 @@ size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize)
    ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax);
    size_t const min = (size_t)1 << bounds.lowerBound;
    size_t const max = (size_t)1 << bounds.upperBound;
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    if (maxWindowSize < min) return ERROR(parameter_outOfBound);
-    if (maxWindowSize > max) return ERROR(parameter_outOfBound);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound);
+    RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound);
    dctx->maxWindowSize = maxWindowSize;
    return 0;
 }
@@ -1311,15 +1399,15 @@ static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value)
 }

 #define CHECK_DBOUNDS(p,v) {                \
-    if (!ZSTD_dParam_withinBounds(p, v))    \
-        return ERROR(parameter_outOfBound); \
+    RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound); \
 }

 size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
    switch(dParam) {
        case ZSTD_d_windowLogMax:
+            if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT;
            CHECK_DBOUNDS(ZSTD_d_windowLogMax, value);
            dctx->maxWindowSize = ((size_t)1) << value;
            return 0;
@@ -1329,19 +1417,20 @@ size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value
            return 0;
        default:;
    }
-    return ERROR(parameter_unsupported);
+    RETURN_ERROR(parameter_unsupported);
 }

 size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset)
 {
    if ( (reset == ZSTD_reset_session_only)
      || (reset == ZSTD_reset_session_and_parameters) ) {
-        (void)ZSTD_initDStream(dctx);
+        dctx->streamStage = zdss_init;
+        dctx->noForwardProgress = 0;
    }
    if ( (reset == ZSTD_reset_parameters)
      || (reset == ZSTD_reset_session_and_parameters) ) {
-        if (dctx->streamStage != zdss_init)
-            return ERROR(stage_wrong);
+        RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+        ZSTD_clearDict(dctx);
        dctx->format = ZSTD_f_zstd1;
        dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
    }
@@ -1360,7 +1449,8 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long
    unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
    unsigned long long const neededSize = MIN(frameContentSize, neededRBSize);
    size_t const minRBSize = (size_t) neededSize;
-    if ((unsigned long long)minRBSize != neededSize) return ERROR(frameParameter_windowTooLarge);
+    RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize,
+                    frameParameter_windowTooLarge);
    return minRBSize;
 }

@@ -1378,9 +1468,9 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
    ZSTD_frameHeader zfh;
    size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize);
    if (ZSTD_isError(err)) return err;
-    if (err>0) return ERROR(srcSize_wrong);
-    if (zfh.windowSize > windowSizeMax)
-        return ERROR(frameParameter_windowTooLarge);
+    RETURN_ERROR_IF(err>0, srcSize_wrong);
+    RETURN_ERROR_IF(zfh.windowSize > windowSizeMax,
+                    frameParameter_windowTooLarge);
    return ZSTD_estimateDStreamSize((size_t)zfh.windowSize);
 }

@@ -1406,16 +1496,16 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
    U32 someMoreWork = 1;

    DEBUGLOG(5, "ZSTD_decompressStream");
-    if (input->pos > input->size) {  /* forbidden */
-        DEBUGLOG(5, "in: pos: %u   vs size: %u",
-                    (U32)input->pos, (U32)input->size);
-        return ERROR(srcSize_wrong);
-    }
-    if (output->pos > output->size) {  /* forbidden */
-        DEBUGLOG(5, "out: pos: %u   vs size: %u",
-                    (U32)output->pos, (U32)output->size);
-        return ERROR(dstSize_tooSmall);
-    }
+    RETURN_ERROR_IF(
+        input->pos > input->size,
+        srcSize_wrong,
+        "forbidden. in: pos: %u   vs size: %u",
+        (U32)input->pos, (U32)input->size);
+    RETURN_ERROR_IF(
+        output->pos > output->size,
+        dstSize_tooSmall,
+        "forbidden. out: pos: %u   vs size: %u",
+        (U32)output->pos, (U32)output->size);
    DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));

    while (someMoreWork) {
@@ -1423,15 +1513,18 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
        {
        case zdss_init :
            DEBUGLOG(5, "stage zdss_init => transparent reset ");
-            ZSTD_resetDStream(zds);   /* transparent reset on starting decoding a new frame */
+            zds->streamStage = zdss_loadHeader;
+            zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
+            zds->legacyVersion = 0;
+            zds->hostageByte = 0;
            /* fall-through */

        case zdss_loadHeader :
            DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip));
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
            if (zds->legacyVersion) {
-                /* legacy support is incompatible with static dctx */
-                if (zds->staticSize) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(zds->staticSize, memory_allocation,
+                    "legacy support is incompatible with static dctx");
                {   size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
                    if (hint==0) zds->streamStage = zdss_init;
                    return hint;
@@ -1443,12 +1536,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
                    U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
                    if (legacyVersion) {
-                        const void* const dict = zds->ddict ? ZSTD_DDict_dictContent(zds->ddict) : NULL;
-                        size_t const dictSize = zds->ddict ? ZSTD_DDict_dictSize(zds->ddict) : 0;
+                        ZSTD_DDict const* const ddict = ZSTD_getDDict(zds);
+                        const void* const dict = ddict ? ZSTD_DDict_dictContent(ddict) : NULL;
+                        size_t const dictSize = ddict ? ZSTD_DDict_dictSize(ddict) : 0;
                        DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion);
-                        /* legacy support is incompatible with static dctx */
-                        if (zds->staticSize) return ERROR(memory_allocation);
-                        CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext,
+                        RETURN_ERROR_IF(zds->staticSize, memory_allocation,
+                            "legacy support is incompatible with static dctx");
+                        FORWARD_IF_ERROR(ZSTD_initLegacyStream(&zds->legacyContext,
                                    zds->previousLegacyVersion, legacyVersion,
                                    dict, dictSize));
                        zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
@@ -1482,7 +1576,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
                if (cSize <= (size_t)(iend-istart)) {
                    /* shortcut : using single-pass mode */
-                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
+                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, ZSTD_getDDict(zds));
                    if (ZSTD_isError(decompressedSize)) return decompressedSize;
                    DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()")
                    ip = istart + cSize;
@@ -1495,13 +1589,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB

            /* Consume header (see ZSTDds_decodeFrameHeader) */
            DEBUGLOG(4, "Consume header");
-            CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds)));

            if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {  /* skippable frame */
                zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE);
                zds->stage = ZSTDds_skipFrame;
            } else {
-                CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
+                FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
                zds->expected = ZSTD_blockHeaderSize;
                zds->stage = ZSTDds_decodeBlockHeader;
            }
@@ -1511,7 +1605,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                        (U32)(zds->fParams.windowSize >>10),
                        (U32)(zds->maxWindowSize >> 10) );
            zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
-            if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
+            RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize,
+                            frameParameter_windowTooLarge);

            /* Adapt buffer sizes to frame header instructions */
            {   size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */);
@@ -1525,14 +1620,15 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                    if (zds->staticSize) {  /* static DCtx */
                        DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize);
                        assert(zds->staticSize >= sizeof(ZSTD_DCtx));  /* controlled at init */
-                        if (bufferSize > zds->staticSize - sizeof(ZSTD_DCtx))
-                            return ERROR(memory_allocation);
+                        RETURN_ERROR_IF(
+                            bufferSize > zds->staticSize - sizeof(ZSTD_DCtx),
+                            memory_allocation);
                    } else {
                        ZSTD_free(zds->inBuff, zds->customMem);
                        zds->inBuffSize = 0;
                        zds->outBuffSize = 0;
                        zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem);
-                        if (zds->inBuff == NULL) return ERROR(memory_allocation);
+                        RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation);
                    }
                    zds->inBuffSize = neededInBuffSize;
                    zds->outBuff = zds->inBuff + zds->inBuffSize;
@@ -1574,7 +1670,9 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                if (isSkipFrame) {
                    loadedSize = MIN(toLoad, (size_t)(iend-ip));
                } else {
-                    if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected);   /* should never happen */
+                    RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos,
+                                    corruption_detected,
+                                    "should never happen");
                    loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend-ip);
                }
                ip += loadedSize;
@@ -1615,7 +1713,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB

        default:
            assert(0);    /* impossible */
-            return ERROR(GENERIC);   /* some compiler require default to do something */
+            RETURN_ERROR(GENERIC);   /* some compiler require default to do something */
    }   }

    /* result */
@@ -1624,8 +1722,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
    if ((ip==istart) && (op==ostart)) {  /* no forward progress */
        zds->noForwardProgress ++;
        if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) {
-            if (op==oend) return ERROR(dstSize_tooSmall);
-            if (ip==iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(op==oend, dstSize_tooSmall);
+            RETURN_ERROR_IF(ip==iend, srcSize_wrong);
            assert(0);
        }
    } else {
@@ -56,14 +56,15 @@ static void ZSTD_copy4(void* dst, const void* src) { memcpy(dst, src, 4); }
 size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
                          blockProperties_t* bpPtr)
 {
-    if (srcSize < ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong);
+
    {   U32 const cBlockHeader = MEM_readLE24(src);
        U32 const cSize = cBlockHeader >> 3;
        bpPtr->lastBlock = cBlockHeader & 1;
        bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
        bpPtr->origSize = cSize;   /* only useful for RLE */
        if (bpPtr->blockType == bt_rle) return 1;
-        if (bpPtr->blockType == bt_reserved) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected);
        return cSize;
    }
 }
@@ -78,7 +79,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
 size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                          const void* src, size_t srcSize)   /* note : srcSize < BLOCKSIZE */
 {
-    if (srcSize < MIN_CBLOCK_SIZE) return ERROR(corruption_detected);
+    RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected);

    {   const BYTE* const istart = (const BYTE*) src;
        symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
@@ -86,11 +87,11 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
        switch(litEncType)
        {
        case set_repeat:
-            if (dctx->litEntropy==0) return ERROR(dictionary_corrupted);
+            RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted);
            /* fall-through */

        case set_compressed:
-            if (srcSize < 5) return ERROR(corruption_detected);   /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
+            RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3");
            {   size_t lhSize, litSize, litCSize;
                U32 singleStream=0;
                U32 const lhlCode = (istart[0] >> 2) & 3;
@@ -118,8 +119,8 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                    litCSize = (lhc >> 22) + (istart[4] << 10);
                    break;
                }
-                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
-                if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
+                RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected);

                /* prefetch huffman table if cold */
                if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) {
@@ -157,7 +158,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                    }
                }

-                if (HUF_isError(hufSuccess)) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected);

                dctx->litPtr = dctx->litBuffer;
                dctx->litSize = litSize;
@@ -187,7 +188,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                }

                if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) {  /* risk reading beyond src buffer with wildcopy */
-                    if (litSize+lhSize > srcSize) return ERROR(corruption_detected);
+                    RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected);
                    memcpy(dctx->litBuffer, istart+lhSize, litSize);
                    dctx->litPtr = dctx->litBuffer;
                    dctx->litSize = litSize;
@@ -216,17 +217,17 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                case 3:
                    lhSize = 3;
                    litSize = MEM_readLE24(istart) >> 4;
-                    if (srcSize<4) return ERROR(corruption_detected);   /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
+                    RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4");
                    break;
                }
-                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
                memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
                dctx->litPtr = dctx->litBuffer;
                dctx->litSize = litSize;
                return lhSize+1;
            }
        default:
-            return ERROR(corruption_detected);   /* impossible */
+            RETURN_ERROR(corruption_detected, "impossible");
        }
    }
 }
@@ -436,8 +437,8 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
    switch(type)
    {
    case set_rle :
-        if (!srcSize) return ERROR(srcSize_wrong);
-        if ( (*(const BYTE*)src) > max) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(!srcSize, srcSize_wrong);
+        RETURN_ERROR_IF((*(const BYTE*)src) > max, corruption_detected);
        {   U32 const symbol = *(const BYTE*)src;
            U32 const baseline = baseValue[symbol];
            U32 const nbBits = nbAdditionalBits[symbol];
@@ -449,7 +450,7 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
        *DTablePtr = defaultTable;
        return 0;
    case set_repeat:
-        if (!flagRepeatTable) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(!flagRepeatTable, corruption_detected);
        /* prefetch FSE table if used */
        if (ddictIsCold && (nbSeq > 24 /* heuristic */)) {
            const void* const pStart = *DTablePtr;
@@ -461,15 +462,15 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
        {   unsigned tableLog;
            S16 norm[MaxSeq+1];
            size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
-            if (FSE_isError(headerSize)) return ERROR(corruption_detected);
-            if (tableLog > maxLog) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected);
+            RETURN_ERROR_IF(tableLog > maxLog, corruption_detected);
            ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog);
            *DTablePtr = DTableSpace;
            return headerSize;
        }
-    default :   /* impossible */
+    default :
        assert(0);
-        return ERROR(GENERIC);
+        RETURN_ERROR(GENERIC, "impossible");
    }
 }

@@ -483,28 +484,28 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
    DEBUGLOG(5, "ZSTD_decodeSeqHeaders");

    /* check */
-    if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong);

    /* SeqHead */
    nbSeq = *ip++;
    if (!nbSeq) {
        *nbSeqPtr=0;
-        if (srcSize != 1) return ERROR(srcSize_wrong);
+        RETURN_ERROR_IF(srcSize != 1, srcSize_wrong);
        return 1;
    }
    if (nbSeq > 0x7F) {
        if (nbSeq == 0xFF) {
-            if (ip+2 > iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong);
            nbSeq = MEM_readLE16(ip) + LONGNBSEQ, ip+=2;
        } else {
-            if (ip >= iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(ip >= iend, srcSize_wrong);
            nbSeq = ((nbSeq-0x80)<<8) + *ip++;
        }
    }
    *nbSeqPtr = nbSeq;

    /* FSE table descriptors */
-    if (ip+4 > iend) return ERROR(srcSize_wrong); /* minimum possible size */
+    RETURN_ERROR_IF(ip+1 > iend, srcSize_wrong); /* minimum possible size: 1 byte for symbol encoding types */
    {   symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
        symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
        symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
@@ -517,7 +518,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                      LL_base, LL_bits,
                                                      LL_defaultDTable, dctx->fseEntropy,
                                                      dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(llhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected);
            ip += llhSize;
        }

@@ -527,7 +528,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                      OF_base, OF_bits,
                                                      OF_defaultDTable, dctx->fseEntropy,
                                                      dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(ofhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected);
            ip += ofhSize;
        }

@@ -537,7 +538,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                      ML_base, ML_bits,
                                                      ML_defaultDTable, dctx->fseEntropy,
                                                      dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(mlhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected);
            ip += mlhSize;
        }
    }
@@ -590,8 +591,8 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
    const BYTE* match = oLitEnd - sequence.offset;

    /* check */
-    if (oMatchEnd>oend) return ERROR(dstSize_tooSmall);   /* last match must fit within dstBuffer */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* try to read beyond literal buffer */
+    RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must fit within dstBuffer");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "try to read beyond literal buffer");

    /* copy literals */
    while (op < oLitEnd) *op++ = *(*litPtr)++;
@@ -599,7 +600,7 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
    /* copy Match */
    if (sequence.offset > (size_t)(oLitEnd - base)) {
        /* offset beyond prefix */
-        if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - vBase),corruption_detected);
        match = dictEnd - (base-match);
        if (match + sequence.matchLength <= dictEnd) {
            memmove(oLitEnd, match, sequence.matchLength);
@@ -631,22 +632,22 @@ size_t ZSTD_execSequence(BYTE* op,
    const BYTE* match = oLitEnd - sequence.offset;

    /* check */
-    if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* over-read beyond lit buffer */
+    RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
    if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);

    /* copy Literals */
-    ZSTD_copy8(op, *litPtr);
    if (sequence.litLength > 8)
-        ZSTD_wildcopy(op+8, (*litPtr)+8, sequence.litLength - 8);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+        ZSTD_wildcopy_16min(op, (*litPtr), sequence.litLength, ZSTD_no_overlap);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+    else
+        ZSTD_copy8(op, *litPtr);
    op = oLitEnd;
    *litPtr = iLitEnd;   /* update for next sequence */

    /* copy Match */
    if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
        /* offset beyond prefix -> go into extDict */
-        if (sequence.offset > (size_t)(oLitEnd - virtualStart))
-            return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected);
        match = dictEnd + (match - prefixStart);
        if (match + sequence.matchLength <= dictEnd) {
            memmove(oLitEnd, match, sequence.matchLength);
@@ -686,13 +687,13 @@ size_t ZSTD_execSequence(BYTE* op,

    if (oMatchEnd > oend-(16-MINMATCH)) {
        if (op < oend_w) {
-            ZSTD_wildcopy(op, match, oend_w - op);
+            ZSTD_wildcopy(op, match, oend_w - op, ZSTD_overlap_src_before_dst);
            match += oend_w - op;
            op = oend_w;
        }
        while (op < oMatchEnd) *op++ = *match++;
    } else {
-        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8);   /* works even if matchLength < 8 */
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst);   /* works even if matchLength < 8 */
    }
    return sequenceLength;
 }
@@ -712,21 +713,23 @@ size_t ZSTD_execSequenceLong(BYTE* op,
    const BYTE* match = sequence.match;

    /* check */
-    if (oMatchEnd > oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* over-read beyond lit buffer */
+    RETURN_ERROR_IF(oMatchEnd > oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
    if (oLitEnd > oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, dictStart, dictEnd);

    /* copy Literals */
-    ZSTD_copy8(op, *litPtr);  /* note : op <= oLitEnd <= oend_w == oend - 8 */
    if (sequence.litLength > 8)
-        ZSTD_wildcopy(op+8, (*litPtr)+8, sequence.litLength - 8);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+        ZSTD_wildcopy_16min(op, *litPtr, sequence.litLength, ZSTD_no_overlap);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+    else
+        ZSTD_copy8(op, *litPtr);  /* note : op <= oLitEnd <= oend_w == oend - 8 */
+
    op = oLitEnd;
    *litPtr = iLitEnd;   /* update for next sequence */

    /* copy Match */
    if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
        /* offset beyond prefix */
-        if (sequence.offset > (size_t)(oLitEnd - dictStart)) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - dictStart), corruption_detected);
        if (match + sequence.matchLength <= dictEnd) {
            memmove(oLitEnd, match, sequence.matchLength);
            return sequenceLength;
@@ -766,13 +769,13 @@ size_t ZSTD_execSequenceLong(BYTE* op,

    if (oMatchEnd > oend-(16-MINMATCH)) {
        if (op < oend_w) {
-            ZSTD_wildcopy(op, match, oend_w - op);
+            ZSTD_wildcopy(op, match, oend_w - op, ZSTD_overlap_src_before_dst);
            match += oend_w - op;
            op = oend_w;
        }
        while (op < oMatchEnd) *op++ = *match++;
    } else {
-        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8);   /* works even if matchLength < 8 */
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst);   /* works even if matchLength < 8 */
    }
    return sequenceLength;
 }
@@ -801,7 +804,7 @@ ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD)
 /* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum
 * offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1)
 * bits before reloading. This value is the maximum number of bytes we read
- * after reloading when we are decoding long offets.
+ * after reloading when we are decoding long offsets.
 */
 #define LONG_OFFSETS_MAX_EXTRA_BITS_32                       \
    (ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32       \
@@ -889,6 +892,7 @@ ZSTD_decodeSequence(seqState_t* seqState, const ZSTD_longOffset_e longOffsets)
 }

 FORCE_INLINE_TEMPLATE size_t
+DONT_VECTORIZE
 ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
                               void* dst, size_t maxDstSize,
                         const void* seqStart, size_t seqSize, int nbSeq,
@@ -911,11 +915,18 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
        seqState_t seqState;
        dctx->fseEntropy = 1;
        { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
-        CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected);
        ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
        ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
        ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);

+        ZSTD_STATIC_ASSERT(
+                BIT_DStream_unfinished < BIT_DStream_completed &&
+                BIT_DStream_endOfBuffer < BIT_DStream_completed &&
+                BIT_DStream_completed < BIT_DStream_overflow);
+
        for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq ; ) {
            nbSeq--;
            {   seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset);
@@ -927,14 +938,15 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,

        /* check if reached exact end */
        DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
-        if (nbSeq) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(nbSeq, corruption_detected);
+        RETURN_ERROR_IF(BIT_reloadDStream(&seqState.DStream) < BIT_DStream_completed, corruption_detected);
        /* save reps for next block */
        { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
    }

    /* last literal segment */
    {   size_t const lastLLSize = litEnd - litPtr;
-        if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
        memcpy(op, litPtr, lastLLSize);
        op += lastLLSize;
    }
@@ -1066,7 +1078,9 @@ ZSTD_decompressSequencesLong_body(
        seqState.pos = (size_t)(op-prefixStart);
        seqState.dictEnd = dictEnd;
        assert(iend >= ip);
-        CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected);
        ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
        ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
        ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
@@ -1076,7 +1090,7 @@ ZSTD_decompressSequencesLong_body(
            sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, isLongOffset);
            PREFETCH_L1(sequences[seqNb].match); PREFETCH_L1(sequences[seqNb].match + sequences[seqNb].matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */
        }
-        if (seqNb<seqAdvance) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(seqNb<seqAdvance, corruption_detected);

        /* decode and decompress */
        for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && (seqNb<nbSeq) ; seqNb++) {
@@ -1087,7 +1101,7 @@ ZSTD_decompressSequencesLong_body(
            sequences[seqNb & STORED_SEQS_MASK] = sequence;
            op += oneSeqSize;
        }
-        if (seqNb<nbSeq) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(seqNb<nbSeq, corruption_detected);

        /* finish queue */
        seqNb -= seqAdvance;
@@ -1103,7 +1117,7 @@ ZSTD_decompressSequencesLong_body(

    /* last literal segment */
    {   size_t const lastLLSize = litEnd - litPtr;
-        if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
        memcpy(op, litPtr, lastLLSize);
        op += lastLLSize;
    }
@@ -1127,6 +1141,7 @@ ZSTD_decompressSequencesLong_default(ZSTD_DCtx* dctx,

 #ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
 static TARGET_ATTRIBUTE("bmi2") size_t
+DONT_VECTORIZE
 ZSTD_decompressSequences_bmi2(ZSTD_DCtx* dctx,
                                 void* dst, size_t maxDstSize,
                           const void* seqStart, size_t seqSize, int nbSeq,
@@ -1176,7 +1191,7 @@ ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize,
 /* ZSTD_decompressSequencesLong() :
 * decompression function triggered when a minimum share of offsets is considered "long",
 * aka out of cache.
- * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes mearning "farther than memory cache distance".
+ * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance".
 * This function will try to mitigate main memory latency through the use of prefetching */
 static size_t
 ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx,
@@ -1240,7 +1255,7 @@ ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
    ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN))));
    DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize);

-    if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong);

    /* Decode literals section */
    {   size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
@@ -89,6 +89,12 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
 typedef enum { zdss_init=0, zdss_loadHeader,
               zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;

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

    /* streaming */
    ZSTD_dStreamStage streamStage;
@@ -391,7 +391,7 @@ static void COVER_group(COVER_ctx_t *ctx, const void *group,
 *
 *     Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
 *
- * Once the dmer d is in the dictionay we set F(d) = 0.
+ * Once the dmer d is in the dictionary we set F(d) = 0.
 */
 static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
                                           COVER_map_t *activeDmers, U32 begin,
@@ -435,7 +435,7 @@ static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
      U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer);
      activeSegment.begin += 1;
      *delDmerOcc -= 1;
-      /* If this is the last occurence of the dmer, subtract its score */
+      /* If this is the last occurrence of the dmer, subtract its score */
      if (*delDmerOcc == 0) {
        COVER_map_remove(activeDmers, delDmer);
        activeSegment.score -= freqs[delDmer];
@@ -526,10 +526,10 @@ static void COVER_ctx_destroy(COVER_ctx_t *ctx) {
 * Prepare a context for dictionary building.
 * The context is only dependent on the parameter `d` and can used multiple
 * times.
- * Returns 1 on success or zero on error.
+ * Returns 0 on success or error code on error.
 * The context must be destroyed with `COVER_ctx_destroy()`.
 */
-static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
+static size_t COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
                          const size_t *samplesSizes, unsigned nbSamples,
                          unsigned d, double splitPoint) {
  const BYTE *const samples = (const BYTE *)samplesBuffer;
@@ -544,17 +544,17 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
      totalSamplesSize >= (size_t)COVER_MAX_SAMPLES_SIZE) {
    DISPLAYLEVEL(1, "Total samples size is too large (%u MB), maximum size is %u MB\n",
                 (unsigned)(totalSamplesSize>>20), (COVER_MAX_SAMPLES_SIZE >> 20));
-    return 0;
+    return ERROR(srcSize_wrong);
  }
  /* Check if there are at least 5 training samples */
  if (nbTrainSamples < 5) {
    DISPLAYLEVEL(1, "Total number of training samples is %u and is invalid.", nbTrainSamples);
-    return 0;
+    return ERROR(srcSize_wrong);
  }
  /* Check if there's testing sample */
  if (nbTestSamples < 1) {
    DISPLAYLEVEL(1, "Total number of testing samples is %u and is invalid.", nbTestSamples);
-    return 0;
+    return ERROR(srcSize_wrong);
  }
  /* Zero the context */
  memset(ctx, 0, sizeof(*ctx));
@@ -577,7 +577,7 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
  if (!ctx->suffix || !ctx->dmerAt || !ctx->offsets) {
    DISPLAYLEVEL(1, "Failed to allocate scratch buffers\n");
    COVER_ctx_destroy(ctx);
-    return 0;
+    return ERROR(memory_allocation);
  }
  ctx->freqs = NULL;
  ctx->d = d;
@@ -624,7 +624,40 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
                (ctx->d <= 8 ? &COVER_cmp8 : &COVER_cmp), &COVER_group);
  ctx->freqs = ctx->suffix;
  ctx->suffix = NULL;
-  return 1;
+  return 0;
+}
+
+void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel)
+{
+  const double ratio = (double)nbDmers / maxDictSize;
+  if (ratio >= 10) {
+      return;
+  }
+  LOCALDISPLAYLEVEL(displayLevel, 1,
+                    "WARNING: The maximum dictionary size %u is too large "
+                    "compared to the source size %u! "
+                    "size(source)/size(dictionary) = %f, but it should be >= "
+                    "10! This may lead to a subpar dictionary! We recommend "
+                    "training on sources at least 10x, and up to 100x the "
+                    "size of the dictionary!\n", (U32)maxDictSize,
+                    (U32)nbDmers, ratio);
+}
+
+COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize,
+                                       U32 nbDmers, U32 k, U32 passes)
+{
+  const U32 minEpochSize = k * 10;
+  COVER_epoch_info_t epochs;
+  epochs.num = MAX(1, maxDictSize / k / passes);
+  epochs.size = nbDmers / epochs.num;
+  if (epochs.size >= minEpochSize) {
+      assert(epochs.size * epochs.num <= nbDmers);
+      return epochs;
+  }
+  epochs.size = MIN(minEpochSize, nbDmers);
+  epochs.num = nbDmers / epochs.size;
+  assert(epochs.size * epochs.num <= nbDmers);
+  return epochs;
 }

 /**
@@ -636,28 +669,34 @@ static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs,
                                    ZDICT_cover_params_t parameters) {
  BYTE *const dict = (BYTE *)dictBuffer;
  size_t tail = dictBufferCapacity;
-  /* Divide the data up into epochs of equal size.
-   * We will select at least one segment from each epoch.
-   */
-  const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k / 4));
-  const unsigned epochSize = (U32)(ctx->suffixSize / epochs);
+  /* Divide the data into epochs. We will select one segment from each epoch. */
+  const COVER_epoch_info_t epochs = COVER_computeEpochs(
+      (U32)dictBufferCapacity, (U32)ctx->suffixSize, parameters.k, 4);
+  const size_t maxZeroScoreRun = MAX(10, MIN(100, epochs.num >> 3));
+  size_t zeroScoreRun = 0;
  size_t epoch;
  DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n",
-                epochs, epochSize);
+                (U32)epochs.num, (U32)epochs.size);
  /* Loop through the epochs until there are no more segments or the dictionary
   * is full.
   */
-  for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) {
-    const U32 epochBegin = (U32)(epoch * epochSize);
-    const U32 epochEnd = epochBegin + epochSize;
+  for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) {
+    const U32 epochBegin = (U32)(epoch * epochs.size);
+    const U32 epochEnd = epochBegin + epochs.size;
    size_t segmentSize;
    /* Select a segment */
    COVER_segment_t segment = COVER_selectSegment(
        ctx, freqs, activeDmers, epochBegin, epochEnd, parameters);
-    /* If the segment covers no dmers, then we are out of content */
+    /* If the segment covers no dmers, then we are out of content.
+     * There may be new content in other epochs, for continue for some time.
+     */
    if (segment.score == 0) {
-      break;
+      if (++zeroScoreRun >= maxZeroScoreRun) {
+          break;
+      }
+      continue;
    }
+    zeroScoreRun = 0;
    /* Trim the segment if necessary and if it is too small then we are done */
    segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
    if (segmentSize < parameters.d) {
@@ -690,11 +729,11 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
  /* Checks */
  if (!COVER_checkParameters(parameters, dictBufferCapacity)) {
    DISPLAYLEVEL(1, "Cover parameters incorrect\n");
-    return ERROR(GENERIC);
+    return ERROR(parameter_outOfBound);
  }
  if (nbSamples == 0) {
    DISPLAYLEVEL(1, "Cover must have at least one input file\n");
-    return ERROR(GENERIC);
+    return ERROR(srcSize_wrong);
  }
  if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
    DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n",
@@ -702,14 +741,18 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
    return ERROR(dstSize_tooSmall);
  }
  /* Initialize context and activeDmers */
-  if (!COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
-                      parameters.d, parameters.splitPoint)) {
-    return ERROR(GENERIC);
+  {
+    size_t const initVal = COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
+                      parameters.d, parameters.splitPoint);
+    if (ZSTD_isError(initVal)) {
+      return initVal;
+    }
  }
+  COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, g_displayLevel);
  if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) {
    DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n");
    COVER_ctx_destroy(&ctx);
-    return ERROR(GENERIC);
+    return ERROR(memory_allocation);
  }

  DISPLAYLEVEL(2, "Building dictionary\n");
@@ -770,7 +813,7 @@ size_t COVER_checkTotalCompressedSize(const ZDICT_cover_params_t parameters,
        cctx, dst, dstCapacity, samples + offsets[i],
        samplesSizes[i], cdict);
    if (ZSTD_isError(size)) {
-      totalCompressedSize = ERROR(GENERIC);
+      totalCompressedSize = size;
      goto _compressCleanup;
    }
    totalCompressedSize += size;
@@ -846,9 +889,11 @@ void COVER_best_start(COVER_best_t *best) {
 * Decrements liveJobs and signals any waiting threads if liveJobs == 0.
 * If this dictionary is the best so far save it and its parameters.
 */
-void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
-                              ZDICT_cover_params_t parameters, void *dict,
-                              size_t dictSize) {
+void COVER_best_finish(COVER_best_t *best, ZDICT_cover_params_t parameters,
+                              COVER_dictSelection_t selection) {
+  void* dict = selection.dictContent;
+  size_t compressedSize = selection.totalCompressedSize;
+  size_t dictSize = selection.dictSize;
  if (!best) {
    return;
  }
@@ -874,6 +919,9 @@ void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
        }
      }
      /* Save the dictionary, parameters, and size */
+      if (!dict) {
+        return;
+      }
      memcpy(best->dict, dict, dictSize);
      best->dictSize = dictSize;
      best->parameters = parameters;
@@ -886,6 +934,111 @@ void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
  }
 }

+COVER_dictSelection_t COVER_dictSelectionError(size_t error) {
+    COVER_dictSelection_t selection = { NULL, 0, error };
+    return selection;
+}
+
+unsigned COVER_dictSelectionIsError(COVER_dictSelection_t selection) {
+  return (ZSTD_isError(selection.totalCompressedSize) || !selection.dictContent);
+}
+
+void COVER_dictSelectionFree(COVER_dictSelection_t selection){
+  free(selection.dictContent);
+}
+
+COVER_dictSelection_t COVER_selectDict(BYTE* customDictContent,
+        size_t dictContentSize, const BYTE* samplesBuffer, const size_t* samplesSizes, unsigned nbFinalizeSamples,
+        size_t nbCheckSamples, size_t nbSamples, ZDICT_cover_params_t params, size_t* offsets, size_t totalCompressedSize) {
+
+  size_t largestDict = 0;
+  size_t largestCompressed = 0;
+  BYTE* customDictContentEnd = customDictContent + dictContentSize;
+
+  BYTE * largestDictbuffer = (BYTE *)malloc(dictContentSize);
+  BYTE * candidateDictBuffer = (BYTE *)malloc(dictContentSize);
+  double regressionTolerance = ((double)params.shrinkDictMaxRegression / 100.0) + 1.00;
+
+  if (!largestDictbuffer || !candidateDictBuffer) {
+    free(largestDictbuffer);
+    free(candidateDictBuffer);
+    return COVER_dictSelectionError(dictContentSize);
+  }
+
+  /* Initial dictionary size and compressed size */
+  memcpy(largestDictbuffer, customDictContent, dictContentSize);
+  dictContentSize = ZDICT_finalizeDictionary(
+    largestDictbuffer, dictContentSize, customDictContent, dictContentSize,
+    samplesBuffer, samplesSizes, nbFinalizeSamples, params.zParams);
+
+  if (ZDICT_isError(dictContentSize)) {
+    free(largestDictbuffer);
+    free(candidateDictBuffer);
+    return COVER_dictSelectionError(dictContentSize);
+  }
+
+  totalCompressedSize = COVER_checkTotalCompressedSize(params, samplesSizes,
+                                                       samplesBuffer, offsets,
+                                                       nbCheckSamples, nbSamples,
+                                                       largestDictbuffer, dictContentSize);
+
+  if (ZSTD_isError(totalCompressedSize)) {
+    free(largestDictbuffer);
+    free(candidateDictBuffer);
+    return COVER_dictSelectionError(totalCompressedSize);
+  }
+
+  if (params.shrinkDict == 0) {
+    COVER_dictSelection_t selection = { largestDictbuffer, dictContentSize, totalCompressedSize };
+    free(candidateDictBuffer);
+    return selection;
+  }
+
+  largestDict = dictContentSize;
+  largestCompressed = totalCompressedSize;
+  dictContentSize = ZDICT_DICTSIZE_MIN;
+
+  /* Largest dict is initially at least ZDICT_DICTSIZE_MIN */
+  while (dictContentSize < largestDict) {
+    memcpy(candidateDictBuffer, largestDictbuffer, largestDict);
+    dictContentSize = ZDICT_finalizeDictionary(
+      candidateDictBuffer, dictContentSize, customDictContentEnd - dictContentSize, dictContentSize,
+      samplesBuffer, samplesSizes, nbFinalizeSamples, params.zParams);
+
+    if (ZDICT_isError(dictContentSize)) {
+      free(largestDictbuffer);
+      free(candidateDictBuffer);
+      return COVER_dictSelectionError(dictContentSize);
+
+    }
+
+    totalCompressedSize = COVER_checkTotalCompressedSize(params, samplesSizes,
+                                                         samplesBuffer, offsets,
+                                                         nbCheckSamples, nbSamples,
+                                                         candidateDictBuffer, dictContentSize);
+
+    if (ZSTD_isError(totalCompressedSize)) {
+      free(largestDictbuffer);
+      free(candidateDictBuffer);
+      return COVER_dictSelectionError(totalCompressedSize);
+    }
+
+    if (totalCompressedSize <= largestCompressed * regressionTolerance) {
+      COVER_dictSelection_t selection = { candidateDictBuffer, dictContentSize, totalCompressedSize };
+      free(largestDictbuffer);
+      return selection;
+    }
+    dictContentSize *= 2;
+  }
+  dictContentSize = largestDict;
+  totalCompressedSize = largestCompressed;
+  {
+    COVER_dictSelection_t selection = { largestDictbuffer, dictContentSize, totalCompressedSize };
+    free(candidateDictBuffer);
+    return selection;
+  }
+}
+
 /**
 * Parameters for COVER_tryParameters().
 */
@@ -911,6 +1064,7 @@ static void COVER_tryParameters(void *opaque) {
  /* Allocate space for hash table, dict, and freqs */
  COVER_map_t activeDmers;
  BYTE *const dict = (BYTE * const)malloc(dictBufferCapacity);
+  COVER_dictSelection_t selection = COVER_dictSelectionError(ERROR(GENERIC));
  U32 *freqs = (U32 *)malloc(ctx->suffixSize * sizeof(U32));
  if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) {
    DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n");
@@ -926,29 +1080,21 @@ static void COVER_tryParameters(void *opaque) {
  {
    const size_t tail = COVER_buildDictionary(ctx, freqs, &activeDmers, dict,
                                              dictBufferCapacity, parameters);
-    dictBufferCapacity = ZDICT_finalizeDictionary(
-        dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail,
-        ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbTrainSamples,
-        parameters.zParams);
-    if (ZDICT_isError(dictBufferCapacity)) {
-      DISPLAYLEVEL(1, "Failed to finalize dictionary\n");
+    selection = COVER_selectDict(dict + tail, dictBufferCapacity - tail,
+        ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbTrainSamples, ctx->nbTrainSamples, ctx->nbSamples, parameters, ctx->offsets,
+        totalCompressedSize);
+
+    if (COVER_dictSelectionIsError(selection)) {
+      DISPLAYLEVEL(1, "Failed to select dictionary\n");
      goto _cleanup;
    }
  }
-  /* Check total compressed size */
-  totalCompressedSize = COVER_checkTotalCompressedSize(parameters, ctx->samplesSizes,
-                                                       ctx->samples, ctx->offsets,
-                                                       ctx->nbTrainSamples, ctx->nbSamples,
-                                                       dict, dictBufferCapacity);
-
 _cleanup:
-  COVER_best_finish(data->best, totalCompressedSize, parameters, dict,
-                    dictBufferCapacity);
+  free(dict);
+  COVER_best_finish(data->best, parameters, selection);
  free(data);
  COVER_map_destroy(&activeDmers);
-  if (dict) {
-    free(dict);
-  }
+  COVER_dictSelectionFree(selection);
  if (freqs) {
    free(freqs);
  }
@@ -970,6 +1116,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
  const unsigned kStepSize = MAX((kMaxK - kMinK) / kSteps, 1);
  const unsigned kIterations =
      (1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize);
+  const unsigned shrinkDict = 0;
  /* Local variables */
  const int displayLevel = parameters->zParams.notificationLevel;
  unsigned iteration = 1;
@@ -977,19 +1124,20 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
  unsigned k;
  COVER_best_t best;
  POOL_ctx *pool = NULL;
+  int warned = 0;

  /* Checks */
  if (splitPoint <= 0 || splitPoint > 1) {
    LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n");
-    return ERROR(GENERIC);
+    return ERROR(parameter_outOfBound);
  }
  if (kMinK < kMaxD || kMaxK < kMinK) {
    LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n");
-    return ERROR(GENERIC);
+    return ERROR(parameter_outOfBound);
  }
  if (nbSamples == 0) {
    DISPLAYLEVEL(1, "Cover must have at least one input file\n");
-    return ERROR(GENERIC);
+    return ERROR(srcSize_wrong);
  }
  if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
    DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n",
@@ -1013,11 +1161,18 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
    /* Initialize the context for this value of d */
    COVER_ctx_t ctx;
    LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d);
-    if (!COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint)) {
-      LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n");
-      COVER_best_destroy(&best);
-      POOL_free(pool);
-      return ERROR(GENERIC);
+    {
+      const size_t initVal = COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint);
+      if (ZSTD_isError(initVal)) {
+        LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n");
+        COVER_best_destroy(&best);
+        POOL_free(pool);
+        return initVal;
+      }
+    }
+    if (!warned) {
+      COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, displayLevel);
+      warned = 1;
    }
    /* Loop through k reusing the same context */
    for (k = kMinK; k <= kMaxK; k += kStepSize) {
@@ -1030,7 +1185,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
        COVER_best_destroy(&best);
        COVER_ctx_destroy(&ctx);
        POOL_free(pool);
-        return ERROR(GENERIC);
+        return ERROR(memory_allocation);
      }
      data->ctx = &ctx;
      data->best = &best;
@@ -1040,6 +1195,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
      data->parameters.d = d;
      data->parameters.splitPoint = splitPoint;
      data->parameters.steps = kSteps;
+      data->parameters.shrinkDict = shrinkDict;
      data->parameters.zParams.notificationLevel = g_displayLevel;
      /* Check the parameters */
      if (!COVER_checkParameters(data->parameters, dictBufferCapacity)) {
@@ -38,6 +38,44 @@ typedef struct {
  U32 score;
 } COVER_segment_t;

+/**
+ *Number of epochs and size of each epoch.
+ */
+typedef struct {
+  U32 num;
+  U32 size;
+} COVER_epoch_info_t;
+
+/**
+ * Struct used for the dictionary selection function.
+ */
+typedef struct COVER_dictSelection {
+  BYTE* dictContent;
+  size_t dictSize;
+  size_t totalCompressedSize;
+} COVER_dictSelection_t;
+
+/**
+ * Computes the number of epochs and the size of each epoch.
+ * We will make sure that each epoch gets at least 10 * k bytes.
+ *
+ * The COVER algorithms divide the data up into epochs of equal size and
+ * select one segment from each epoch.
+ *
+ * @param maxDictSize The maximum allowed dictionary size.
+ * @param nbDmers     The number of dmers we are training on.
+ * @param k           The parameter k (segment size).
+ * @param passes      The target number of passes over the dmer corpus.
+ *                    More passes means a better dictionary.
+ */
+COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, U32 nbDmers,
+                                       U32 k, U32 passes);
+
+/**
+ * Warns the user when their corpus is too small.
+ */
+void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel);
+
 /**
 *  Checks total compressed size of a dictionary
 */
@@ -78,6 +116,32 @@ void COVER_best_start(COVER_best_t *best);
 * Decrements liveJobs and signals any waiting threads if liveJobs == 0.
 * If this dictionary is the best so far save it and its parameters.
 */
-void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
-                       ZDICT_cover_params_t parameters, void *dict,
-                       size_t dictSize);
+void COVER_best_finish(COVER_best_t *best, ZDICT_cover_params_t parameters,
+                       COVER_dictSelection_t selection);
+/**
+ * Error function for COVER_selectDict function. Checks if the return
+ * value is an error.
+ */
+unsigned COVER_dictSelectionIsError(COVER_dictSelection_t selection);
+
+ /**
+  * Error function for COVER_selectDict function. Returns a struct where
+  * return.totalCompressedSize is a ZSTD error.
+  */
+COVER_dictSelection_t COVER_dictSelectionError(size_t error);
+
+/**
+ * Always call after selectDict is called to free up used memory from
+ * newly created dictionary.
+ */
+void COVER_dictSelectionFree(COVER_dictSelection_t selection);
+
+/**
+ * Called to finalize the dictionary and select one based on whether or not
+ * the shrink-dict flag was enabled. If enabled the dictionary used is the
+ * smallest dictionary within a specified regression of the compressed size
+ * from the largest dictionary.
+ */
+ COVER_dictSelection_t COVER_selectDict(BYTE* customDictContent,
+                       size_t dictContentSize, const BYTE* samplesBuffer, const size_t* samplesSizes, unsigned nbFinalizeSamples,
+                       size_t nbCheckSamples, size_t nbSamples, ZDICT_cover_params_t params, size_t* offsets, size_t totalCompressedSize);
@@ -132,7 +132,7 @@ typedef struct {
 *
 *     Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
 *
- * Once the dmer with hash value d is in the dictionay we set F(d) = 0.
+ * Once the dmer with hash value d is in the dictionary we set F(d) = 0.
 */
 static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
                                              U32 *freqs, U32 begin, U32 end,
@@ -161,7 +161,7 @@ static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
    /* Get hash value of current dmer */
    const size_t idx = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, f, d);

-    /* Add frequency of this index to score if this is the first occurence of index in active segment */
+    /* Add frequency of this index to score if this is the first occurrence of index in active segment */
    if (segmentFreqs[idx] == 0) {
      activeSegment.score += freqs[idx];
    }
@@ -287,10 +287,10 @@ FASTCOVER_computeFrequency(U32* freqs, const FASTCOVER_ctx_t* ctx)
 * Prepare a context for dictionary building.
 * The context is only dependent on the parameter `d` and can used multiple
 * times.
- * Returns 1 on success or zero on error.
+ * Returns 0 on success or error code on error.
 * The context must be destroyed with `FASTCOVER_ctx_destroy()`.
 */
-static int
+static size_t
 FASTCOVER_ctx_init(FASTCOVER_ctx_t* ctx,
                   const void* samplesBuffer,
                   const size_t* samplesSizes, unsigned nbSamples,
@@ -310,19 +310,19 @@ FASTCOVER_ctx_init(FASTCOVER_ctx_t* ctx,
        totalSamplesSize >= (size_t)FASTCOVER_MAX_SAMPLES_SIZE) {
        DISPLAYLEVEL(1, "Total samples size is too large (%u MB), maximum size is %u MB\n",
                    (unsigned)(totalSamplesSize >> 20), (FASTCOVER_MAX_SAMPLES_SIZE >> 20));
-        return 0;
+        return ERROR(srcSize_wrong);
    }

    /* Check if there are at least 5 training samples */
    if (nbTrainSamples < 5) {
        DISPLAYLEVEL(1, "Total number of training samples is %u and is invalid\n", nbTrainSamples);
-        return 0;
+        return ERROR(srcSize_wrong);
    }

    /* Check if there's testing sample */
    if (nbTestSamples < 1) {
        DISPLAYLEVEL(1, "Total number of testing samples is %u and is invalid.\n", nbTestSamples);
-        return 0;
+        return ERROR(srcSize_wrong);
    }

    /* Zero the context */
@@ -347,7 +347,7 @@ FASTCOVER_ctx_init(FASTCOVER_ctx_t* ctx,
    if (ctx->offsets == NULL) {
        DISPLAYLEVEL(1, "Failed to allocate scratch buffers \n");
        FASTCOVER_ctx_destroy(ctx);
-        return 0;
+        return ERROR(memory_allocation);
    }

    /* Fill offsets from the samplesSizes */
@@ -364,13 +364,13 @@ FASTCOVER_ctx_init(FASTCOVER_ctx_t* ctx,
    if (ctx->freqs == NULL) {
        DISPLAYLEVEL(1, "Failed to allocate frequency table \n");
        FASTCOVER_ctx_destroy(ctx);
-        return 0;
+        return ERROR(memory_allocation);
    }

    DISPLAYLEVEL(2, "Computing frequencies\n");
    FASTCOVER_computeFrequency(ctx->freqs, ctx);

-    return 1;
+    return 0;
 }


@@ -386,29 +386,35 @@ FASTCOVER_buildDictionary(const FASTCOVER_ctx_t* ctx,
 {
  BYTE *const dict = (BYTE *)dictBuffer;
  size_t tail = dictBufferCapacity;
-  /* Divide the data up into epochs of equal size.
-   * We will select at least one segment from each epoch.
-   */
-  const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k));
-  const unsigned epochSize = (U32)(ctx->nbDmers / epochs);
+  /* Divide the data into epochs. We will select one segment from each epoch. */
+  const COVER_epoch_info_t epochs = COVER_computeEpochs(
+      (U32)dictBufferCapacity, (U32)ctx->nbDmers, parameters.k, 1);
+  const size_t maxZeroScoreRun = 10;
+  size_t zeroScoreRun = 0;
  size_t epoch;
  DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n",
-                epochs, epochSize);
+                (U32)epochs.num, (U32)epochs.size);
  /* Loop through the epochs until there are no more segments or the dictionary
   * is full.
   */
-  for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) {
-    const U32 epochBegin = (U32)(epoch * epochSize);
-    const U32 epochEnd = epochBegin + epochSize;
+  for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) {
+    const U32 epochBegin = (U32)(epoch * epochs.size);
+    const U32 epochEnd = epochBegin + epochs.size;
    size_t segmentSize;
    /* Select a segment */
    COVER_segment_t segment = FASTCOVER_selectSegment(
        ctx, freqs, epochBegin, epochEnd, parameters, segmentFreqs);

-    /* If the segment covers no dmers, then we are out of content */
+    /* If the segment covers no dmers, then we are out of content.
+     * There may be new content in other epochs, for continue for some time.
+     */
    if (segment.score == 0) {
-      break;
+      if (++zeroScoreRun >= maxZeroScoreRun) {
+          break;
+      }
+      continue;
    }
+    zeroScoreRun = 0;

    /* Trim the segment if necessary and if it is too small then we are done */
    segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
@@ -429,7 +435,6 @@ FASTCOVER_buildDictionary(const FASTCOVER_ctx_t* ctx,
  return tail;
 }

-
 /**
 * Parameters for FASTCOVER_tryParameters().
 */
@@ -458,6 +463,7 @@ static void FASTCOVER_tryParameters(void *opaque)
  U16* segmentFreqs = (U16 *)calloc(((U64)1 << ctx->f), sizeof(U16));
  /* Allocate space for hash table, dict, and freqs */
  BYTE *const dict = (BYTE * const)malloc(dictBufferCapacity);
+  COVER_dictSelection_t selection = COVER_dictSelectionError(ERROR(GENERIC));
  U32 *freqs = (U32*) malloc(((U64)1 << ctx->f) * sizeof(U32));
  if (!segmentFreqs || !dict || !freqs) {
    DISPLAYLEVEL(1, "Failed to allocate buffers: out of memory\n");
@@ -467,27 +473,24 @@ static void FASTCOVER_tryParameters(void *opaque)
  memcpy(freqs, ctx->freqs, ((U64)1 << ctx->f) * sizeof(U32));
  /* Build the dictionary */
  { const size_t tail = FASTCOVER_buildDictionary(ctx, freqs, dict, dictBufferCapacity,
-                                                  parameters, segmentFreqs);
+                                                    parameters, segmentFreqs);
+
    const unsigned nbFinalizeSamples = (unsigned)(ctx->nbTrainSamples * ctx->accelParams.finalize / 100);
-    dictBufferCapacity = ZDICT_finalizeDictionary(
-        dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail,
-        ctx->samples, ctx->samplesSizes, nbFinalizeSamples, parameters.zParams);
-    if (ZDICT_isError(dictBufferCapacity)) {
-      DISPLAYLEVEL(1, "Failed to finalize dictionary\n");
+    selection = COVER_selectDict(dict + tail, dictBufferCapacity - tail,
+         ctx->samples, ctx->samplesSizes, nbFinalizeSamples, ctx->nbTrainSamples, ctx->nbSamples, parameters, ctx->offsets,
+         totalCompressedSize);
+
+    if (COVER_dictSelectionIsError(selection)) {
+      DISPLAYLEVEL(1, "Failed to select dictionary\n");
      goto _cleanup;
    }
  }
-  /* Check total compressed size */
-  totalCompressedSize = COVER_checkTotalCompressedSize(parameters, ctx->samplesSizes,
-                                                       ctx->samples, ctx->offsets,
-                                                       ctx->nbTrainSamples, ctx->nbSamples,
-                                                       dict, dictBufferCapacity);
 _cleanup:
-  COVER_best_finish(data->best, totalCompressedSize, parameters, dict,
-                    dictBufferCapacity);
+  free(dict);
+  COVER_best_finish(data->best, parameters, selection);
  free(data);
  free(segmentFreqs);
-  free(dict);
+  COVER_dictSelectionFree(selection);
  free(freqs);
 }

@@ -502,6 +505,7 @@ FASTCOVER_convertToCoverParams(ZDICT_fastCover_params_t fastCoverParams,
    coverParams->nbThreads = fastCoverParams.nbThreads;
    coverParams->splitPoint = fastCoverParams.splitPoint;
    coverParams->zParams = fastCoverParams.zParams;
+    coverParams->shrinkDict = fastCoverParams.shrinkDict;
 }


@@ -518,6 +522,7 @@ FASTCOVER_convertToFastCoverParams(ZDICT_cover_params_t coverParams,
    fastCoverParams->f = f;
    fastCoverParams->accel = accel;
    fastCoverParams->zParams = coverParams.zParams;
+    fastCoverParams->shrinkDict = coverParams.shrinkDict;
 }


@@ -544,11 +549,11 @@ ZDICT_trainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity,
    if (!FASTCOVER_checkParameters(coverParams, dictBufferCapacity, parameters.f,
                                   parameters.accel)) {
      DISPLAYLEVEL(1, "FASTCOVER parameters incorrect\n");
-      return ERROR(GENERIC);
+      return ERROR(parameter_outOfBound);
    }
    if (nbSamples == 0) {
      DISPLAYLEVEL(1, "FASTCOVER must have at least one input file\n");
-      return ERROR(GENERIC);
+      return ERROR(srcSize_wrong);
    }
    if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
      DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n",
@@ -558,12 +563,16 @@ ZDICT_trainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity,
    /* Assign corresponding FASTCOVER_accel_t to accelParams*/
    accelParams = FASTCOVER_defaultAccelParameters[parameters.accel];
    /* Initialize context */
-    if (!FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
+    {
+      size_t const initVal = FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
                            coverParams.d, parameters.splitPoint, parameters.f,
-                            accelParams)) {
-      DISPLAYLEVEL(1, "Failed to initialize context\n");
-      return ERROR(GENERIC);
+                            accelParams);
+      if (ZSTD_isError(initVal)) {
+        DISPLAYLEVEL(1, "Failed to initialize context\n");
+        return initVal;
+      }
    }
+    COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, g_displayLevel);
    /* Build the dictionary */
    DISPLAYLEVEL(2, "Building dictionary\n");
    {
@@ -609,6 +618,7 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
        (1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize);
    const unsigned f = parameters->f == 0 ? DEFAULT_F : parameters->f;
    const unsigned accel = parameters->accel == 0 ? DEFAULT_ACCEL : parameters->accel;
+    const unsigned shrinkDict = 0;
    /* Local variables */
    const int displayLevel = parameters->zParams.notificationLevel;
    unsigned iteration = 1;
@@ -616,22 +626,23 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
    unsigned k;
    COVER_best_t best;
    POOL_ctx *pool = NULL;
+    int warned = 0;
    /* Checks */
    if (splitPoint <= 0 || splitPoint > 1) {
      LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect splitPoint\n");
-      return ERROR(GENERIC);
+      return ERROR(parameter_outOfBound);
    }
    if (accel == 0 || accel > FASTCOVER_MAX_ACCEL) {
      LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect accel\n");
-      return ERROR(GENERIC);
+      return ERROR(parameter_outOfBound);
    }
    if (kMinK < kMaxD || kMaxK < kMinK) {
      LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect k\n");
-      return ERROR(GENERIC);
+      return ERROR(parameter_outOfBound);
    }
    if (nbSamples == 0) {
      LOCALDISPLAYLEVEL(displayLevel, 1, "FASTCOVER must have at least one input file\n");
-      return ERROR(GENERIC);
+      return ERROR(srcSize_wrong);
    }
    if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
      LOCALDISPLAYLEVEL(displayLevel, 1, "dictBufferCapacity must be at least %u\n",
@@ -658,11 +669,18 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
      /* Initialize the context for this value of d */
      FASTCOVER_ctx_t ctx;
      LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d);
-      if (!FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint, f, accelParams)) {
-        LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n");
-        COVER_best_destroy(&best);
-        POOL_free(pool);
-        return ERROR(GENERIC);
+      {
+        size_t const initVal = FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint, f, accelParams);
+        if (ZSTD_isError(initVal)) {
+          LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n");
+          COVER_best_destroy(&best);
+          POOL_free(pool);
+          return initVal;
+        }
+      }
+      if (!warned) {
+        COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, displayLevel);
+        warned = 1;
      }
      /* Loop through k reusing the same context */
      for (k = kMinK; k <= kMaxK; k += kStepSize) {
@@ -675,7 +693,7 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
          COVER_best_destroy(&best);
          FASTCOVER_ctx_destroy(&ctx);
          POOL_free(pool);
-          return ERROR(GENERIC);
+          return ERROR(memory_allocation);
        }
        data->ctx = &ctx;
        data->best = &best;
@@ -685,6 +703,7 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
        data->parameters.d = d;
        data->parameters.splitPoint = splitPoint;
        data->parameters.steps = kSteps;
+        data->parameters.shrinkDict = shrinkDict;
        data->parameters.zParams.notificationLevel = g_displayLevel;
        /* Check the parameters */
        if (!FASTCOVER_checkParameters(data->parameters, dictBufferCapacity,
@@ -741,7 +741,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    /* analyze, build stats, starting with literals */
    {   size_t maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog);
        if (HUF_isError(maxNbBits)) {
-            eSize = ERROR(GENERIC);
+            eSize = maxNbBits;
            DISPLAYLEVEL(1, " HUF_buildCTable error \n");
            goto _cleanup;
        }
@@ -764,7 +764,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    total=0; for (u=0; u<=offcodeMax; u++) total+=offcodeCount[u];
    errorCode = FSE_normalizeCount(offcodeNCount, Offlog, offcodeCount, total, offcodeMax);
    if (FSE_isError(errorCode)) {
-        eSize = ERROR(GENERIC);
+        eSize = errorCode;
        DISPLAYLEVEL(1, "FSE_normalizeCount error with offcodeCount \n");
        goto _cleanup;
    }
@@ -773,7 +773,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    total=0; for (u=0; u<=MaxML; u++) total+=matchLengthCount[u];
    errorCode = FSE_normalizeCount(matchLengthNCount, mlLog, matchLengthCount, total, MaxML);
    if (FSE_isError(errorCode)) {
-        eSize = ERROR(GENERIC);
+        eSize = errorCode;
        DISPLAYLEVEL(1, "FSE_normalizeCount error with matchLengthCount \n");
        goto _cleanup;
    }
@@ -782,7 +782,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    total=0; for (u=0; u<=MaxLL; u++) total+=litLengthCount[u];
    errorCode = FSE_normalizeCount(litLengthNCount, llLog, litLengthCount, total, MaxLL);
    if (FSE_isError(errorCode)) {
-        eSize = ERROR(GENERIC);
+        eSize = errorCode;
        DISPLAYLEVEL(1, "FSE_normalizeCount error with litLengthCount \n");
        goto _cleanup;
    }
@@ -791,7 +791,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    /* write result to buffer */
    {   size_t const hhSize = HUF_writeCTable(dstPtr, maxDstSize, hufTable, 255, huffLog);
        if (HUF_isError(hhSize)) {
-            eSize = ERROR(GENERIC);
+            eSize = hhSize;
            DISPLAYLEVEL(1, "HUF_writeCTable error \n");
            goto _cleanup;
        }
@@ -802,7 +802,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,

    {   size_t const ohSize = FSE_writeNCount(dstPtr, maxDstSize, offcodeNCount, OFFCODE_MAX, Offlog);
        if (FSE_isError(ohSize)) {
-            eSize = ERROR(GENERIC);
+            eSize = ohSize;
            DISPLAYLEVEL(1, "FSE_writeNCount error with offcodeNCount \n");
            goto _cleanup;
        }
@@ -813,7 +813,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,

    {   size_t const mhSize = FSE_writeNCount(dstPtr, maxDstSize, matchLengthNCount, MaxML, mlLog);
        if (FSE_isError(mhSize)) {
-            eSize = ERROR(GENERIC);
+            eSize = mhSize;
            DISPLAYLEVEL(1, "FSE_writeNCount error with matchLengthNCount \n");
            goto _cleanup;
        }
@@ -824,7 +824,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,

    {   size_t const lhSize = FSE_writeNCount(dstPtr, maxDstSize, litLengthNCount, MaxLL, llLog);
        if (FSE_isError(lhSize)) {
-            eSize = ERROR(GENERIC);
+            eSize = lhSize;
            DISPLAYLEVEL(1, "FSE_writeNCount error with litlengthNCount \n");
            goto _cleanup;
        }
@@ -834,7 +834,7 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
    }

    if (maxDstSize<12) {
-        eSize = ERROR(GENERIC);
+        eSize = ERROR(dstSize_tooSmall);
        DISPLAYLEVEL(1, "not enough space to write RepOffsets \n");
        goto _cleanup;
    }
@@ -46,7 +46,12 @@ extern "C" {
 *  The resulting dictionary will be saved into `dictBuffer`.
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
 *          or an error code, which can be tested with ZDICT_isError().
- *  Note: ZDICT_trainFromBuffer() requires about 9 bytes of memory for each input byte.
+ *  Note:  Dictionary training will fail if there are not enough samples to construct a
+ *         dictionary, or if most of the samples are too small (< 8 bytes being the lower limit).
+ *         If dictionary training fails, you should use zstd without a dictionary, as the dictionary
+ *         would've been ineffective anyways. If you believe your samples would benefit from a dictionary
+ *         please open an issue with details, and we can look into it.
+ *  Note: ZDICT_trainFromBuffer()'s memory usage is about 6 MB.
 *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
 *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
 *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
@@ -89,6 +94,8 @@ typedef struct {
    unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (40) : Higher means more parameters checked */
    unsigned nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
    double splitPoint;           /* Percentage of samples used for training: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (1.0), 1.0 when all samples are used for both training and testing */
+    unsigned shrinkDict;         /* Train dictionaries to shrink in size starting from the minimum size and selects the smallest dictionary that is shrinkDictMaxRegression% worse than the largest dictionary. 0 means no shrinking and 1 means shrinking  */
+    unsigned shrinkDictMaxRegression; /* Sets shrinkDictMaxRegression so that a smaller dictionary can be at worse shrinkDictMaxRegression% worse than the max dict size dictionary. */
    ZDICT_params_t zParams;
 } ZDICT_cover_params_t;

@@ -100,6 +107,9 @@ typedef struct {
    unsigned nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
    double splitPoint;           /* Percentage of samples used for training: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (0.75), 1.0 when all samples are used for both training and testing */
    unsigned accel;              /* Acceleration level: constraint: 0 < accel <= 10, higher means faster and less accurate, 0 means default(1) */
+    unsigned shrinkDict;         /* Train dictionaries to shrink in size starting from the minimum size and selects the smallest dictionary that is shrinkDictMaxRegression% worse than the largest dictionary. 0 means no shrinking and 1 means shrinking  */
+    unsigned shrinkDictMaxRegression; /* Sets shrinkDictMaxRegression so that a smaller dictionary can be at worse shrinkDictMaxRegression% worse than the max dict size dictionary. */
+
    ZDICT_params_t zParams;
 } ZDICT_fastCover_params_t;

@@ -110,6 +120,7 @@ typedef struct {
 *  The resulting dictionary will be saved into `dictBuffer`.
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
 *          or an error code, which can be tested with ZDICT_isError().
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
 *  Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte.
 *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
 *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
@@ -133,8 +144,9 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
 * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000].
 *
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- *           On success `*parameters` contains the parameters selected.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          On success `*parameters` contains the parameters selected.
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
 * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread.
 */
 ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
@@ -151,7 +163,8 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
 *  The resulting dictionary will be saved into `dictBuffer`.
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
 *          or an error code, which can be tested with ZDICT_isError().
- *  Note: ZDICT_trainFromBuffer_fastCover() requires about 1 bytes of memory for each input byte and additionally another 6 * 2^f bytes of memory .
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ *  Note: ZDICT_trainFromBuffer_fastCover() requires 6 * 2^f bytes of memory.
 *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
 *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
 *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
@@ -175,9 +188,10 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_fastCover(void *dictBuffer,
 * If accel is zero, default value of 1 is used.
 *
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- *           On success `*parameters` contains the parameters selected.
- * Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 1 byte of memory for each input byte and additionally another 6 * 2^f bytes of memory for each thread.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          On success `*parameters` contains the parameters selected.
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ * Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 6 * 2^f bytes of memory for each thread.
 */
 ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer,
                    size_t dictBufferCapacity, const void* samplesBuffer,
@@ -195,7 +209,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer,
 * maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes.
 *
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
- *           or an error code, which can be tested by ZDICT_isError().
+ *          or an error code, which can be tested by ZDICT_isError().
 * Note: ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0.
 * Note 2: dictBuffer and dictContent can overlap
 */
@@ -219,6 +233,7 @@ typedef struct {
 * `parameters` is optional and can be provided with values set to 0 to mean "default".
 * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
 *          or an error code, which can be tested with ZDICT_isError().
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
 *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
 *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
 *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
@@ -6,14 +6,15 @@ COPY programs\datagen.h bin\example\
 COPY programs\util.h bin\example\
 COPY programs\platform.h bin\example\
 COPY lib\common\mem.h bin\example\
-COPY lib\common\zstd_errors.h bin\example\
 COPY lib\common\zstd_internal.h bin\example\
 COPY lib\common\error_private.h bin\example\
 COPY lib\common\xxhash.h bin\example\
-COPY lib\zstd.h bin\include\
 COPY lib\libzstd.a bin\static\libzstd_static.lib
 COPY lib\dll\libzstd.* bin\dll\
 COPY lib\dll\example\Makefile bin\example\
 COPY lib\dll\example\fullbench-dll.* bin\example\
 COPY lib\dll\example\README.md bin\
+COPY lib\zstd.h bin\include\
+COPY lib\common\zstd_errors.h bin\include\
+COPY lib\dictBuilder\zdict.h bin\include\
 COPY programs\zstd.exe bin\zstd.exe
@@ -1,87 +0,0 @@
-LIBRARY libzstd.dll
-EXPORTS
-    ZDICT_getDictID
-    ZDICT_getErrorName
-    ZDICT_isError
-    ZDICT_trainFromBuffer
-    ZSTD_CStreamInSize
-    ZSTD_CStreamOutSize
-    ZSTD_DStreamInSize
-    ZSTD_DStreamOutSize
-    ZSTD_adjustCParams
-    ZSTD_checkCParams
-    ZSTD_compress
-    ZSTD_compressBegin
-    ZSTD_compressBegin_advanced
-    ZSTD_compressBegin_usingDict
-    ZSTD_compressBlock
-    ZSTD_compressBound
-    ZSTD_compressCCtx
-    ZSTD_compressContinue
-    ZSTD_compressEnd
-    ZSTD_compressStream
-    ZSTD_compress_advanced
-    ZSTD_compress_usingCDict
-    ZSTD_compress_usingDict
-    ZSTD_copyCCtx
-    ZSTD_copyDCtx
-    ZSTD_createCCtx
-    ZSTD_createCCtx_advanced
-    ZSTD_createCDict
-    ZSTD_createCDict_advanced
-    ZSTD_createCStream
-    ZSTD_createCStream_advanced
-    ZSTD_createDCtx
-    ZSTD_createDCtx_advanced
-    ZSTD_createDDict
-    ZSTD_createDStream
-    ZSTD_createDStream_advanced
-    ZSTD_decompress
-    ZSTD_decompressBegin
-    ZSTD_decompressBegin_usingDict
-    ZSTD_decompressBlock
-    ZSTD_decompressContinue
-    ZSTD_decompressDCtx
-    ZSTD_decompressStream
-    ZSTD_decompress_usingDDict
-    ZSTD_decompress_usingDict
-    ZSTD_endStream
-    ZSTD_estimateCCtxSize
-    ZSTD_estimateDCtxSize
-    ZSTD_flushStream
-    ZSTD_freeCCtx
-    ZSTD_freeCDict
-    ZSTD_freeCStream
-    ZSTD_freeDCtx
-    ZSTD_freeDDict
-    ZSTD_freeDStream
-    ZSTD_getBlockSizeMax
-    ZSTD_getCParams
-    ZSTD_getDecompressedSize
-    ZSTD_findDecompressedSize
-    ZSTD_getFrameContentSize
-    ZSTD_getErrorName
-    ZSTD_getFrameParams
-    ZSTD_getParams
-    ZSTD_initCStream
-    ZSTD_initCStream_advanced
-    ZSTD_initCStream_usingCDict
-    ZSTD_initCStream_usingDict
-    ZSTD_initDStream
-    ZSTD_initDStream_usingDDict
-    ZSTD_initDStream_usingDict
-    ZSTD_insertBlock
-    ZSTD_isError
-    ZSTD_isFrame
-    ZSTD_maxCLevel
-    ZSTD_nextInputType
-    ZSTD_nextSrcSizeToDecompress
-    ZSTD_resetCStream
-    ZSTD_resetDStream
-    ZSTD_sizeof_CCtx
-    ZSTD_sizeof_CDict
-    ZSTD_sizeof_CStream
-    ZSTD_sizeof_DCtx
-    ZSTD_sizeof_DDict
-    ZSTD_sizeof_DStream
-    ZSTD_versionNumber
@@ -20,7 +20,7 @@ extern "C" {
 ***************************************/
 #include "mem.h"            /* MEM_STATIC */
 #include "error_private.h"  /* ERROR */
-#include "zstd.h"           /* ZSTD_inBuffer, ZSTD_outBuffer */
+#include "zstd_internal.h"  /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTD_frameSizeInfo */

 #if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0)
 #  undef ZSTD_LEGACY_SUPPORT
@@ -178,43 +178,77 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
    }
 }

-MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src,
-                                             size_t compressedSize)
+MEM_STATIC ZSTD_frameSizeInfo ZSTD_findFrameSizeInfoLegacy(const void *src, size_t srcSize)
 {
-    U32 const version = ZSTD_isLegacy(src, compressedSize);
+    ZSTD_frameSizeInfo frameSizeInfo;
+    U32 const version = ZSTD_isLegacy(src, srcSize);
    switch(version)
    {
 #if (ZSTD_LEGACY_SUPPORT <= 1)
        case 1 :
-            return ZSTDv01_findFrameCompressedSize(src, compressedSize);
+            ZSTDv01_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 2)
        case 2 :
-            return ZSTDv02_findFrameCompressedSize(src, compressedSize);
+            ZSTDv02_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 3)
        case 3 :
-            return ZSTDv03_findFrameCompressedSize(src, compressedSize);
+            ZSTDv03_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 4)
        case 4 :
-            return ZSTDv04_findFrameCompressedSize(src, compressedSize);
+            ZSTDv04_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 5)
        case 5 :
-            return ZSTDv05_findFrameCompressedSize(src, compressedSize);
+            ZSTDv05_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 6)
        case 6 :
-            return ZSTDv06_findFrameCompressedSize(src, compressedSize);
+            ZSTDv06_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 7)
        case 7 :
-            return ZSTDv07_findFrameCompressedSize(src, compressedSize);
+            ZSTDv07_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
        default :
-            return ERROR(prefix_unknown);
+            frameSizeInfo.compressedSize = ERROR(prefix_unknown);
+            frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+            break;
    }
+    if (!ZSTD_isError(frameSizeInfo.compressedSize) && frameSizeInfo.compressedSize > srcSize) {
+        frameSizeInfo.compressedSize = ERROR(srcSize_wrong);
+        frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+    }
+    return frameSizeInfo;
+}
+
+MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo frameSizeInfo = ZSTD_findFrameSizeInfoLegacy(src, srcSize);
+    return frameSizeInfo.compressedSize;
 }

 MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
@@ -1073,99 +1073,102 @@ static size_t HUF_decompress_usingDTable(   /* -3% slower when non static */
    const void* cSrc, size_t cSrcSize,
    const U16* DTable)
 {
-    BYTE* const ostart = (BYTE*) dst;
-    BYTE* op = ostart;
-    BYTE* const omax = op + maxDstSize;
-    BYTE* const olimit = omax-15;
-
-    const void* ptr = DTable;
-    const HUF_DElt* const dt = (const HUF_DElt*)(ptr)+1;
-    const U32 dtLog = DTable[0];
-    size_t errorCode;
-    U32 reloadStatus;
-
-    /* Init */
-
-    const U16* jumpTable = (const U16*)cSrc;
-    const size_t length1 = FSE_readLE16(jumpTable);
-    const size_t length2 = FSE_readLE16(jumpTable+1);
-    const size_t length3 = FSE_readLE16(jumpTable+2);
-    const size_t length4 = cSrcSize - 6 - length1 - length2 - length3;   // check coherency !!
-    const char* const start1 = (const char*)(cSrc) + 6;
-    const char* const start2 = start1 + length1;
-    const char* const start3 = start2 + length2;
-    const char* const start4 = start3 + length3;
-    FSE_DStream_t bitD1, bitD2, bitD3, bitD4;
-
-    if (length1+length2+length3+6 >= cSrcSize) return (size_t)-FSE_ERROR_srcSize_wrong;
-
-    errorCode = FSE_initDStream(&bitD1, start1, length1);
-    if (FSE_isError(errorCode)) return errorCode;
-    errorCode = FSE_initDStream(&bitD2, start2, length2);
-    if (FSE_isError(errorCode)) return errorCode;
-    errorCode = FSE_initDStream(&bitD3, start3, length3);
-    if (FSE_isError(errorCode)) return errorCode;
-    errorCode = FSE_initDStream(&bitD4, start4, length4);
-    if (FSE_isError(errorCode)) return errorCode;
-
-    reloadStatus=FSE_reloadDStream(&bitD2);
-
-    /* 16 symbols per loop */
-    for ( ; (reloadStatus<FSE_DStream_completed) && (op<olimit);  /* D2-3-4 are supposed to be synchronized and finish together */
-        op+=16, reloadStatus = FSE_reloadDStream(&bitD2) | FSE_reloadDStream(&bitD3) | FSE_reloadDStream(&bitD4), FSE_reloadDStream(&bitD1))
+    if (cSrcSize < 6) return (size_t)-FSE_ERROR_srcSize_wrong;
    {
-#define HUF_DECODE_SYMBOL_0(n, Dstream) \
-        op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog);
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* op = ostart;
+        BYTE* const omax = op + maxDstSize;
+        BYTE* const olimit = omax-15;

-#define HUF_DECODE_SYMBOL_1(n, Dstream) \
-        op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog); \
-        if (FSE_32bits() && (HUF_MAX_TABLELOG>12)) FSE_reloadDStream(&Dstream)
+        const void* ptr = DTable;
+        const HUF_DElt* const dt = (const HUF_DElt*)(ptr)+1;
+        const U32 dtLog = DTable[0];
+        size_t errorCode;
+        U32 reloadStatus;

-#define HUF_DECODE_SYMBOL_2(n, Dstream) \
-        op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog); \
-        if (FSE_32bits()) FSE_reloadDStream(&Dstream)
+        /* Init */

-        HUF_DECODE_SYMBOL_1( 0, bitD1);
-        HUF_DECODE_SYMBOL_1( 1, bitD2);
-        HUF_DECODE_SYMBOL_1( 2, bitD3);
-        HUF_DECODE_SYMBOL_1( 3, bitD4);
-        HUF_DECODE_SYMBOL_2( 4, bitD1);
-        HUF_DECODE_SYMBOL_2( 5, bitD2);
-        HUF_DECODE_SYMBOL_2( 6, bitD3);
-        HUF_DECODE_SYMBOL_2( 7, bitD4);
-        HUF_DECODE_SYMBOL_1( 8, bitD1);
-        HUF_DECODE_SYMBOL_1( 9, bitD2);
-        HUF_DECODE_SYMBOL_1(10, bitD3);
-        HUF_DECODE_SYMBOL_1(11, bitD4);
-        HUF_DECODE_SYMBOL_0(12, bitD1);
-        HUF_DECODE_SYMBOL_0(13, bitD2);
-        HUF_DECODE_SYMBOL_0(14, bitD3);
-        HUF_DECODE_SYMBOL_0(15, bitD4);
-    }
+        const U16* jumpTable = (const U16*)cSrc;
+        const size_t length1 = FSE_readLE16(jumpTable);
+        const size_t length2 = FSE_readLE16(jumpTable+1);
+        const size_t length3 = FSE_readLE16(jumpTable+2);
+        const size_t length4 = cSrcSize - 6 - length1 - length2 - length3;   // check coherency !!
+        const char* const start1 = (const char*)(cSrc) + 6;
+        const char* const start2 = start1 + length1;
+        const char* const start3 = start2 + length2;
+        const char* const start4 = start3 + length3;
+        FSE_DStream_t bitD1, bitD2, bitD3, bitD4;

-    if (reloadStatus!=FSE_DStream_completed)   /* not complete : some bitStream might be FSE_DStream_unfinished */
-        return (size_t)-FSE_ERROR_corruptionDetected;
+        if (length1+length2+length3+6 >= cSrcSize) return (size_t)-FSE_ERROR_srcSize_wrong;

-    /* tail */
-    {
-        // bitTail = bitD1;   // *much* slower : -20% !??!
-        FSE_DStream_t bitTail;
-        bitTail.ptr = bitD1.ptr;
-        bitTail.bitsConsumed = bitD1.bitsConsumed;
-        bitTail.bitContainer = bitD1.bitContainer;   // required in case of FSE_DStream_endOfBuffer
-        bitTail.start = start1;
-        for ( ; (FSE_reloadDStream(&bitTail) < FSE_DStream_completed) && (op<omax) ; op++)
+        errorCode = FSE_initDStream(&bitD1, start1, length1);
+        if (FSE_isError(errorCode)) return errorCode;
+        errorCode = FSE_initDStream(&bitD2, start2, length2);
+        if (FSE_isError(errorCode)) return errorCode;
+        errorCode = FSE_initDStream(&bitD3, start3, length3);
+        if (FSE_isError(errorCode)) return errorCode;
+        errorCode = FSE_initDStream(&bitD4, start4, length4);
+        if (FSE_isError(errorCode)) return errorCode;
+
+        reloadStatus=FSE_reloadDStream(&bitD2);
+
+        /* 16 symbols per loop */
+        for ( ; (reloadStatus<FSE_DStream_completed) && (op<olimit);  /* D2-3-4 are supposed to be synchronized and finish together */
+            op+=16, reloadStatus = FSE_reloadDStream(&bitD2) | FSE_reloadDStream(&bitD3) | FSE_reloadDStream(&bitD4), FSE_reloadDStream(&bitD1))
        {
-            HUF_DECODE_SYMBOL_0(0, bitTail);
+    #define HUF_DECODE_SYMBOL_0(n, Dstream) \
+            op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog);
+
+    #define HUF_DECODE_SYMBOL_1(n, Dstream) \
+            op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog); \
+            if (FSE_32bits() && (HUF_MAX_TABLELOG>12)) FSE_reloadDStream(&Dstream)
+
+    #define HUF_DECODE_SYMBOL_2(n, Dstream) \
+            op[n] = HUF_decodeSymbol(&Dstream, dt, dtLog); \
+            if (FSE_32bits()) FSE_reloadDStream(&Dstream)
+
+            HUF_DECODE_SYMBOL_1( 0, bitD1);
+            HUF_DECODE_SYMBOL_1( 1, bitD2);
+            HUF_DECODE_SYMBOL_1( 2, bitD3);
+            HUF_DECODE_SYMBOL_1( 3, bitD4);
+            HUF_DECODE_SYMBOL_2( 4, bitD1);
+            HUF_DECODE_SYMBOL_2( 5, bitD2);
+            HUF_DECODE_SYMBOL_2( 6, bitD3);
+            HUF_DECODE_SYMBOL_2( 7, bitD4);
+            HUF_DECODE_SYMBOL_1( 8, bitD1);
+            HUF_DECODE_SYMBOL_1( 9, bitD2);
+            HUF_DECODE_SYMBOL_1(10, bitD3);
+            HUF_DECODE_SYMBOL_1(11, bitD4);
+            HUF_DECODE_SYMBOL_0(12, bitD1);
+            HUF_DECODE_SYMBOL_0(13, bitD2);
+            HUF_DECODE_SYMBOL_0(14, bitD3);
+            HUF_DECODE_SYMBOL_0(15, bitD4);
        }

-        if (FSE_endOfDStream(&bitTail))
-            return op-ostart;
+        if (reloadStatus!=FSE_DStream_completed)   /* not complete : some bitStream might be FSE_DStream_unfinished */
+            return (size_t)-FSE_ERROR_corruptionDetected;
+
+        /* tail */
+        {
+            // bitTail = bitD1;   // *much* slower : -20% !??!
+            FSE_DStream_t bitTail;
+            bitTail.ptr = bitD1.ptr;
+            bitTail.bitsConsumed = bitD1.bitsConsumed;
+            bitTail.bitContainer = bitD1.bitContainer;   // required in case of FSE_DStream_endOfBuffer
+            bitTail.start = start1;
+            for ( ; (FSE_reloadDStream(&bitTail) < FSE_DStream_completed) && (op<omax) ; op++)
+            {
+                HUF_DECODE_SYMBOL_0(0, bitTail);
+            }
+
+            if (FSE_endOfDStream(&bitTail))
+                return op-ostart;
+        }
+
+        if (op==omax) return (size_t)-FSE_ERROR_dstSize_tooSmall;   /* dst buffer is full, but cSrc unfinished */
+
+        return (size_t)-FSE_ERROR_corruptionDetected;
    }
-
-    if (op==omax) return (size_t)-FSE_ERROR_dstSize_tooSmall;   /* dst buffer is full, but cSrc unfinished */
-
-    return (size_t)-FSE_ERROR_corruptionDetected;
 }


@@ -1336,6 +1339,8 @@ static const U32 ZSTD_magicNumber = 0xFD2FB51E;   /* 3rd version : seqNb header
 #define LITERAL_NOENTROPY 63
 #define COMMAND_NOENTROPY 7   /* to remove */

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const size_t ZSTD_blockHeaderSize = 3;
 static const size_t ZSTD_frameHeaderSize = 4;

@@ -1353,8 +1358,6 @@ static unsigned ZSTD_isLittleEndian(void)

 static U16    ZSTD_read16(const void* p) { U16 r; memcpy(&r, p, sizeof(r)); return r; }

-static U32    ZSTD_read32(const void* p) { U32 r; memcpy(&r, p, sizeof(r)); return r; }
-
 static void   ZSTD_copy4(void* dst, const void* src) { memcpy(dst, src, 4); }

 static void   ZSTD_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
@@ -1379,16 +1382,9 @@ static U16 ZSTD_readLE16(const void* memPtr)
    }
 }

-
-static U32 ZSTD_readLE32(const void* memPtr)
+static U32 ZSTD_readLE24(const void* memPtr)
 {
-    if (ZSTD_isLittleEndian())
-        return ZSTD_read32(memPtr);
-    else
-    {
-        const BYTE* p = (const BYTE*)memPtr;
-        return (U32)((U32)p[0] + ((U32)p[1]<<8) + ((U32)p[2]<<16) + ((U32)p[3]<<24));
-    }
+    return ZSTD_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
 }

 static U32 ZSTD_readBE32(const void* memPtr)
@@ -1702,13 +1698,13 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    seqState->prevOffset = seq->offset;
    if (litLength == MaxLL)
    {
-        U32 add = dumps<de ? *dumps++ : 0;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) litLength += add;
        else
        {
            if (dumps<=(de-3))
            {
-                litLength = ZSTD_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+                litLength = ZSTD_readLE24(dumps);
                dumps += 3;
            }
        }
@@ -1730,13 +1726,13 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
    if (matchLength == MaxML)
    {
-        U32 add = dumps<de ? *dumps++ : 0;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) matchLength += add;
        else
        {
            if (dumps<=(de-3))
            {
-                matchLength = ZSTD_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+                matchLength = ZSTD_readLE24(dumps);
                dumps += 3;
            }
        }
@@ -1757,7 +1753,7 @@ static size_t ZSTD_execSequence(BYTE* op,
                                BYTE* const base, BYTE* const oend)
 {
    static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* substracted */
+    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* subtracted */
    const BYTE* const ostart = op;
    const size_t litLength = sequence.litLength;
    BYTE* const endMatch = op + litLength + sequence.matchLength;    /* risk : address space overflow (32-bits) */
@@ -1999,36 +1995,59 @@ size_t ZSTDv01_decompress(void* dst, size_t maxDstSize, const void* src, size_t
    return ZSTDv01_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
 }

-size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    U32 magicNumber;
    blockProperties_t blockProperties;

    /* Frame Header */
-    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
    magicNumber = ZSTD_readBE32(src);
-    if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
+    if (magicNumber != ZSTD_magicNumber) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
    ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;

    /* Loop on each block */
    while (1)
    {
        size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTDv01_isError(blockSize)) return blockSize;
+        if (ZSTDv01_isError(blockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, blockSize);
+            return;
+        }

        ip += ZSTD_blockHeaderSize;
        remainingSize -= ZSTD_blockHeaderSize;
-        if (blockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (blockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (blockSize == 0) break;   /* bt_end */

        ip += blockSize;
        remainingSize -= blockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }

 /*******************************
@@ -35,13 +35,18 @@ ZSTDv01_decompress() : decompress ZSTD frames compliant with v0.1.x format
 size_t ZSTDv01_decompress( void* dst, size_t maxOriginalSize,
                     const void* src, size_t compressedSize);

-/**
-ZSTDv01_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.1.x format
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv01_isError())
-*/
-size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t compressedSize);
+ /**
+ ZSTDv01_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.1.x format
+     srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+     cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                 or an error code if it fails (which can be tested using ZSTDv01_isError())
+     dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                 or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+     note : assumes `cSize` and `dBound` are _not_ NULL.
+ */
+void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                     size_t* cSize, unsigned long long* dBound);

 /**
 ZSTDv01_isError() : tells if the result of ZSTDv01_decompress() is an error
@@ -217,6 +217,11 @@ MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
    }
 }

+MEM_STATIC U32 MEM_readLE24(const void* memPtr)
+{
+    return MEM_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
+}
+
 MEM_STATIC U32 MEM_readLE32(const void* memPtr)
 {
    if (MEM_isLittleEndian())
@@ -2728,6 +2733,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_
 #define LITERAL_NOENTROPY 63
 #define COMMAND_NOENTROPY 7   /* to remove */

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const size_t ZSTD_blockHeaderSize = 3;
 static const size_t ZSTD_frameHeaderSize = 4;

@@ -3041,11 +3048,11 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    seqState->prevOffset = seq->offset;
    if (litLength == MaxLL)
    {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) litLength += add;
-        else
+        else if (dumps + 3 <= de)
        {
-            litLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+            litLength = MEM_readLE24(dumps);
            dumps += 3;
        }
        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
@@ -3071,11 +3078,11 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
    if (matchLength == MaxML)
    {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) matchLength += add;
-        else
+        else if (dumps + 3 <= de)
        {
-            matchLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+            matchLength = MEM_readLE24(dumps);
            dumps += 3;
        }
        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
@@ -3096,7 +3103,7 @@ static size_t ZSTD_execSequence(BYTE* op,
                                BYTE* const base, BYTE* const oend)
 {
    static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* substracted */
+    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* subtracted */
    const BYTE* const ostart = op;
    BYTE* const oLitEnd = op + sequence.litLength;
    BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength;   /* risk : address space overflow (32-bits) */
@@ -3312,37 +3319,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz
    return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
 }

-static size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
 {
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}

+void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
+{
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    U32 magicNumber;
    blockProperties_t blockProperties;

    /* Frame Header */
-    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
    magicNumber = MEM_readLE32(src);
-    if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
+    if (magicNumber != ZSTD_magicNumber) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
    ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;

    /* Loop on each block */
    while (1)
    {
        size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTD_isError(cBlockSize)) return cBlockSize;
+        if (ZSTD_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTD_blockHeaderSize;
        remainingSize -= ZSTD_blockHeaderSize;
-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (cBlockSize == 0) break;   /* bt_end */

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }

 /*******************************
@@ -3458,11 +3487,6 @@ size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize,
    return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize);
 }

-size_t ZSTDv02_findFrameCompressedSize(const void *src, size_t compressedSize)
-{
-    return ZSTD_findFrameCompressedSize(src, compressedSize);
-}
-
 ZSTDv02_Dctx* ZSTDv02_createDCtx(void)
 {
    return (ZSTDv02_Dctx*)ZSTD_createDCtx();
@@ -35,13 +35,18 @@ ZSTDv02_decompress() : decompress ZSTD frames compliant with v0.2.x format
 size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize,
                     const void* src, size_t compressedSize);

-/**
-ZSTDv02_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.2.x format
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv02_isError())
-*/
-size_t ZSTDv02_findFrameCompressedSize(const void* src, size_t compressedSize);
+ /**
+ ZSTDv02_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.2.x format
+     srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+     cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                 or an error code if it fails (which can be tested using ZSTDv01_isError())
+     dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                 or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
+ */
+void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                     size_t* cSize, unsigned long long* dBound);

 /**
 ZSTDv02_isError() : tells if the result of ZSTDv02_decompress() is an error
@@ -219,6 +219,11 @@ MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
    }
 }

+MEM_STATIC U32 MEM_readLE24(const void* memPtr)
+{
+    return MEM_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
+}
+
 MEM_STATIC U32 MEM_readLE32(const void* memPtr)
 {
    if (MEM_isLittleEndian())
@@ -2369,6 +2374,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_
 #define LITERAL_NOENTROPY 63
 #define COMMAND_NOENTROPY 7   /* to remove */

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const size_t ZSTD_blockHeaderSize = 3;
 static const size_t ZSTD_frameHeaderSize = 4;

@@ -2682,11 +2689,11 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    seqState->prevOffset = seq->offset;
    if (litLength == MaxLL)
    {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) litLength += add;
-        else
+        else if (dumps + 3 <= de)
        {
-            litLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+            litLength = MEM_readLE24(dumps);
            dumps += 3;
        }
        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
@@ -2712,11 +2719,11 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
    if (matchLength == MaxML)
    {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) matchLength += add;
-        else
+        else if (dumps + 3 <= de)
        {
-            matchLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+            matchLength = MEM_readLE24(dumps);
            dumps += 3;
        }
        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
@@ -2737,7 +2744,7 @@ static size_t ZSTD_execSequence(BYTE* op,
                                BYTE* const base, BYTE* const oend)
 {
    static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* substracted */
+    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* subtracted */
    const BYTE* const ostart = op;
    BYTE* const oLitEnd = op + sequence.litLength;
    BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength;   /* risk : address space overflow (32-bits) */
@@ -2953,36 +2960,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz
    return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
 }

-static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+MEM_STATIC void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    U32 magicNumber;
    blockProperties_t blockProperties;

    /* Frame Header */
-    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
    magicNumber = MEM_readLE32(src);
-    if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
+    if (magicNumber != ZSTD_magicNumber) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
    ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;

    /* Loop on each block */
    while (1)
    {
        size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTD_isError(cBlockSize)) return cBlockSize;
+        if (ZSTD_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTD_blockHeaderSize;
        remainingSize -= ZSTD_blockHeaderSize;
-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (cBlockSize == 0) break;   /* bt_end */

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }


@@ -3099,11 +3129,6 @@ size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize,
    return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize);
 }

-size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t srcSize)
-{
-    return ZSTD_findFrameCompressedSize(src, srcSize);
-}
-
 ZSTDv03_Dctx* ZSTDv03_createDCtx(void)
 {
    return (ZSTDv03_Dctx*)ZSTD_createDCtx();
@@ -35,13 +35,18 @@ ZSTDv03_decompress() : decompress ZSTD frames compliant with v0.3.x format
 size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize,
                     const void* src, size_t compressedSize);

-/**
-ZSTDv03_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.3.x format
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv03_isError())
-*/
-size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t compressedSize);
+ /**
+ ZSTDv03_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.3.x format
+     srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+     cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                 or an error code if it fails (which can be tested using ZSTDv01_isError())
+     dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                 or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
+ */
+ void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                      size_t* cSize, unsigned long long* dBound);

    /**
 ZSTDv03_isError() : tells if the result of ZSTDv03_decompress() is an error
@@ -189,6 +189,11 @@ MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
    }
 }

+MEM_STATIC U32 MEM_readLE24(const void* memPtr)
+{
+    return MEM_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
+}
+
 MEM_STATIC U32 MEM_readLE32(const void* memPtr)
 {
    if (MEM_isLittleEndian())
@@ -373,6 +378,8 @@ static const size_t ZSTD_frameHeaderSize_min = 5;
 #define MIN_SEQUENCES_SIZE (2 /*seqNb*/ + 2 /*dumps*/ + 3 /*seqTables*/ + 1 /*bitStream*/)
 #define MIN_CBLOCK_SIZE (3 /*litCSize*/ + MIN_SEQUENCES_SIZE)

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;


@@ -2806,13 +2813,12 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    litLength = FSE_decodeSymbol(&(seqState->stateLL), &(seqState->DStream));
    prevOffset = litLength ? seq->offset : seqState->prevOffset;
    if (litLength == MaxLL) {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) litLength += add;
-        else {
-            litLength = dumps[0] + (dumps[1]<<8) + (dumps[2]<<16);
+        else if (dumps + 3 <= de) {
+            litLength = MEM_readLE24(dumps);
            dumps += 3;
        }
-        if (dumps > de) { litLength = MaxLL+255; }  /* late correction, to avoid using uninitialized memory */
        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
    }

@@ -2835,13 +2841,12 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
    /* MatchLength */
    matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
    if (matchLength == MaxML) {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) matchLength += add;
-        else {
-            matchLength = dumps[0] + (dumps[1]<<8) + (dumps[2]<<16);
+        else if (dumps + 3 <= de){
+            matchLength = MEM_readLE24(dumps);
            dumps += 3;
        }
-        if (dumps > de) { matchLength = MaxML+255; }  /* late correction, to avoid using uninitialized memory */
        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
    }
    matchLength += MINMATCH;
@@ -2860,7 +2865,7 @@ static size_t ZSTD_execSequence(BYTE* op,
                                const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd)
 {
    static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };   /* added */
-    static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* substracted */
+    static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* subtracted */
    BYTE* const oLitEnd = op + sequence.litLength;
    const size_t sequenceLength = sequence.litLength + sequence.matchLength;
    BYTE* const oMatchEnd = op + sequenceLength;   /* risk : address space overflow (32-bits) */
@@ -3119,34 +3124,57 @@ static size_t ZSTD_decompress_usingDict(ZSTD_DCtx* ctx,
    return op-ostart;
 }

-static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    blockProperties_t blockProperties;

    /* Frame Header */
-    if (srcSize < ZSTD_frameHeaderSize_min) return ERROR(srcSize_wrong);
-    if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) return ERROR(prefix_unknown);
+    if (srcSize < ZSTD_frameHeaderSize_min) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
+    if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
    ip += ZSTD_frameHeaderSize_min; remainingSize -= ZSTD_frameHeaderSize_min;

    /* Loop on each block */
    while (1)
    {
        size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTD_isError(cBlockSize)) return cBlockSize;
+        if (ZSTD_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTD_blockHeaderSize;
        remainingSize -= ZSTD_blockHeaderSize;
-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (cBlockSize == 0) break;   /* bt_end */

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }

 /* ******************************
@@ -3578,11 +3606,6 @@ size_t ZSTDv04_decompress(void* dst, size_t maxDstSize, const void* src, size_t
 #endif
 }

-size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t srcSize)
-{
-    return ZSTD_findFrameCompressedSize(src, srcSize);
-}
-
 size_t ZSTDv04_resetDCtx(ZSTDv04_Dctx* dctx) { return ZSTD_resetDCtx(dctx); }

 size_t ZSTDv04_nextSrcSizeToDecompress(ZSTDv04_Dctx* dctx)
@@ -35,13 +35,18 @@ ZSTDv04_decompress() : decompress ZSTD frames compliant with v0.4.x format
 size_t ZSTDv04_decompress( void* dst, size_t maxOriginalSize,
                     const void* src, size_t compressedSize);

-/**
-ZSTDv04_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.4.x format
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv04_isError())
-*/
-size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t compressedSize);
+ /**
+ ZSTDv04_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.4.x format
+     srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+     cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                 or an error code if it fails (which can be tested using ZSTDv01_isError())
+     dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                 or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
+ */
+ void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                      size_t* cSize, unsigned long long* dBound);

 /**
 ZSTDv04_isError() : tells if the result of ZSTDv04_decompress() is an error
@@ -491,6 +491,8 @@ static const size_t ZSTDv05_frameHeaderSize_min = 5;

 #define WILDCOPY_OVERLENGTH 8

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;


@@ -1996,91 +1998,92 @@ size_t HUFv05_decompress4X2_usingDTable(
    const void* cSrc, size_t cSrcSize,
    const U16* DTable)
 {
-    const BYTE* const istart = (const BYTE*) cSrc;
-    BYTE* const ostart = (BYTE*) dst;
-    BYTE* const oend = ostart + dstSize;
-    const void* const dtPtr = DTable;
-    const HUFv05_DEltX2* const dt = ((const HUFv05_DEltX2*)dtPtr) +1;
-    const U32 dtLog = DTable[0];
-    size_t errorCode;
-
-    /* Init */
-    BITv05_DStream_t bitD1;
-    BITv05_DStream_t bitD2;
-    BITv05_DStream_t bitD3;
-    BITv05_DStream_t bitD4;
-    const size_t length1 = MEM_readLE16(istart);
-    const size_t length2 = MEM_readLE16(istart+2);
-    const size_t length3 = MEM_readLE16(istart+4);
-    size_t length4;
-    const BYTE* const istart1 = istart + 6;  /* jumpTable */
-    const BYTE* const istart2 = istart1 + length1;
-    const BYTE* const istart3 = istart2 + length2;
-    const BYTE* const istart4 = istart3 + length3;
-    const size_t segmentSize = (dstSize+3) / 4;
-    BYTE* const opStart2 = ostart + segmentSize;
-    BYTE* const opStart3 = opStart2 + segmentSize;
-    BYTE* const opStart4 = opStart3 + segmentSize;
-    BYTE* op1 = ostart;
-    BYTE* op2 = opStart2;
-    BYTE* op3 = opStart3;
-    BYTE* op4 = opStart4;
-    U32 endSignal;
-
    /* Check */
    if (cSrcSize < 10) return ERROR(corruption_detected);   /* strict minimum : jump table + 1 byte per stream */
+    {
+        const BYTE* const istart = (const BYTE*) cSrc;
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        const void* const dtPtr = DTable;
+        const HUFv05_DEltX2* const dt = ((const HUFv05_DEltX2*)dtPtr) +1;
+        const U32 dtLog = DTable[0];
+        size_t errorCode;

-    length4 = cSrcSize - (length1 + length2 + length3 + 6);
-    if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
-    errorCode = BITv05_initDStream(&bitD1, istart1, length1);
-    if (HUFv05_isError(errorCode)) return errorCode;
-    errorCode = BITv05_initDStream(&bitD2, istart2, length2);
-    if (HUFv05_isError(errorCode)) return errorCode;
-    errorCode = BITv05_initDStream(&bitD3, istart3, length3);
-    if (HUFv05_isError(errorCode)) return errorCode;
-    errorCode = BITv05_initDStream(&bitD4, istart4, length4);
-    if (HUFv05_isError(errorCode)) return errorCode;
+        /* Init */
+        BITv05_DStream_t bitD1;
+        BITv05_DStream_t bitD2;
+        BITv05_DStream_t bitD3;
+        BITv05_DStream_t bitD4;
+        const size_t length1 = MEM_readLE16(istart);
+        const size_t length2 = MEM_readLE16(istart+2);
+        const size_t length3 = MEM_readLE16(istart+4);
+        size_t length4;
+        const BYTE* const istart1 = istart + 6;  /* jumpTable */
+        const BYTE* const istart2 = istart1 + length1;
+        const BYTE* const istart3 = istart2 + length2;
+        const BYTE* const istart4 = istart3 + length3;
+        const size_t segmentSize = (dstSize+3) / 4;
+        BYTE* const opStart2 = ostart + segmentSize;
+        BYTE* const opStart3 = opStart2 + segmentSize;
+        BYTE* const opStart4 = opStart3 + segmentSize;
+        BYTE* op1 = ostart;
+        BYTE* op2 = opStart2;
+        BYTE* op3 = opStart3;
+        BYTE* op4 = opStart4;
+        U32 endSignal;

-    /* 16-32 symbols per loop (4-8 symbols per stream) */
-    endSignal = BITv05_reloadDStream(&bitD1) | BITv05_reloadDStream(&bitD2) | BITv05_reloadDStream(&bitD3) | BITv05_reloadDStream(&bitD4);
-    for ( ; (endSignal==BITv05_DStream_unfinished) && (op4<(oend-7)) ; ) {
-        HUFv05_DECODE_SYMBOLX2_2(op1, &bitD1);
-        HUFv05_DECODE_SYMBOLX2_2(op2, &bitD2);
-        HUFv05_DECODE_SYMBOLX2_2(op3, &bitD3);
-        HUFv05_DECODE_SYMBOLX2_2(op4, &bitD4);
-        HUFv05_DECODE_SYMBOLX2_1(op1, &bitD1);
-        HUFv05_DECODE_SYMBOLX2_1(op2, &bitD2);
-        HUFv05_DECODE_SYMBOLX2_1(op3, &bitD3);
-        HUFv05_DECODE_SYMBOLX2_1(op4, &bitD4);
-        HUFv05_DECODE_SYMBOLX2_2(op1, &bitD1);
-        HUFv05_DECODE_SYMBOLX2_2(op2, &bitD2);
-        HUFv05_DECODE_SYMBOLX2_2(op3, &bitD3);
-        HUFv05_DECODE_SYMBOLX2_2(op4, &bitD4);
-        HUFv05_DECODE_SYMBOLX2_0(op1, &bitD1);
-        HUFv05_DECODE_SYMBOLX2_0(op2, &bitD2);
-        HUFv05_DECODE_SYMBOLX2_0(op3, &bitD3);
-        HUFv05_DECODE_SYMBOLX2_0(op4, &bitD4);
+        length4 = cSrcSize - (length1 + length2 + length3 + 6);
+        if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
+        errorCode = BITv05_initDStream(&bitD1, istart1, length1);
+        if (HUFv05_isError(errorCode)) return errorCode;
+        errorCode = BITv05_initDStream(&bitD2, istart2, length2);
+        if (HUFv05_isError(errorCode)) return errorCode;
+        errorCode = BITv05_initDStream(&bitD3, istart3, length3);
+        if (HUFv05_isError(errorCode)) return errorCode;
+        errorCode = BITv05_initDStream(&bitD4, istart4, length4);
+        if (HUFv05_isError(errorCode)) return errorCode;
+
+        /* 16-32 symbols per loop (4-8 symbols per stream) */
        endSignal = BITv05_reloadDStream(&bitD1) | BITv05_reloadDStream(&bitD2) | BITv05_reloadDStream(&bitD3) | BITv05_reloadDStream(&bitD4);
+        for ( ; (endSignal==BITv05_DStream_unfinished) && (op4<(oend-7)) ; ) {
+            HUFv05_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUFv05_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUFv05_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUFv05_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUFv05_DECODE_SYMBOLX2_1(op1, &bitD1);
+            HUFv05_DECODE_SYMBOLX2_1(op2, &bitD2);
+            HUFv05_DECODE_SYMBOLX2_1(op3, &bitD3);
+            HUFv05_DECODE_SYMBOLX2_1(op4, &bitD4);
+            HUFv05_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUFv05_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUFv05_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUFv05_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUFv05_DECODE_SYMBOLX2_0(op1, &bitD1);
+            HUFv05_DECODE_SYMBOLX2_0(op2, &bitD2);
+            HUFv05_DECODE_SYMBOLX2_0(op3, &bitD3);
+            HUFv05_DECODE_SYMBOLX2_0(op4, &bitD4);
+            endSignal = BITv05_reloadDStream(&bitD1) | BITv05_reloadDStream(&bitD2) | BITv05_reloadDStream(&bitD3) | BITv05_reloadDStream(&bitD4);
+        }
+
+        /* check corruption */
+        if (op1 > opStart2) return ERROR(corruption_detected);
+        if (op2 > opStart3) return ERROR(corruption_detected);
+        if (op3 > opStart4) return ERROR(corruption_detected);
+        /* note : op4 supposed already verified within main loop */
+
+        /* finish bitStreams one by one */
+        HUFv05_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
+        HUFv05_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
+        HUFv05_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
+        HUFv05_decodeStreamX2(op4, &bitD4, oend,     dt, dtLog);
+
+        /* check */
+        endSignal = BITv05_endOfDStream(&bitD1) & BITv05_endOfDStream(&bitD2) & BITv05_endOfDStream(&bitD3) & BITv05_endOfDStream(&bitD4);
+        if (!endSignal) return ERROR(corruption_detected);
+
+        /* decoded size */
+        return dstSize;
    }
-
-    /* check corruption */
-    if (op1 > opStart2) return ERROR(corruption_detected);
-    if (op2 > opStart3) return ERROR(corruption_detected);
-    if (op3 > opStart4) return ERROR(corruption_detected);
-    /* note : op4 supposed already verified within main loop */
-
-    /* finish bitStreams one by one */
-    HUFv05_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
-    HUFv05_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
-    HUFv05_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
-    HUFv05_decodeStreamX2(op4, &bitD4, oend,     dt, dtLog);
-
-    /* check */
-    endSignal = BITv05_endOfDStream(&bitD1) & BITv05_endOfDStream(&bitD2) & BITv05_endOfDStream(&bitD3) & BITv05_endOfDStream(&bitD4);
-    if (!endSignal) return ERROR(corruption_detected);
-
-    /* decoded size */
-    return dstSize;
 }


@@ -3148,14 +3151,17 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
    litLength = FSEv05_peakSymbol(&(seqState->stateLL));
    prevOffset = litLength ? seq->offset : seqState->prevOffset;
    if (litLength == MaxLL) {
-        U32 add = *dumps++;
+        const U32 add = *dumps++;
        if (add < 255) litLength += add;
-        else {
-            litLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no risk : dumps is always followed by seq tables > 1 byte */
-            if (litLength&1) litLength>>=1, dumps += 3;
-            else litLength = (U16)(litLength)>>1, dumps += 2;
+        else if (dumps + 2 <= de) {
+            litLength = MEM_readLE16(dumps);
+            dumps += 2;
+            if ((litLength & 1) && dumps < de) {
+                litLength += *dumps << 16;
+                dumps += 1;
+            }
+            litLength>>=1;
        }
-        if (dumps > de) { litLength = MaxLL+255; }  /* late correction, to avoid using uninitialized memory */
        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
    }

@@ -3182,14 +3188,17 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
    /* MatchLength */
    matchLength = FSEv05_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
    if (matchLength == MaxML) {
-        U32 add = *dumps++;
+        const U32 add = dumps<de ? *dumps++ : 0;
        if (add < 255) matchLength += add;
-        else {
-            matchLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
-            if (matchLength&1) matchLength>>=1, dumps += 3;
-            else matchLength = (U16)(matchLength)>>1, dumps += 2;
+        else if (dumps + 2 <= de) {
+            matchLength = MEM_readLE16(dumps);
+            dumps += 2;
+            if ((matchLength & 1) && dumps < de) {
+                matchLength += *dumps << 16;
+                dumps += 1;
+            }
+            matchLength >>= 1;
        }
-        if (dumps > de) { matchLength = MaxML+255; }  /* late correction, to avoid using uninitialized memory */
        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
    }
    matchLength += MINMATCH;
@@ -3217,7 +3226,7 @@ static size_t ZSTDv05_execSequence(BYTE* op,
                                const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd)
 {
    static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };   /* added */
-    static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* substracted */
+    static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* subtracted */
    BYTE* const oLitEnd = op + sequence.litLength;
    const size_t sequenceLength = sequence.litLength + sequence.matchLength;
    BYTE* const oMatchEnd = op + sequenceLength;   /* risk : address space overflow (32-bits) */
@@ -3508,34 +3517,57 @@ size_t ZSTDv05_decompress(void* dst, size_t maxDstSize, const void* src, size_t
 #endif
 }

-size_t ZSTDv05_findFrameCompressedSize(const void *src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    blockProperties_t blockProperties;

    /* Frame Header */
-    if (srcSize < ZSTDv05_frameHeaderSize_min) return ERROR(srcSize_wrong);
-    if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) return ERROR(prefix_unknown);
+    if (srcSize < ZSTDv05_frameHeaderSize_min) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
+    if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
    ip += ZSTDv05_frameHeaderSize_min; remainingSize -= ZSTDv05_frameHeaderSize_min;

    /* Loop on each block */
    while (1)
    {
        size_t cBlockSize = ZSTDv05_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTDv05_isError(cBlockSize)) return cBlockSize;
+        if (ZSTDv05_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTDv05_blockHeaderSize;
        remainingSize -= ZSTDv05_blockHeaderSize;
-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (cBlockSize == 0) break;   /* bt_end */

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }

 /* ******************************
@@ -33,13 +33,18 @@ extern "C" {
 size_t ZSTDv05_decompress( void* dst, size_t dstCapacity,
                     const void* src, size_t compressedSize);

-/**
-ZSTDv05_getFrameSrcSize() : get the source length of a ZSTD frame
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv05_isError())
-*/
-size_t ZSTDv05_findFrameCompressedSize(const void* src, size_t compressedSize);
+ /**
+ ZSTDv05_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.5.x format
+     srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+     cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                 or an error code if it fails (which can be tested using ZSTDv01_isError())
+     dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                 or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
+ */
+void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                     size_t* cSize, unsigned long long* dBound);

 /* *************************************
 *  Helper functions
@@ -506,6 +506,8 @@ typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;
 #define FSEv06_ENCODING_STATIC  2
 #define FSEv06_ENCODING_DYNAMIC 3

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
                                      1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12,
                                     13,14,15,16 };
@@ -3240,14 +3242,12 @@ static size_t ZSTDv06_decodeSeqHeaders(int* nbSeqPtr,
    }

    /* FSE table descriptors */
+    if (ip + 4 > iend) return ERROR(srcSize_wrong); /* min : header byte + all 3 are "raw", hence no header, but at least xxLog bits per type */
    {   U32 const LLtype  = *ip >> 6;
        U32 const Offtype = (*ip >> 4) & 3;
        U32 const MLtype  = (*ip >> 2) & 3;
        ip++;

-        /* check */
-        if (ip > iend-3) return ERROR(srcSize_wrong); /* min : all 3 are "raw", hence no header, but at least xxLog bits per type */
-
        /* Build DTables */
        {   size_t const bhSize = ZSTDv06_buildSeqTable(DTableLL, LLtype, MaxLL, LLFSELog, ip, iend-ip, LL_defaultNorm, LL_defaultNormLog, flagRepeatTable);
            if (ZSTDv06_isError(bhSize)) return ERROR(corruption_detected);
@@ -3406,7 +3406,7 @@ static size_t ZSTDv06_execSequence(BYTE* op,
    if (sequence.offset < 8) {
        /* close range match, overlap */
        static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };   /* added */
-        static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* substracted */
+        static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* subtracted */
        int const sub2 = dec64table[sequence.offset];
        op[0] = match[0];
        op[1] = match[1];
@@ -3654,36 +3654,62 @@ size_t ZSTDv06_decompress(void* dst, size_t dstCapacity, const void* src, size_t
 #endif
 }

-size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
    blockProperties_t blockProperties = { bt_compressed, 0 };

    /* Frame Header */
-    {   size_t const frameHeaderSize = ZSTDv06_frameHeaderSize(src, ZSTDv06_frameHeaderSize_min);
-        if (ZSTDv06_isError(frameHeaderSize)) return frameHeaderSize;
-        if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) return ERROR(prefix_unknown);
-        if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) return ERROR(srcSize_wrong);
+    {   size_t const frameHeaderSize = ZSTDv06_frameHeaderSize(src, srcSize);
+        if (ZSTDv06_isError(frameHeaderSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize);
+            return;
+        }
+        if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+            return;
+        }
+        if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }
        ip += frameHeaderSize; remainingSize -= frameHeaderSize;
    }

    /* Loop on each block */
    while (1) {
        size_t const cBlockSize = ZSTDv06_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTDv06_isError(cBlockSize)) return cBlockSize;
+        if (ZSTDv06_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTDv06_blockHeaderSize;
        remainingSize -= ZSTDv06_blockHeaderSize;
-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        if (cBlockSize == 0) break;   /* bt_end */

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * ZSTDv06_BLOCKSIZE_MAX;
 }

 /*_******************************
@@ -43,12 +43,17 @@ ZSTDLIBv06_API size_t ZSTDv06_decompress( void* dst, size_t dstCapacity,
                                    const void* src, size_t compressedSize);

 /**
-ZSTDv06_getFrameSrcSize() : get the source length of a ZSTD frame
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv06_isError())
+ZSTDv06_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.6.x format
+    srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+    cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                or an error code if it fails (which can be tested using ZSTDv01_isError())
+    dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
 */
-size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t compressedSize);
+void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                     size_t* cSize, unsigned long long* dBound);

 /* *************************************
 *  Helper functions
@@ -2740,6 +2740,8 @@ typedef enum { lbt_huffman, lbt_repeat, lbt_raw, lbt_rle } litBlockType_t;
 #define FSEv07_ENCODING_STATIC  2
 #define FSEv07_ENCODING_DYNAMIC 3

+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
                                      1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12,
                                     13,14,15,16 };
@@ -3468,14 +3470,12 @@ static size_t ZSTDv07_decodeSeqHeaders(int* nbSeqPtr,
    }

    /* FSE table descriptors */
+    if (ip + 4 > iend) return ERROR(srcSize_wrong); /* min : header byte + all 3 are "raw", hence no header, but at least xxLog bits per type */
    {   U32 const LLtype  = *ip >> 6;
        U32 const OFtype = (*ip >> 4) & 3;
        U32 const MLtype  = (*ip >> 2) & 3;
        ip++;

-        /* check */
-        if (ip > iend-3) return ERROR(srcSize_wrong); /* min : all 3 are "raw", hence no header, but at least xxLog bits per type */
-
        /* Build DTables */
        {   size_t const llhSize = ZSTDv07_buildSeqTable(DTableLL, LLtype, MaxLL, LLFSELog, ip, iend-ip, LL_defaultNorm, LL_defaultNormLog, flagRepeatTable);
            if (ZSTDv07_isError(llhSize)) return ERROR(corruption_detected);
@@ -3631,7 +3631,7 @@ size_t ZSTDv07_execSequence(BYTE* op,
    if (sequence.offset < 8) {
        /* close range match, overlap */
        static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };   /* added */
-        static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* substracted */
+        static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* subtracted */
        int const sub2 = dec64table[sequence.offset];
        op[0] = match[0];
        op[1] = match[1];
@@ -3895,19 +3895,40 @@ size_t ZSTDv07_decompress(void* dst, size_t dstCapacity, const void* src, size_t
 #endif
 }

-size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
    const BYTE* ip = (const BYTE*)src;
    size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;

    /* check */
-    if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong);
+    if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }

    /* Frame Header */
-    {   size_t const frameHeaderSize = ZSTDv07_frameHeaderSize(src, ZSTDv07_frameHeaderSize_min);
-        if (ZSTDv07_isError(frameHeaderSize)) return frameHeaderSize;
-        if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) return ERROR(prefix_unknown);
-        if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong);
+    {   size_t const frameHeaderSize = ZSTDv07_frameHeaderSize(src, srcSize);
+        if (ZSTDv07_isError(frameHeaderSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize);
+            return;
+        }
+        if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+            return;
+        }
+        if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }
        ip += frameHeaderSize; remainingSize -= frameHeaderSize;
    }

@@ -3915,20 +3936,28 @@ size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize)
    while (1) {
        blockProperties_t blockProperties;
        size_t const cBlockSize = ZSTDv07_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTDv07_isError(cBlockSize)) return cBlockSize;
+        if (ZSTDv07_isError(cBlockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
+            return;
+        }

        ip += ZSTDv07_blockHeaderSize;
        remainingSize -= ZSTDv07_blockHeaderSize;

        if (blockProperties.blockType == bt_end) break;

-        if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (cBlockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }

        ip += cBlockSize;
        remainingSize -= cBlockSize;
+        nbBlocks++;
    }

-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * ZSTDv07_BLOCKSIZE_ABSOLUTEMAX;
 }

 /*_******************************
@@ -50,12 +50,17 @@ ZSTDLIBv07_API size_t ZSTDv07_decompress( void* dst, size_t dstCapacity,
                                    const void* src, size_t compressedSize);

 /**
-ZSTDv07_getFrameSrcSize() : get the source length of a ZSTD frame
-    compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
-    return : the number of bytes that would be read to decompress this frame
-             or an errorCode if it fails (which can be tested using ZSTDv07_isError())
+ZSTDv07_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.7.x format
+    srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
+    cSize (output parameter)  : the number of bytes that would be read to decompress this frame
+                                or an error code if it fails (which can be tested using ZSTDv01_isError())
+    dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
+                                or ZSTD_CONTENTSIZE_ERROR if an error occurs
+
+    note : assumes `cSize` and `dBound` are _not_ NULL.
 */
-size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t compressedSize);
+void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
+                                     size_t* cSize, unsigned long long* dBound);

 /*======  Helper functions  ======*/
 ZSTDLIBv07_API unsigned    ZSTDv07_isError(size_t code);          /*!< tells if a `size_t` function result is an error code */
@@ -70,8 +70,8 @@ extern "C" {

 /*------   Version   ------*/
 #define ZSTD_VERSION_MAJOR    1
-#define ZSTD_VERSION_MINOR    3
-#define ZSTD_VERSION_RELEASE  8
+#define ZSTD_VERSION_MINOR    4
+#define ZSTD_VERSION_RELEASE  2

 #define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
 ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< to check runtime library version */
@@ -82,13 +82,28 @@ ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< to check runtime library v
 #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
 ZSTDLIB_API const char* ZSTD_versionString(void);   /* requires v1.3.0+ */

-/***************************************
-*  Default constant
-***************************************/
+/* *************************************
+ *  Default constant
+ ***************************************/
 #ifndef ZSTD_CLEVEL_DEFAULT
 #  define ZSTD_CLEVEL_DEFAULT 3
 #endif

+/* *************************************
+ *  Constants
+ ***************************************/
+
+/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */
+#define ZSTD_MAGICNUMBER            0xFD2FB528    /* valid since v0.8.0 */
+#define ZSTD_MAGIC_DICTIONARY       0xEC30A437    /* valid since v0.7.0 */
+#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50    /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */
+#define ZSTD_MAGIC_SKIPPABLE_MASK   0xFFFFFFF0
+
+#define ZSTD_BLOCKSIZELOG_MAX  17
+#define ZSTD_BLOCKSIZE_MAX     (1<<ZSTD_BLOCKSIZELOG_MAX)
+
+
+
 /***************************************
 *  Simple API
 ***************************************/
@@ -145,12 +160,21 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t
 * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */
 ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);

+/*! ZSTD_findFrameCompressedSize() :
+ * `src` should point to the start of a ZSTD frame or skippable frame.
+ * `srcSize` must be >= first frame size
+ * @return : the compressed size of the first frame starting at `src`,
+ *           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
+ *        or an error code if input is invalid */
+ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
+

 /*======  Helper functions  ======*/
 #define ZSTD_COMPRESSBOUND(srcSize)   ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0))  /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */
 ZSTDLIB_API size_t      ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */
 ZSTDLIB_API unsigned    ZSTD_isError(size_t code);          /*!< tells if a `size_t` function result is an error code */
 ZSTDLIB_API const char* ZSTD_getErrorName(size_t code);     /*!< provides readable string from an error code */
+ZSTDLIB_API int         ZSTD_minCLevel(void);               /*!< minimum negative compression level allowed */
 ZSTDLIB_API int         ZSTD_maxCLevel(void);               /*!< maximum compression level available */


@@ -159,9 +183,14 @@ ZSTDLIB_API int         ZSTD_maxCLevel(void);               /*!< maximum compres
 ***************************************/
 /*= Compression context
 *  When compressing many times,
- *  it is recommended to allocate a context just once, and re-use it for each successive compression operation.
+ *  it is recommended to allocate a context just once,
+ *  and re-use it for each successive compression operation.
 *  This will make workload friendlier for system's memory.
- *  Use one context per thread for parallel execution in multi-threaded environments. */
+ *  Note : re-using context is just a speed / resource optimization.
+ *         It doesn't change the compression ratio, which remains identical.
+ *  Note 2 : In multi-threaded environments,
+ *         use one different context per thread for parallel execution.
+ */
 typedef struct ZSTD_CCtx_s ZSTD_CCtx;
 ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void);
 ZSTDLIB_API size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);
@@ -195,279 +224,6 @@ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx,
                                 const void* src, size_t srcSize);


-/**************************
-*  Simple dictionary API
-***************************/
-/*! ZSTD_compress_usingDict() :
- *  Compression at an explicit compression level using a Dictionary.
- *  A dictionary can be any arbitrary data segment (also called a prefix),
- *  or a buffer with specified information (see dictBuilder/zdict.h).
- *  Note : This function loads the dictionary, resulting in significant startup delay.
- *         It's intended for a dictionary used only once.
- *  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */
-ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
-                                           void* dst, size_t dstCapacity,
-                                     const void* src, size_t srcSize,
-                                     const void* dict,size_t dictSize,
-                                           int compressionLevel);
-
-/*! ZSTD_decompress_usingDict() :
- *  Decompression using a known Dictionary.
- *  Dictionary must be identical to the one used during compression.
- *  Note : This function loads the dictionary, resulting in significant startup delay.
- *         It's intended for a dictionary used only once.
- *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
-ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
-                                             void* dst, size_t dstCapacity,
-                                       const void* src, size_t srcSize,
-                                       const void* dict,size_t dictSize);
-
-
-/***********************************
- *  Bulk processing dictionary API
- **********************************/
-typedef struct ZSTD_CDict_s ZSTD_CDict;
-
-/*! ZSTD_createCDict() :
- *  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
- *  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
- *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
- * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
- *  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
- *  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
-                                         int compressionLevel);
-
-/*! ZSTD_freeCDict() :
- *  Function frees memory allocated by ZSTD_createCDict(). */
-ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
-
-/*! ZSTD_compress_usingCDict() :
- *  Compression using a digested Dictionary.
- *  Recommended when same dictionary is used multiple times.
- *  Note : compression level is _decided at dictionary creation time_,
- *     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */
-ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
-                                            void* dst, size_t dstCapacity,
-                                      const void* src, size_t srcSize,
-                                      const ZSTD_CDict* cdict);
-
-
-typedef struct ZSTD_DDict_s ZSTD_DDict;
-
-/*! ZSTD_createDDict() :
- *  Create a digested dictionary, ready to start decompression operation without startup delay.
- *  dictBuffer can be released after DDict creation, as its content is copied inside DDict. */
-ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
-
-/*! ZSTD_freeDDict() :
- *  Function frees memory allocated with ZSTD_createDDict() */
-ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
-
-/*! ZSTD_decompress_usingDDict() :
- *  Decompression using a digested Dictionary.
- *  Recommended when same dictionary is used multiple times. */
-ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
-                                              void* dst, size_t dstCapacity,
-                                        const void* src, size_t srcSize,
-                                        const ZSTD_DDict* ddict);
-
-
-/****************************
-*  Streaming
-****************************/
-
-typedef struct ZSTD_inBuffer_s {
-  const void* src;    /**< start of input buffer */
-  size_t size;        /**< size of input buffer */
-  size_t pos;         /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
-} ZSTD_inBuffer;
-
-typedef struct ZSTD_outBuffer_s {
-  void*  dst;         /**< start of output buffer */
-  size_t size;        /**< size of output buffer */
-  size_t pos;         /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
-} ZSTD_outBuffer;
-
-
-
-/*-***********************************************************************
-*  Streaming compression - HowTo
-*
-*  A ZSTD_CStream object is required to track streaming operation.
-*  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
-*  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
-*  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
-*
-*  For parallel execution, use one separate ZSTD_CStream per thread.
-*
-*  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
-*
-*  Parameters are sticky : when starting a new compression on the same context,
-*  it will re-use the same sticky parameters as previous compression session.
-*  When in doubt, it's recommended to fully initialize the context before usage.
-*  Use ZSTD_initCStream() to set the parameter to a selected compression level.
-*  Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters.
-*
-*  Use ZSTD_compressStream() as many times as necessary to consume input stream.
-*  The function will automatically update both `pos` fields within `input` and `output`.
-*  Note that the function may not consume the entire input,
-*  for example, because the output buffer is already full,
-*  in which case `input.pos < input.size`.
-*  The caller must check if input has been entirely consumed.
-*  If not, the caller must make some room to receive more compressed data,
-*  and then present again remaining input data.
-* @return : a size hint, preferred nb of bytes to use as input for next function call
-*           or an error code, which can be tested using ZSTD_isError().
-*           Note 1 : it's just a hint, to help latency a little, any value will work fine.
-*           Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize()
-*
-*  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
-*  using ZSTD_flushStream(). `output->pos` will be updated.
-*  Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0).
-*  In which case, make some room to receive more compressed data, and call again ZSTD_flushStream().
-*  @return : 0 if internal buffers are entirely flushed,
-*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-*            or an error code, which can be tested using ZSTD_isError().
-*
-*  ZSTD_endStream() instructs to finish a frame.
-*  It will perform a flush and write frame epilogue.
-*  The epilogue is required for decoders to consider a frame completed.
-*  flush() operation is the same, and follows same rules as ZSTD_flushStream().
-*  @return : 0 if frame fully completed and fully flushed,
-*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-*            or an error code, which can be tested using ZSTD_isError().
-*
-* *******************************************************************/
-
-typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
-                                 /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */
-/*===== ZSTD_CStream management functions =====*/
-ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
-ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
-
-/*===== Streaming compression functions =====*/
-ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
-ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-
-ZSTDLIB_API size_t ZSTD_CStreamInSize(void);    /**< recommended size for input buffer */
-ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */
-
-
-
-/*-***************************************************************************
-*  Streaming decompression - HowTo
-*
-*  A ZSTD_DStream object is required to track streaming operations.
-*  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
-*  ZSTD_DStream objects can be re-used multiple times.
-*
-*  Use ZSTD_initDStream() to start a new decompression operation.
-* @return : recommended first input size
-*  Alternatively, use advanced API to set specific properties.
-*
-*  Use ZSTD_decompressStream() repetitively to consume your input.
-*  The function will update both `pos` fields.
-*  If `input.pos < input.size`, some input has not been consumed.
-*  It's up to the caller to present again remaining data.
-*  The function tries to flush all data decoded immediately, respecting output buffer size.
-*  If `output.pos < output.size`, decoder has flushed everything it could.
-*  But if `output.pos == output.size`, there might be some data left within internal buffers.,
-*  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
-*  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
-* @return : 0 when a frame is completely decoded and fully flushed,
-*        or an error code, which can be tested using ZSTD_isError(),
-*        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
-*                                the return value is a suggested next input size (just a hint for better latency)
-*                                that will never request more than the remaining frame size.
-* *******************************************************************************/
-
-typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
-                                 /* For compatibility with versions <= v1.2.0, prefer differentiating them. */
-/*===== ZSTD_DStream management functions =====*/
-ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
-ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
-
-/*===== Streaming decompression functions =====*/
-ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds);
-ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-
-ZSTDLIB_API size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
-ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
-
-#endif  /* ZSTD_H_235446 */
-
-
-
-
-/****************************************************************************************
- *   ADVANCED AND EXPERIMENTAL FUNCTIONS
- ****************************************************************************************
- * The definitions in the following section are considered experimental.
- * They are provided for advanced scenarios.
- * They should never be used with a dynamic library, as prototypes may change in the future.
- * Use them only in association with static linking.
- * ***************************************************************************************/
-
-#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
-#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
-
-
-/****************************************************************************************
- *   Candidate API for promotion to stable status
- ****************************************************************************************
- * The following symbols and constants form the "staging area" :
- * they are considered to join "stable API" by v1.4.0.
- * The proposal is written so that it can be made stable "as is",
- * though it's still possible to suggest improvements.
- * Staging is in fact last chance for changes,
- * the API is locked once reaching "stable" status.
- * ***************************************************************************************/
-
-
-/* ===  Constants   === */
-
-/* all magic numbers are supposed read/written to/from files/memory using little-endian convention */
-#define ZSTD_MAGICNUMBER            0xFD2FB528    /* valid since v0.8.0 */
-#define ZSTD_MAGIC_DICTIONARY       0xEC30A437    /* valid since v0.7.0 */
-#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50    /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */
-#define ZSTD_MAGIC_SKIPPABLE_MASK   0xFFFFFFF0
-
-#define ZSTD_BLOCKSIZELOG_MAX  17
-#define ZSTD_BLOCKSIZE_MAX     (1<<ZSTD_BLOCKSIZELOG_MAX)
-
-
-/* ===   query limits   === */
-
-ZSTDLIB_API int ZSTD_minCLevel(void);  /*!< minimum negative compression level allowed */
-
-
-/* ===   frame size   === */
-
-/*! ZSTD_findFrameCompressedSize() :
- * `src` should point to the start of a ZSTD frame or skippable frame.
- * `srcSize` must be >= first frame size
- * @return : the compressed size of the first frame starting at `src`,
- *           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
- *        or an error code if input is invalid */
-ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
-
-
-/* ===   Memory management   === */
-
-/*! ZSTD_sizeof_*() :
- *  These functions give the _current_ memory usage of selected object.
- *  Note that object memory usage can evolve (increase or decrease) over time. */
-ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
-ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
-ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
-ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
-ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
-ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
-
-
 /***************************************
 *  Advanced compression API
 ***************************************/
@@ -503,7 +259,10 @@ typedef enum { ZSTD_fast=1,

 typedef enum {

-    /* compression parameters */
+    /* compression parameters
+     * Note: When compressing with a ZSTD_CDict these parameters are superseded
+     * by the parameters used to construct the ZSTD_CDict. See ZSTD_CCtx_refCDict()
+     * for more info (superseded-by-cdict). */
    ZSTD_c_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table
                              * Default level is ZSTD_CLEVEL_DEFAULT==3.
                              * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT.
@@ -625,6 +384,8 @@ typedef enum {
     * ZSTD_c_format
     * ZSTD_c_forceMaxWindow
     * ZSTD_c_forceAttachDict
+     * ZSTD_c_literalCompressionMode
+     * ZSTD_c_targetCBlockSize
     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
     * note : never ever use experimentalParam? names directly;
     *        also, the enums values themselves are unstable and can still change.
@@ -632,10 +393,11 @@ typedef enum {
     ZSTD_c_experimentalParam1=500,
     ZSTD_c_experimentalParam2=10,
     ZSTD_c_experimentalParam3=1000,
-     ZSTD_c_experimentalParam4=1001
+     ZSTD_c_experimentalParam4=1001,
+     ZSTD_c_experimentalParam5=1002,
+     ZSTD_c_experimentalParam6=1003,
 } ZSTD_cParameter;

-
 typedef struct {
    size_t error;
    int lowerBound;
@@ -677,10 +439,443 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param
 *  Note 3 : Whenever all input data is provided and consumed in a single round,
 *           for example with ZSTD_compress2(),
 *           or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end),
- *           this value is automatically overriden by srcSize instead.
+ *           this value is automatically overridden by srcSize instead.
 */
 ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);

+typedef enum {
+    ZSTD_reset_session_only = 1,
+    ZSTD_reset_parameters = 2,
+    ZSTD_reset_session_and_parameters = 3
+} ZSTD_ResetDirective;
+
+/*! ZSTD_CCtx_reset() :
+ *  There are 2 different things that can be reset, independently or jointly :
+ *  - The session : will stop compressing current frame, and make CCtx ready to start a new one.
+ *                  Useful after an error, or to interrupt any ongoing compression.
+ *                  Any internal data not yet flushed is cancelled.
+ *                  Compression parameters and dictionary remain unchanged.
+ *                  They will be used to compress next frame.
+ *                  Resetting session never fails.
+ *  - The parameters : changes all parameters back to "default".
+ *                  This removes any reference to any dictionary too.
+ *                  Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing)
+ *                  otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError())
+ *  - Both : similar to resetting the session, followed by resetting parameters.
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset);
+
+/*! ZSTD_compress2() :
+ *  Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API.
+ *  ZSTD_compress2() always starts a new frame.
+ *  Should cctx hold data from a previously unfinished frame, everything about it is forgotten.
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+ *  - The function is always blocking, returns when compression is completed.
+ *  Hint : compression runs faster if `dstCapacity` >=  `ZSTD_compressBound(srcSize)`.
+ * @return : compressed size written into `dst` (<= `dstCapacity),
+ *           or an error code if it fails (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx,
+                                   void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
+
+
+/***************************************
+*  Advanced decompression API
+***************************************/
+
+/* The advanced API pushes parameters one by one into an existing DCtx context.
+ * Parameters are sticky, and remain valid for all following frames
+ * using the same DCtx context.
+ * It's possible to reset parameters to default values using ZSTD_DCtx_reset().
+ * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream().
+ *        Therefore, no new decompression function is necessary.
+ */
+
+typedef enum {
+
+    ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which
+                              * the streaming API will refuse to allocate memory buffer
+                              * in order to protect the host from unreasonable memory requirements.
+                              * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
+                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT).
+                              * Special: value 0 means "use default maximum windowLog". */
+
+    /* note : additional experimental parameters are also available
+     * within the experimental section of the API.
+     * At the time of this writing, they include :
+     * ZSTD_c_format
+     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
+     * note : never ever use experimentalParam? names directly
+     */
+     ZSTD_d_experimentalParam1=1000
+
+} ZSTD_dParameter;
+
+/*! ZSTD_dParam_getBounds() :
+ *  All parameters must belong to an interval with lower and upper bounds,
+ *  otherwise they will either trigger an error or be automatically clamped.
+ * @return : a structure, ZSTD_bounds, which contains
+ *         - an error status field, which must be tested using ZSTD_isError()
+ *         - both lower and upper bounds, inclusive
+ */
+ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam);
+
+/*! ZSTD_DCtx_setParameter() :
+ *  Set one compression parameter, selected by enum ZSTD_dParameter.
+ *  All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds().
+ *  Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter).
+ *  Setting a parameter is only possible during frame initialization (before starting decompression).
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value);
+
+/*! ZSTD_DCtx_reset() :
+ *  Return a DCtx to clean state.
+ *  Session and parameters can be reset jointly or separately.
+ *  Parameters can only be reset when no active frame is being decompressed.
+ * @return : 0, or an error code, which can be tested with ZSTD_isError()
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+
+
+/****************************
+*  Streaming
+****************************/
+
+typedef struct ZSTD_inBuffer_s {
+  const void* src;    /**< start of input buffer */
+  size_t size;        /**< size of input buffer */
+  size_t pos;         /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_inBuffer;
+
+typedef struct ZSTD_outBuffer_s {
+  void*  dst;         /**< start of output buffer */
+  size_t size;        /**< size of output buffer */
+  size_t pos;         /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_outBuffer;
+
+
+
+/*-***********************************************************************
+*  Streaming compression - HowTo
+*
+*  A ZSTD_CStream object is required to track streaming operation.
+*  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
+*  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
+*  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
+*
+*  For parallel execution, use one separate ZSTD_CStream per thread.
+*
+*  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
+*
+*  Parameters are sticky : when starting a new compression on the same context,
+*  it will re-use the same sticky parameters as previous compression session.
+*  When in doubt, it's recommended to fully initialize the context before usage.
+*  Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(),
+*  ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to
+*  set more specific parameters, the pledged source size, or load a dictionary.
+*
+*  Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to
+*  consume input stream. The function will automatically update both `pos`
+*  fields within `input` and `output`.
+*  Note that the function may not consume the entire input, for example, because
+*  the output buffer is already full, in which case `input.pos < input.size`.
+*  The caller must check if input has been entirely consumed.
+*  If not, the caller must make some room to receive more compressed data,
+*  and then present again remaining input data.
+*  note: ZSTD_e_continue is guaranteed to make some forward progress when called,
+*        but doesn't guarantee maximal forward progress. This is especially relevant
+*        when compressing with multiple threads. The call won't block if it can
+*        consume some input, but if it can't it will wait for some, but not all,
+*        output to be flushed.
+* @return : provides a minimum amount of data remaining to be flushed from internal buffers
+*           or an error code, which can be tested using ZSTD_isError().
+*
+*  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
+*  using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated.
+*  Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0).
+*  In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the
+*  operation.
+*  note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if internal buffers are entirely flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+*  Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame.
+*  It will perform a flush and write frame epilogue.
+*  The epilogue is required for decoders to consider a frame completed.
+*  flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to
+*  start a new frame.
+*  note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if frame fully completed and fully flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+* *******************************************************************/
+
+typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
+                                 /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */
+/*===== ZSTD_CStream management functions =====*/
+ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
+ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
+
+/*===== Streaming compression functions =====*/
+typedef enum {
+    ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */
+    ZSTD_e_flush=1,    /* flush any data provided so far,
+                        * it creates (at least) one new block, that can be decoded immediately on reception;
+                        * frame will continue: any future data can still reference previously compressed data, improving compression.
+                        * note : multithreaded compression will block to flush as much output as possible. */
+    ZSTD_e_end=2       /* flush any remaining data _and_ close current frame.
+                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
+                        * After that point, any additional data starts a new frame.
+                        * note : each frame is independent (does not reference any content from previous frame).
+                        : note : multithreaded compression will block to flush as much output as possible. */
+} ZSTD_EndDirective;
+
+/*! ZSTD_compressStream2() :
+ *  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+ *  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
+ *  - output->pos must be <= dstCapacity, input->pos must be <= srcSize
+ *  - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
+ *  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
+ *  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
+ *                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
+ *                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
+ *  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
+ *  - @return provides a minimum amount of data remaining to be flushed from internal buffers
+ *            or an error code, which can be tested using ZSTD_isError().
+ *            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
+ *            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
+ *            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
+ *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
+ *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+ *            Before starting a new compression job, or changing compression parameters,
+ *            it is required to fully flush internal buffers.
+ */
+ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
+                                         ZSTD_outBuffer* output,
+                                         ZSTD_inBuffer* input,
+                                         ZSTD_EndDirective endOp);
+
+
+/* These buffer sizes are softly recommended.
+ * They are not required : ZSTD_compressStream*() happily accepts any buffer size, for both input and output.
+ * Respecting the recommended size just makes it a bit easier for ZSTD_compressStream*(),
+ * reducing the amount of memory shuffling and buffering, resulting in minor performance savings.
+ *
+ * However, note that these recommendations are from the perspective of a C caller program.
+ * If the streaming interface is invoked from some other language,
+ * especially managed ones such as Java or Go, through a foreign function interface such as jni or cgo,
+ * a major performance rule is to reduce crossing such interface to an absolute minimum.
+ * It's not rare that performance ends being spent more into the interface, rather than compression itself.
+ * In which cases, prefer using large buffers, as large as practical,
+ * for both input and output, to reduce the nb of roundtrips.
+ */
+ZSTDLIB_API size_t ZSTD_CStreamInSize(void);    /**< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */
+
+
+/* *****************************************************************************
+ * This following is a legacy streaming API.
+ * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2().
+ * It is redundant, but remains fully supported.
+ * Advanced parameters and dictionary compression can only be used through the
+ * new API.
+ ******************************************************************************/
+
+/*!
+ * Equivalent to:
+ *
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ */
+ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
+/*!
+ * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue).
+ * NOTE: The return value is different. ZSTD_compressStream() returns a hint for
+ * the next read size (if non-zero and not an error). ZSTD_compressStream2()
+ * returns the minimum nb of bytes left to flush (if non-zero and not an error).
+ */
+ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */
+ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */
+ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+
+
+/*-***************************************************************************
+*  Streaming decompression - HowTo
+*
+*  A ZSTD_DStream object is required to track streaming operations.
+*  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
+*  ZSTD_DStream objects can be re-used multiple times.
+*
+*  Use ZSTD_initDStream() to start a new decompression operation.
+* @return : recommended first input size
+*  Alternatively, use advanced API to set specific properties.
+*
+*  Use ZSTD_decompressStream() repetitively to consume your input.
+*  The function will update both `pos` fields.
+*  If `input.pos < input.size`, some input has not been consumed.
+*  It's up to the caller to present again remaining data.
+*  The function tries to flush all data decoded immediately, respecting output buffer size.
+*  If `output.pos < output.size`, decoder has flushed everything it could.
+*  But if `output.pos == output.size`, there might be some data left within internal buffers.,
+*  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
+*  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
+* @return : 0 when a frame is completely decoded and fully flushed,
+*        or an error code, which can be tested using ZSTD_isError(),
+*        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
+*                                the return value is a suggested next input size (just a hint for better latency)
+*                                that will never request more than the remaining frame size.
+* *******************************************************************************/
+
+typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
+                                 /* For compatibility with versions <= v1.2.0, prefer differentiating them. */
+/*===== ZSTD_DStream management functions =====*/
+ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
+ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
+
+/*===== Streaming decompression functions =====*/
+
+/* This function is redundant with the advanced API and equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds);
+ *     ZSTD_DCtx_refDDict(zds, NULL);
+ */
+ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds);
+
+ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+
+ZSTDLIB_API size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
+
+
+/**************************
+*  Simple dictionary API
+***************************/
+/*! ZSTD_compress_usingDict() :
+ *  Compression at an explicit compression level using a Dictionary.
+ *  A dictionary can be any arbitrary data segment (also called a prefix),
+ *  or a buffer with specified information (see dictBuilder/zdict.h).
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const void* dict,size_t dictSize,
+                                           int compressionLevel);
+
+/*! ZSTD_decompress_usingDict() :
+ *  Decompression using a known Dictionary.
+ *  Dictionary must be identical to the one used during compression.
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                             void* dst, size_t dstCapacity,
+                                       const void* src, size_t srcSize,
+                                       const void* dict,size_t dictSize);
+
+
+/***********************************
+ *  Bulk processing dictionary API
+ **********************************/
+typedef struct ZSTD_CDict_s ZSTD_CDict;
+
+/*! ZSTD_createCDict() :
+ *  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
+ *  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
+ *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
+ *  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
+ *  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+                                         int compressionLevel);
+
+/*! ZSTD_freeCDict() :
+ *  Function frees memory allocated by ZSTD_createCDict(). */
+ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
+
+/*! ZSTD_compress_usingCDict() :
+ *  Compression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times.
+ *  Note : compression level is _decided at dictionary creation time_,
+ *     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */
+ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                            void* dst, size_t dstCapacity,
+                                      const void* src, size_t srcSize,
+                                      const ZSTD_CDict* cdict);
+
+
+typedef struct ZSTD_DDict_s ZSTD_DDict;
+
+/*! ZSTD_createDDict() :
+ *  Create a digested dictionary, ready to start decompression operation without startup delay.
+ *  dictBuffer can be released after DDict creation, as its content is copied inside DDict. */
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
+
+/*! ZSTD_freeDDict() :
+ *  Function frees memory allocated with ZSTD_createDDict() */
+ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
+
+/*! ZSTD_decompress_usingDDict() :
+ *  Decompression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                              void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize,
+                                        const ZSTD_DDict* ddict);
+
+
+/********************************
+ *  Dictionary helper functions
+ *******************************/
+
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompressed the frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary to be decoded (most common case).
+ *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+
+
+/*******************************************************************************
+ * Advanced dictionary and prefix API
+ *
+ * This API allows dictionaries to be used with ZSTD_compress2(),
+ * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and
+ * only reset with the context is reset with ZSTD_reset_parameters or
+ * ZSTD_reset_session_and_parameters. Prefixes are single-use.
+ ******************************************************************************/
+
+
 /*! ZSTD_CCtx_loadDictionary() :
 *  Create an internal CDict from `dict` buffer.
 *  Decompression will have to use same dictionary.
@@ -703,7 +898,9 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s
 /*! ZSTD_CCtx_refCDict() :
 *  Reference a prepared dictionary, to be used for all next compressed frames.
 *  Note that compression parameters are enforced from within CDict,
- *  and supercede any compression parameter previously set within CCtx.
+ *  and supersede any compression parameter previously set within CCtx.
+ *  The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs.
+ *  The ignored parameters will be used again if the CCtx is returned to no-dictionary mode.
 *  The dictionary will remain valid for future compressed frames using same CCtx.
 * @result : 0, or an error code (which can be tested with ZSTD_isError()).
 *  Special : Referencing a NULL CDict means "return to no-dictionary mode".
@@ -733,136 +930,6 @@ ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
 ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
                                 const void* prefix, size_t prefixSize);

-
-typedef enum {
-    ZSTD_reset_session_only = 1,
-    ZSTD_reset_parameters = 2,
-    ZSTD_reset_session_and_parameters = 3
-} ZSTD_ResetDirective;
-
-/*! ZSTD_CCtx_reset() :
- *  There are 2 different things that can be reset, independently or jointly :
- *  - The session : will stop compressing current frame, and make CCtx ready to start a new one.
- *                  Useful after an error, or to interrupt any ongoing compression.
- *                  Any internal data not yet flushed is cancelled.
- *                  Compression parameters and dictionary remain unchanged.
- *                  They will be used to compress next frame.
- *                  Resetting session never fails.
- *  - The parameters : changes all parameters back to "default".
- *                  This removes any reference to any dictionary too.
- *                  Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing)
- *                  otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError())
- *  - Both : similar to resetting the session, followed by resetting parameters.
- */
-ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset);
-
-
-
-/*! ZSTD_compress2() :
- *  Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API.
- *  ZSTD_compress2() always starts a new frame.
- *  Should cctx hold data from a previously unfinished frame, everything about it is forgotten.
- *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
- *  - The function is always blocking, returns when compression is completed.
- *  Hint : compression runs faster if `dstCapacity` >=  `ZSTD_compressBound(srcSize)`.
- * @return : compressed size written into `dst` (<= `dstCapacity),
- *           or an error code if it fails (which can be tested using ZSTD_isError()).
- */
-ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx,
-                                   void* dst, size_t dstCapacity,
-                             const void* src, size_t srcSize);
-
-typedef enum {
-    ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */
-    ZSTD_e_flush=1,    /* flush any data provided so far,
-                        * it creates (at least) one new block, that can be decoded immediately on reception;
-                        * frame will continue: any future data can still reference previously compressed data, improving compression. */
-    ZSTD_e_end=2       /* flush any remaining data _and_ close current frame.
-                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
-                        * After that point, any additional data starts a new frame.
-                        * note : each frame is independent (does not reference any content from previous frame). */
-} ZSTD_EndDirective;
-
-/*! ZSTD_compressStream2() :
- *  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
- *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
- *  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
- *  - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize
- *  - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
- *  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
- *  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
- *                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
- *                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
- *  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
- *  - @return provides a minimum amount of data remaining to be flushed from internal buffers
- *            or an error code, which can be tested using ZSTD_isError().
- *            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
- *            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
- *            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
- *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
- *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
- *            Before starting a new compression job, or changing compression parameters,
- *            it is required to fully flush internal buffers.
- */
-ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
-                                         ZSTD_outBuffer* output,
-                                         ZSTD_inBuffer* input,
-                                         ZSTD_EndDirective endOp);
-
-
-
-/* ============================== */
-/*   Advanced decompression API   */
-/* ============================== */
-
-/* The advanced API pushes parameters one by one into an existing DCtx context.
- * Parameters are sticky, and remain valid for all following frames
- * using the same DCtx context.
- * It's possible to reset parameters to default values using ZSTD_DCtx_reset().
- * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream().
- *        Therefore, no new decompression function is necessary.
- */
-
-
-typedef enum {
-
-    ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which
-                              * the streaming API will refuse to allocate memory buffer
-                              * in order to protect the host from unreasonable memory requirements.
-                              * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
-                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) */
-
-    /* note : additional experimental parameters are also available
-     * within the experimental section of the API.
-     * At the time of this writing, they include :
-     * ZSTD_c_format
-     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
-     * note : never ever use experimentalParam? names directly
-     */
-     ZSTD_d_experimentalParam1=1000
-
-} ZSTD_dParameter;
-
-
-/*! ZSTD_dParam_getBounds() :
- *  All parameters must belong to an interval with lower and upper bounds,
- *  otherwise they will either trigger an error or be automatically clamped.
- * @return : a structure, ZSTD_bounds, which contains
- *         - an error status field, which must be tested using ZSTD_isError()
- *         - both lower and upper bounds, inclusive
- */
-ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam);
-
-/*! ZSTD_DCtx_setParameter() :
- *  Set one compression parameter, selected by enum ZSTD_dParameter.
- *  All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds().
- *  Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter).
- *  Setting a parameter is only possible during frame initialization (before starting decompression).
- * @return : 0, or an error code (which can be tested using ZSTD_isError()).
- */
-ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value);
-
-
 /*! ZSTD_DCtx_loadDictionary() :
 *  Create an internal DDict from dict buffer,
 *  to be used to decompress next frames.
@@ -910,15 +977,32 @@ ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
 ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx,
                                 const void* prefix, size_t prefixSize);

-/*! ZSTD_DCtx_reset() :
- *  Return a DCtx to clean state.
- *  Session and parameters can be reset jointly or separately.
- *  Parameters can only be reset when no active frame is being decompressed.
- * @return : 0, or an error code, which can be tested with ZSTD_isError()
- */
-ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+/* ===   Memory management   === */
+
+/*! ZSTD_sizeof_*() :
+ *  These functions give the _current_ memory usage of selected object.
+ *  Note that object memory usage can evolve (increase or decrease) over time. */
+ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+
+#endif  /* ZSTD_H_235446 */


+/* **************************************************************************************
+ *   ADVANCED AND EXPERIMENTAL FUNCTIONS
+ ****************************************************************************************
+ * The definitions in the following section are considered experimental.
+ * They are provided for advanced scenarios.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * Use them only in association with static linking.
+ * ***************************************************************************************/
+
+#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
+#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY

 /****************************************************************************************
 *   experimental API (static linking only)
@@ -962,7 +1046,7 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
 #define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27   /* by default, the streaming decoder will refuse any frame
                                           * requiring larger than (1<<ZSTD_WINDOWLOG_LIMIT_DEFAULT) window size,
                                           * to preserve host's memory from unreasonable requirements.
-                                           * This limit can be overriden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,).
+                                           * This limit can be overridden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,).
                                           * The limit does not apply for one-pass decoders (such as ZSTD_decompress()), since no additional memory is allocated */


@@ -976,6 +1060,10 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
 #define ZSTD_LDM_HASHRATELOG_MIN     0
 #define ZSTD_LDM_HASHRATELOG_MAX (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN)

+/* Advanced parameter bounds */
+#define ZSTD_TARGETCBLOCKSIZE_MIN   64
+#define ZSTD_TARGETCBLOCKSIZE_MAX   ZSTD_BLOCKSIZE_MAX
+
 /* internal */
 #define ZSTD_HASHLOG3_MAX           17

@@ -1064,15 +1152,24 @@ typedef enum {
    ZSTD_dictForceCopy     = 2, /* Always copy the dictionary. */
 } ZSTD_dictAttachPref_e;

+typedef enum {
+  ZSTD_lcm_auto = 0,          /**< Automatically determine the compression mode based on the compression level.
+                               *   Negative compression levels will be uncompressed, and positive compression
+                               *   levels will be compressed. */
+  ZSTD_lcm_huffman = 1,       /**< Always attempt Huffman compression. Uncompressed literals will still be
+                               *   emitted if Huffman compression is not profitable. */
+  ZSTD_lcm_uncompressed = 2,  /**< Always emit uncompressed literals. */
+} ZSTD_literalCompressionMode_e;
+

 /***************************************
 *  Frame size functions
 ***************************************/

 /*! ZSTD_findDecompressedSize() :
- *  `src` should point the start of a series of ZSTD encoded and/or skippable frames
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
 *  `srcSize` must be the _exact_ size of this series
- *       (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
 *  @return : - decompressed size of all data in all successive frames
 *            - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
 *            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
@@ -1092,6 +1189,21 @@ typedef enum {
 *            however it does mean that all frame data must be present and valid. */
 ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);

+/*! ZSTD_decompressBound() :
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
+ *  `srcSize` must be the _exact_ size of this series
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
+ *  @return : - upper-bound for the decompressed size of all data in all successive frames
+ *            - if an error occured: ZSTD_CONTENTSIZE_ERROR
+ *
+ *  note 1  : an error can occur if `src` contains an invalid or incorrectly formatted frame.
+ *  note 2  : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`.
+ *            in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value.
+ *  note 3  : when the decompressed size field isn't available, the upper-bound for that frame is calculated by:
+ *              upper-bound = # blocks * min(128 KB, Window_Size)
+ */
+ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize);
+
 /*! ZSTD_frameHeaderSize() :
 *  srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX.
 * @return : size of the Frame Header,
@@ -1110,7 +1222,7 @@ ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
 *  It will also consider src size to be arbitrarily "large", which is worst case.
 *  If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation.
 *  ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
- *  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+ *  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
 *  Note : CCtx size estimation is only correct for single-threaded compression. */
 ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
 ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams);
@@ -1122,7 +1234,7 @@ ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
 *  It will also consider src size to be arbitrarily "large", which is worst case.
 *  If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation.
 *  ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
- *  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+ *  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
 *  Note : CStream size estimation is only correct for single-threaded compression.
 *  ZSTD_DStream memory budget depends on window Size.
 *  This information can be passed manually, using ZSTD_estimateDStreamSize,
@@ -1226,22 +1338,26 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictS
 ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);

 /*! ZSTD_getCParams() :
-*   @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
-*   `estimatedSrcSize` value is optional, select 0 if not known */
+ * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
+ * `estimatedSrcSize` value is optional, select 0 if not known */
 ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);

 /*! ZSTD_getParams() :
-*   same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
-*   All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */
+ *  same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
+ *  All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */
 ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);

 /*! ZSTD_checkCParams() :
-*   Ensure param values remain within authorized range */
+ *  Ensure param values remain within authorized range.
+ * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */
 ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params);

 /*! ZSTD_adjustCParams() :
 *  optimize params for a given `srcSize` and `dictSize`.
- *  both values are optional, select `0` if unknown. */
+ * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN.
+ * `dictSize` must be `0` when there is no dictionary.
+ *  cPar can be invalid : all parameters will be clamped within valid range in the @return struct.
+ *  This function never fails (wide contract) */
 ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);

 /*! ZSTD_compress_advanced() :
@@ -1314,6 +1430,17 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre
 * See the comments on that enum for an explanation of the feature. */
 #define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4

+/* Controls how the literals are compressed (default is auto).
+ * The value must be of type ZSTD_literalCompressionMode_e.
+ * See ZSTD_literalCompressionMode_t enum definition for details.
+ */
+#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5
+
+/* Tries to fit compressed block size to be around targetCBlockSize.
+ * No target when targetCBlockSize == 0.
+ * There is no guarantee on compressed block size (default:0) */
+#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6
+
 /*! ZSTD_CCtx_getParameter() :
 *  Get the requested compression parameter value, selected by enum ZSTD_cParameter,
 *  and store it into int* value.
@@ -1325,10 +1452,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param
 /*! ZSTD_CCtx_params :
 *  Quick howto :
 *  - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure
- *  - ZSTD_CCtxParam_setParameter() : Push parameters one by one into
- *                                    an existing ZSTD_CCtx_params structure.
- *                                    This is similar to
- *                                    ZSTD_CCtx_setParameter().
+ *  - ZSTD_CCtxParams_setParameter() : Push parameters one by one into
+ *                                     an existing ZSTD_CCtx_params structure.
+ *                                     This is similar to
+ *                                     ZSTD_CCtx_setParameter().
 *  - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to
 *                                    an existing CCtx.
 *                                    These parameters will be applied to
@@ -1359,20 +1486,20 @@ ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compre
 */
 ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params);

-/*! ZSTD_CCtxParam_setParameter() :
+/*! ZSTD_CCtxParams_setParameter() :
 *  Similar to ZSTD_CCtx_setParameter.
 *  Set one compression parameter, selected by enum ZSTD_cParameter.
 *  Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams().
 * @result : 0, or an error code (which can be tested with ZSTD_isError()).
 */
-ZSTDLIB_API size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
+ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);

-/*! ZSTD_CCtxParam_getParameter() :
+/*! ZSTD_CCtxParams_getParameter() :
 * Similar to ZSTD_CCtx_getParameter.
 * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter.
 * @result : 0, or an error code (which can be tested with ZSTD_isError()).
 */
-ZSTDLIB_API size_t ZSTD_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
+ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);

 /*! ZSTD_CCtx_setParametersUsingCCtxParams() :
 *  Apply a set of ZSTD_CCtx_params to the compression context.
@@ -1415,31 +1542,6 @@ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
 *  it must remain read accessible throughout the lifetime of DDict */
 ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);

-
-/*! ZSTD_getDictID_fromDict() :
- *  Provides the dictID stored within dictionary.
- *  if @return == 0, the dictionary is not conformant with Zstandard specification.
- *  It can still be loaded, but as a content-only dictionary. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
-
-/*! ZSTD_getDictID_fromDDict() :
- *  Provides the dictID of the dictionary loaded into `ddict`.
- *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
- *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
-
-/*! ZSTD_getDictID_fromFrame() :
- *  Provides the dictID required to decompressed the frame stored within `src`.
- *  If @return == 0, the dictID could not be decoded.
- *  This could for one of the following reasons :
- *  - The frame does not require a dictionary to be decoded (most common case).
- *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
- *    Note : this use case also happens when using a non-conformant dictionary.
- *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
- *  - This is not a Zstandard frame.
- *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
-
 /*! ZSTD_DCtx_loadDictionary_byReference() :
 *  Same as ZSTD_DCtx_loadDictionary(),
 *  but references `dict` content instead of copying it into `dctx`.
@@ -1501,14 +1603,68 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs (
 ********************************************************************/

 /*=====   Advanced Streaming compression functions  =====*/
-ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */
-ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/
+/**! ZSTD_initCStream_srcSize() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
+ * pledgedSrcSize must be correct. If it is not known at init time, use
+ * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs,
+ * "0" also disables frame content size field. It may be enabled in the future.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);
+/**! ZSTD_initCStream_usingDict() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * Creates of an internal CDict (incompatible with static CCtx), except if
+ * dict == NULL or dictSize < 8, in which case no dict is used.
+ * Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if
+ * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel);
+/**! ZSTD_initCStream_advanced() :
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdParams(zcs, params); // Set the zstd params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy.
+ */
 ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
-                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  /**< note : cdict will just be referenced, and must outlive compression session */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);
+/**! ZSTD_initCStream_usingCDict() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * note : cdict will just be referenced, and must outlive compression session
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
+/**! ZSTD_initCStream_usingCDict_advanced() :
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdFrameParams(zcs, fParams); // Set the zstd frame params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * same as ZSTD_initCStream_usingCDict(), with control over frame parameters.
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);

 /*! ZSTD_resetCStream() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
 *  start a new frame, using same parameters from previous frame.
 *  This is typically useful to skip dictionary loading stage, since it will re-use it in-place.
 *  Note that zcs must be init at least once before using ZSTD_resetCStream().
@@ -1555,9 +1711,32 @@ ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx);


 /*=====   Advanced Streaming decompression functions  =====*/
-ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: no dictionary will be used if dict == NULL or dictSize < 8 */
-ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);  /**< note : ddict is referenced, it must outlive decompression session */
-ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);  /**< re-use decompression parameters from previous init; saves dictionary loading */
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_loadDictionary(zds, dict, dictSize);
+ *
+ * note: no dictionary will be used if dict == NULL or dictSize < 8
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize);
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_refDDict(zds, ddict);
+ *
+ * note : ddict is referenced, it must outlive decompression session
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *
+ * re-use decompression parameters from previous init; saves dictionary loading
+ */
+ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);


 /*********************************************************************
@@ -1696,7 +1875,7 @@ typedef struct {
    unsigned checksumFlag;
 } ZSTD_frameHeader;

-/** ZSTD_getFrameHeader() :
+/*! ZSTD_getFrameHeader() :
 *  decode Frame Header, or requires larger `srcSize`.
 * @return : 0, `zfhPtr` is correctly filled,
 *          >0, `srcSize` is too small, value is wanted `srcSize` amount,
@@ -33,4 +33,5 @@ afl

 # Misc files
 *.bat
+!windres/generate_res.bat
 dirTest*
@@ -51,7 +51,7 @@ endif
 CFLAGS  ?= -O3
 DEBUGFLAGS+=-Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-            -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
+            -Wstrict-prototypes -Wundef -Wpointer-arith \
            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
            -Wredundant-decls -Wmissing-prototypes -Wc++-compat
 CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
@@ -165,7 +165,7 @@ $(ZSTDDECOMP_O): CFLAGS += $(ALIGN_LOOP)
 zstd : CPPFLAGS += $(THREAD_CPP) $(ZLIBCPP) $(LZMACPP) $(LZ4CPP)
 zstd : LDFLAGS += $(THREAD_LD) $(ZLIBLD) $(LZMALD) $(LZ4LD) $(DEBUGFLAGS_LD)
 zstd : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT)
-zstd : $(ZSTDLIB_FILES) zstdcli.o util.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o
+zstd : $(ZSTDLIB_FILES) zstdcli.o util.o timefn.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o
 	@echo "$(THREAD_MSG)"
 	@echo "$(ZLIB_MSG)"
 	@echo "$(LZMA_MSG)"
@@ -183,13 +183,13 @@ zstd-release: zstd
 zstd32 : CPPFLAGS += $(THREAD_CPP)
 zstd32 : LDFLAGS  += $(THREAD_LD)
 zstd32 : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT)
-zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c
+zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c timefn.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c
 ifneq (,$(filter Windows%,$(OS)))
 	windres/generate_res.bat
 endif
 	$(CC) -m32 $(FLAGS) $^ $(RES32_FILE) -o $@$(EXT)

-zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o datagen.o dibio.o
+zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o timefn.o datagen.o dibio.o
 	$(CC) $(FLAGS) $^ -o $@$(EXT) $(LDFLAGS)

 zstd-nomt : THREAD_CPP :=
@@ -222,13 +222,13 @@ zstd-pgo :

 # minimal target, with only zstd compression and decompression. no bench. no legacy.
 zstd-small: CFLAGS = -Os -s
-zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c fileio.c
+zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c timefn.c fileio.c
 	$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT $^ -o $@$(EXT)

-zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c fileio.c
+zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c timefn.c fileio.c
 	$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NOCOMPRESS $^ -o $@$(EXT)

-zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c fileio.c
+zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c timefn.c fileio.c
 	$(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NODECOMPRESS $^ -o $@$(EXT)

 zstdmt: zstd
@@ -265,9 +265,9 @@ man: zstd.1 zstdgrep.1 zstdless.1

 .PHONY: clean-man
 clean-man:
-	rm zstd.1
-	rm zstdgrep.1
-	rm zstdless.1
+	$(RM) zstd.1
+	$(RM) zstdgrep.1
+	$(RM) zstdless.1

 .PHONY: preview-man
 preview-man: clean-man man
@@ -37,7 +37,7 @@ There are however other Makefile targets that create different variations of CLI
  `.gz` support is automatically enabled when `zlib` library is detected at build time.
  It's possible to disable `.gz` support, by setting `HAVE_ZLIB=0`.
  Example : `make zstd HAVE_ZLIB=0`
-  It's also possible to force compilation with zlib support, `using HAVE_ZLIB=1`.
+  It's also possible to force compilation with zlib support, using `HAVE_ZLIB=1`.
  In which case, linking stage will fail if `zlib` library cannot be found.
  This is useful to prevent silent feature disabling.

@@ -45,7 +45,7 @@ There are however other Makefile targets that create different variations of CLI
  This is ordered through commands `--format=xz` and `--format=lzma` respectively.
  Alternatively, symlinks named `xz`, `unxz`, `lzma`, or `unlzma` will mimic intended behavior.
  `.xz` and `.lzma` support is automatically enabled when `lzma` library is detected at build time.
-  It's possible to disable `.xz` and `.lzma` support, by setting `HAVE_LZMA=0` .
+  It's possible to disable `.xz` and `.lzma` support, by setting `HAVE_LZMA=0`.
  Example : `make zstd HAVE_LZMA=0`
  It's also possible to force compilation with lzma support, using `HAVE_LZMA=1`.
  In which case, linking stage will fail if `lzma` library cannot be found.
@@ -157,8 +157,8 @@ Advanced arguments :

 Dictionary builder :
 --train ## : create a dictionary from a training set of files
--train-cover[=k=#,d=#,steps=#,split=#] : use the cover algorithm with optional args
--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,accel=#] : use the fastcover algorithm with optional args
+--train-cover[=k=#,d=#,steps=#,split=#,shrink[=#]] : use the cover algorithm with optional args
+--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,shrink[=#],accel=#] : use the fastcover algorithm with optional args
 --train-legacy[=s=#] : use the legacy algorithm with selectivity (default: 9)
 -o file : `file` is dictionary name (default: dictionary)
 --maxdict=# : limit dictionary to specified size (default: 112640)
@@ -13,25 +13,19 @@
 /* *************************************
 *  Includes
 ***************************************/
-#include "platform.h"    /* Large Files support */
-#include "util.h"        /* UTIL_getFileSize, UTIL_sleep */
 #include <stdlib.h>      /* malloc, free */
 #include <string.h>      /* memset */
-#include <stdio.h>       /* fprintf, fopen */
-#undef NDEBUG            /* assert must not be disabled */
 #include <assert.h>      /* assert */

-#include "mem.h"
+#include "timefn.h"        /* UTIL_time_t, UTIL_getTime */
 #include "benchfn.h"


 /* *************************************
 *  Constants
 ***************************************/
-#define TIMELOOP_MICROSEC     (1*1000000ULL) /* 1 second */
+#define TIMELOOP_MICROSEC     SEC_TO_MICRO      /* 1 second */
 #define TIMELOOP_NANOSEC      (1*1000000000ULL) /* 1 second */
-#define ACTIVEPERIOD_MICROSEC (70*TIMELOOP_MICROSEC) /* 70 seconds */
-#define COOLPERIOD_SEC        10

 #define KB *(1 <<10)
 #define MB *(1 <<20)
@@ -39,14 +33,16 @@


 /* *************************************
-*  Errors
+*  Debug errors
 ***************************************/
-#ifndef DEBUG
-#  define DEBUG 0
+#if defined(DEBUG) && (DEBUG >= 1)
+#  include <stdio.h>       /* fprintf */
+#  define DISPLAY(...)       fprintf(stderr, __VA_ARGS__)
+#  define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }
+#else
+#  define DEBUGOUTPUT(...)
 #endif

-#define DISPLAY(...)       fprintf(stderr, __VA_ARGS__)
-#define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }

 /* error without displaying */
 #define RETURN_QUIET_ERROR(retValue, ...) {           \
@@ -57,6 +53,9 @@
    return retValue;                                  \
 }

+/* Abort execution if a condition is not met */
+#define CONTROL(c) { if (!(c)) { DEBUGOUTPUT("error: %s \n", #c); abort(); } }
+

 /* *************************************
 *  Benchmarking an arbitrary function
@@ -71,13 +70,13 @@ int BMK_isSuccessful_runOutcome(BMK_runOutcome_t outcome)
 *           check outcome validity first, using BMK_isValid_runResult() */
 BMK_runTime_t BMK_extract_runTime(BMK_runOutcome_t outcome)
 {
-    assert(outcome.error_tag_never_ever_use_directly == 0);
+    CONTROL(outcome.error_tag_never_ever_use_directly == 0);
    return outcome.internal_never_ever_use_directly;
 }

 size_t BMK_extract_errorResult(BMK_runOutcome_t outcome)
 {
-    assert(outcome.error_tag_never_ever_use_directly != 0);
+    CONTROL(outcome.error_tag_never_ever_use_directly != 0);
    return outcome.error_result_never_ever_use_directly;
 }

@@ -116,15 +115,7 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
    {   size_t i;
        for(i = 0; i < p.blockCount; i++) {
            memset(p.dstBuffers[i], 0xE5, p.dstCapacities[i]);  /* warm up and erase result buffer */
-        }
-#if 0
-        /* based on testing these seem to lower accuracy of multiple calls of 1 nbLoops vs 1 call of multiple nbLoops
-         * (Makes former slower)
-         */
-        UTIL_sleepMilli(5);  /* give processor time to other processes */
-        UTIL_waitForNextTick();
-#endif
-    }
+    }   }

    /* benchmark */
    {   UTIL_time_t const clockStart = UTIL_getTime();
@@ -146,9 +137,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
            }   }
        }  /* for (loopNb = 0; loopNb < nbLoops; loopNb++) */

-        {   U64 const totalTime = UTIL_clockSpanNano(clockStart);
+        {   PTime const totalTime = UTIL_clockSpanNano(clockStart);
            BMK_runTime_t rt;
-            rt.nanoSecPerRun = totalTime / nbLoops;
+            rt.nanoSecPerRun = (double)totalTime / nbLoops;
            rt.sumOfReturn = dstSize;
            return BMK_setValid_runTime(rt);
    }   }
@@ -158,9 +149,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p,
 /* ====  Benchmarking any function, providing intermediate results  ==== */

 struct BMK_timedFnState_s {
-    U64 timeSpent_ns;
-    U64 timeBudget_ns;
-    U64 runBudget_ns;
+    PTime timeSpent_ns;
+    PTime timeBudget_ns;
+    PTime runBudget_ns;
    BMK_runTime_t fastestRun;
    unsigned nbLoops;
    UTIL_time_t coolTime;
@@ -174,8 +165,20 @@ BMK_timedFnState_t* BMK_createTimedFnState(unsigned total_ms, unsigned run_ms)
    return r;
 }

-void BMK_freeTimedFnState(BMK_timedFnState_t* state) {
-    free(state);
+void BMK_freeTimedFnState(BMK_timedFnState_t* state) { free(state); }
+
+BMK_timedFnState_t*
+BMK_initStatic_timedFnState(void* buffer, size_t size, unsigned total_ms, unsigned run_ms)
+{
+    typedef char check_size[ 2 * (sizeof(BMK_timedFnState_shell) >= sizeof(struct BMK_timedFnState_s)) - 1];  /* static assert : a compilation failure indicates that BMK_timedFnState_shell is not large enough */
+    typedef struct { check_size c; BMK_timedFnState_t tfs; } tfs_align;  /* force tfs to be aligned at its next best position */
+    size_t const tfs_alignment = offsetof(tfs_align, tfs); /* provides the minimal alignment restriction for BMK_timedFnState_t */
+    BMK_timedFnState_t* const r = (BMK_timedFnState_t*)buffer;
+    if (buffer == NULL) return NULL;
+    if (size < sizeof(struct BMK_timedFnState_s)) return NULL;
+    if ((size_t)buffer % tfs_alignment) return NULL;  /* buffer must be properly aligned */
+    BMK_resetTimedFnState(r, total_ms, run_ms);
+    return r;
 }

 void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms, unsigned run_ms)
@@ -184,9 +187,9 @@ void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms,
    if (!run_ms) run_ms = 1;
    if (run_ms > total_ms) run_ms = total_ms;
    timedFnState->timeSpent_ns = 0;
-    timedFnState->timeBudget_ns = (U64)total_ms * TIMELOOP_NANOSEC / 1000;
-    timedFnState->runBudget_ns = (U64)run_ms * TIMELOOP_NANOSEC / 1000;
-    timedFnState->fastestRun.nanoSecPerRun = (U64)(-1LL);
+    timedFnState->timeBudget_ns = (PTime)total_ms * TIMELOOP_NANOSEC / 1000;
+    timedFnState->runBudget_ns = (PTime)run_ms * TIMELOOP_NANOSEC / 1000;
+    timedFnState->fastestRun.nanoSecPerRun = (double)TIMELOOP_NANOSEC * 2000000000;  /* hopefully large enough : must be larger than any potential measurement */
    timedFnState->fastestRun.sumOfReturn = (size_t)(-1LL);
    timedFnState->nbLoops = 1;
    timedFnState->coolTime = UTIL_getTime();
@@ -208,37 +211,27 @@ int BMK_isCompleted_TimedFn(const BMK_timedFnState_t* timedFnState)
 BMK_runOutcome_t BMK_benchTimedFn(BMK_timedFnState_t* cont,
                                  BMK_benchParams_t p)
 {
-    U64 const runBudget_ns = cont->runBudget_ns;
-    U64 const runTimeMin_ns = runBudget_ns / 2;
+    PTime const runBudget_ns = cont->runBudget_ns;
+    PTime const runTimeMin_ns = runBudget_ns / 2;
    int completed = 0;
    BMK_runTime_t bestRunTime = cont->fastestRun;

    while (!completed) {
-        BMK_runOutcome_t runResult;
-
-        /* Overheat protection */
-        if (UTIL_clockSpanMicro(cont->coolTime) > ACTIVEPERIOD_MICROSEC) {
-            DEBUGOUTPUT("\rcooling down ...    \r");
-            UTIL_sleep(COOLPERIOD_SEC);
-            cont->coolTime = UTIL_getTime();
-        }
-
-        /* reinitialize capacity */
-        runResult = BMK_benchFunction(p, cont->nbLoops);
+        BMK_runOutcome_t const runResult = BMK_benchFunction(p, cont->nbLoops);

        if(!BMK_isSuccessful_runOutcome(runResult)) { /* error : move out */
            return runResult;
        }

        {   BMK_runTime_t const newRunTime = BMK_extract_runTime(runResult);
-            U64 const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops;
+            double const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops;

-            cont->timeSpent_ns += loopDuration_ns;
+            cont->timeSpent_ns += (unsigned long long)loopDuration_ns;

            /* estimate nbLoops for next run to last approximately 1 second */
            if (loopDuration_ns > (runBudget_ns / 50)) {
-                U64 const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun);
-                cont->nbLoops = (U32)(runBudget_ns / fastestRun_ns) + 1;
+                double const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun);
+                cont->nbLoops = (unsigned)(runBudget_ns / fastestRun_ns) + 1;
            } else {
                /* previous run was too short : blindly increase workload by x multiplier */
                const unsigned multiplier = 10;
@@ -31,7 +31,7 @@ extern "C" {
 /* BMK_runTime_t: valid result return type */

 typedef struct {
-    unsigned long long nanoSecPerRun;  /* time per iteration (over all blocks) */
+    double nanoSecPerRun;  /* time per iteration (over all blocks) */
    size_t sumOfReturn;         /* sum of return values */
 } BMK_runTime_t;

@@ -58,30 +58,31 @@ typedef size_t (*BMK_initFn_t)(void* initPayload);
 typedef unsigned (*BMK_errorFn_t)(size_t);


-/* BMK_benchFunction() parameters are provided through following structure.
- * This is preferable for readability,
- * as the number of parameters required is pretty large.
+/* BMK_benchFunction() parameters are provided via the following structure.
+ * A structure is preferable for readability,
+ * as the number of parameters required is fairly large.
 * No initializer is provided, because it doesn't make sense to provide some "default" :
- * all parameters should be specified by the caller */
+ * all parameters must be specified by the caller.
+ * optional parameters are labelled explicitly, and accept value NULL when not used */
 typedef struct {
-    BMK_benchFn_t benchFn;   /* the function to benchmark, over the set of blocks */
-    void* benchPayload;      /* pass custom parameters to benchFn  :
-                              * (*benchFn)(srcBuffers[i], srcSizes[i], dstBuffers[i], dstCapacities[i], benchPayload) */
-    BMK_initFn_t initFn;     /* (*initFn)(initPayload) is run once per run, at the beginning. */
-    void* initPayload;       /* Both arguments can be NULL, in which case nothing is run. */
-    BMK_errorFn_t errorFn;   /* errorFn will check each return value of benchFn over each block, to determine if it failed or not.
-                              * errorFn can be NULL, in which case no check is performed.
-                              * errorFn must return 0 when benchFn was successful, and >= 1 if it detects an error.
-                              * Execution is stopped as soon as an error is detected.
-                              * the triggering return value can be retrieved using BMK_extract_errorResult(). */
-    size_t blockCount;       /* number of blocks to operate benchFn on.
-                              * It's also the size of all array parameters :
-                              * srcBuffers, srcSizes, dstBuffers, dstCapacities, blockResults */
-    const void *const * srcBuffers; /* array of buffers to be operated on by benchFn */
-    const size_t* srcSizes;  /* array of the sizes of srcBuffers buffers */
-    void *const * dstBuffers;/* array of buffers to be written into by benchFn */
-    const size_t* dstCapacities; /* array of the capacities of dstBuffers buffers */
-    size_t* blockResults;    /* Optional: store the return value of benchFn for each block. Use NULL if this result is not requested. */
+    BMK_benchFn_t benchFn;    /* the function to benchmark, over the set of blocks */
+    void* benchPayload;       /* pass custom parameters to benchFn  :
+                               * (*benchFn)(srcBuffers[i], srcSizes[i], dstBuffers[i], dstCapacities[i], benchPayload) */
+    BMK_initFn_t initFn;      /* (*initFn)(initPayload) is run once per run, at the beginning. */
+    void* initPayload;        /* Both arguments can be NULL, in which case nothing is run. */
+    BMK_errorFn_t errorFn;    /* errorFn will check each return value of benchFn over each block, to determine if it failed or not.
+                               * errorFn can be NULL, in which case no check is performed.
+                               * errorFn must return 0 when benchFn was successful, and >= 1 if it detects an error.
+                               * Execution is stopped as soon as an error is detected.
+                               * the triggering return value can be retrieved using BMK_extract_errorResult(). */
+    size_t blockCount;        /* number of blocks to operate benchFn on.
+                               * It's also the size of all array parameters :
+                               * srcBuffers, srcSizes, dstBuffers, dstCapacities, blockResults */
+    const void *const * srcBuffers; /* read-only array of buffers to be operated on by benchFn */
+    const size_t* srcSizes;   /* read-only array containing sizes of srcBuffers */
+    void *const * dstBuffers; /* array of buffers to be written into by benchFn. This array is not optional, it must be provided even if unused by benchfn. */
+    const size_t* dstCapacities; /* read-only array containing capacities of dstBuffers. This array must be present. */
+    size_t* blockResults;     /* Optional: store the return value of benchFn for each block. Use NULL if this result is not requested. */
 } BMK_benchParams_t;


@@ -159,6 +160,21 @@ void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms,
 void BMK_freeTimedFnState(BMK_timedFnState_t* state);


+/* BMK_timedFnState_shell and BMK_initStatic_timedFnState() :
+ * Makes it possible to statically allocate a BMK_timedFnState_t on stack.
+ * BMK_timedFnState_shell is only there to allocate space,
+ * never ever access its members.
+ * BMK_timedFnState_t() actually accepts any buffer.
+ * It will check if provided buffer is large enough and is correctly aligned,
+ * and will return NULL if conditions are not respected.
+ */
+#define BMK_TIMEDFNSTATE_SIZE 64
+typedef union {
+    char never_access_space[BMK_TIMEDFNSTATE_SIZE];
+    long long alignment_enforcer;  /* must be aligned on 8-bytes boundaries */
+} BMK_timedFnState_shell;
+BMK_timedFnState_t* BMK_initStatic_timedFnState(void* buffer, size_t size, unsigned total_ms, unsigned run_ms);
+

 #endif   /* BENCH_FN_H_23876 */

@@ -28,6 +28,7 @@
 #include <errno.h>
 #include <assert.h>      /* assert */

+#include "timefn.h"      /* UTIL_time_t */
 #include "benchfn.h"
 #include "mem.h"
 #define ZSTD_STATIC_LINKING_ONLY
@@ -135,7 +136,8 @@ BMK_advancedParams_t BMK_initAdvancedParams(void) {
        0, /* ldmMinMatch */
        0, /* ldmHashLog */
        0, /* ldmBuckSizeLog */
-        0  /* ldmHashRateLog */
+        0,  /* ldmHashRateLog */
+        ZSTD_lcm_auto /* literalCompressionMode */
    };
    return res;
 }
@@ -159,9 +161,13 @@ typedef struct {
 #define MIN(a,b)    ((a) < (b) ? (a) : (b))
 #define MAX(a,b)    ((a) > (b) ? (a) : (b))

-static void BMK_initCCtx(ZSTD_CCtx* ctx,
-    const void* dictBuffer, size_t dictBufferSize, int cLevel,
-    const ZSTD_compressionParameters* comprParams, const BMK_advancedParams_t* adv) {
+static void
+BMK_initCCtx(ZSTD_CCtx* ctx,
+            const void* dictBuffer, size_t dictBufferSize,
+            int cLevel,
+            const ZSTD_compressionParameters* comprParams,
+            const BMK_advancedParams_t* adv)
+{
    ZSTD_CCtx_reset(ctx, ZSTD_reset_session_and_parameters);
    if (adv->nbWorkers==1) {
        CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_nbWorkers, 0));
@@ -174,12 +180,13 @@ static void BMK_initCCtx(ZSTD_CCtx* ctx,
    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmHashLog, adv->ldmHashLog));
    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmBucketSizeLog, adv->ldmBucketSizeLog));
    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmHashRateLog, adv->ldmHashRateLog));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_windowLog, comprParams->windowLog));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_hashLog, comprParams->hashLog));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_chainLog, comprParams->chainLog));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_searchLog, comprParams->searchLog));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_minMatch, comprParams->minMatch));
-    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_targetLength, comprParams->targetLength));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_windowLog, (int)comprParams->windowLog));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_hashLog, (int)comprParams->hashLog));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_chainLog, (int)comprParams->chainLog));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_searchLog, (int)comprParams->searchLog));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_minMatch, (int)comprParams->minMatch));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_targetLength, (int)comprParams->targetLength));
+    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_literalCompressionMode, (int)adv->literalCompressionMode));
    CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_strategy, comprParams->strategy));
    CHECK_Z(ZSTD_CCtx_loadDictionary(ctx, dictBuffer, dictBufferSize));
 }
@@ -376,7 +383,7 @@ BMK_benchMemAdvancedNoAlloc(
        }
    }

-    /* warmimg up `compressedBuffer` */
+    /* warming up `compressedBuffer` */
    if (adv->mode == BMK_decodeOnly) {
        memcpy(compressedBuffer, srcBuffer, loadedCompressedSize);
    } else {
@@ -444,7 +451,7 @@ BMK_benchMemAdvancedNoAlloc(
                    cSize = cResult.sumOfReturn;
                    ratio = (double)srcSize / cSize;
                    {   BMK_benchResult_t newResult;
-                        newResult.cSpeed = ((U64)srcSize * TIMELOOP_NANOSEC / cResult.nanoSecPerRun);
+                        newResult.cSpeed = (U64)((double)srcSize * TIMELOOP_NANOSEC / cResult.nanoSecPerRun);
                        benchResult.cSize = cSize;
                        if (newResult.cSpeed > benchResult.cSpeed)
                            benchResult.cSpeed = newResult.cSpeed;
@@ -468,7 +475,7 @@ BMK_benchMemAdvancedNoAlloc(
                }

                {   BMK_runTime_t const dResult = BMK_extract_runTime(dOutcome);
-                    U64 const newDSpeed = (srcSize * TIMELOOP_NANOSEC / dResult.nanoSecPerRun);
+                    U64 const newDSpeed = (U64)((double)srcSize * TIMELOOP_NANOSEC / dResult.nanoSecPerRun);
                    if (newDSpeed > benchResult.dSpeed)
                        benchResult.dSpeed = newDSpeed;
                }
@@ -505,17 +512,21 @@ BMK_benchMemAdvancedNoAlloc(
                        pos = (U32)(u - bacc);
                        bNb = pos / (128 KB);
                        DISPLAY("(sample %u, block %u, pos %u) \n", segNb, bNb, pos);
-                        if (u>5) {
-                            int n;
+                        {   size_t const lowest = (u>5) ? 5 : u;
+                            size_t n;
                            DISPLAY("origin: ");
-                            for (n=-5; n<0; n++) DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]);
+                            for (n=lowest; n>0; n--)
+                                DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u-n]);
                            DISPLAY(" :%02X:  ", ((const BYTE*)srcBuffer)[u]);
-                            for (n=1; n<3; n++) DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]);
+                            for (n=1; n<3; n++)
+                                DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]);
                            DISPLAY(" \n");
                            DISPLAY("decode: ");
-                            for (n=-5; n<0; n++) DISPLAY("%02X ", resultBuffer[u+n]);
+                            for (n=lowest; n>0; n++)
+                                DISPLAY("%02X ", resultBuffer[u-n]);
                            DISPLAY(" :%02X:  ", resultBuffer[u]);
-                            for (n=1; n<3; n++) DISPLAY("%02X ", resultBuffer[u+n]);
+                            for (n=1; n<3; n++)
+                                DISPLAY("%02X ", resultBuffer[u+n]);
                            DISPLAY(" \n");
                        }
                        break;
@@ -105,17 +105,18 @@ typedef enum {
 } BMK_mode_t;

 typedef struct {
-    BMK_mode_t mode;            /* 0: all, 1: compress only 2: decode only */
-    unsigned nbSeconds;         /* default timing is in nbSeconds */
-    size_t blockSize;           /* Maximum size of each block*/
-    unsigned nbWorkers;         /* multithreading */
-    unsigned realTime;          /* real time priority */
-    int additionalParam;        /* used by python speed benchmark */
-    unsigned ldmFlag;           /* enables long distance matching */
-    unsigned ldmMinMatch;       /* below: parameters for long distance matching, see zstd.1.md */
-    unsigned ldmHashLog;
-    unsigned ldmBucketSizeLog;
-    unsigned ldmHashRateLog;
+    BMK_mode_t mode;        /* 0: all, 1: compress only 2: decode only */
+    unsigned nbSeconds;     /* default timing is in nbSeconds */
+    size_t blockSize;       /* Maximum size of each block*/
+    int nbWorkers;          /* multithreading */
+    unsigned realTime;      /* real time priority */
+    int additionalParam;    /* used by python speed benchmark */
+    int ldmFlag;            /* enables long distance matching */
+    int ldmMinMatch;        /* below: parameters for long distance matching, see zstd.1.md */
+    int ldmHashLog;
+    int ldmBucketSizeLog;
+    int ldmHashRateLog;
+    ZSTD_literalCompressionMode_e literalCompressionMode;
 } BMK_advancedParams_t;

 /* returns default parameters used by nonAdvanced functions */
@@ -169,7 +170,7 @@ BMK_benchOutcome_t BMK_syntheticTest(
 *  comprParams - basic compression parameters
 *  dictBuffer - a dictionary if used, null otherwise
 *  dictBufferSize - size of dictBuffer, 0 otherwise
- *  diplayLevel - see BMK_benchFiles
+ *  displayLevel - see BMK_benchFiles
 *  displayName - name used by display
 * @return:
 *      a variant, which expresses either an error, or a valid result.
@@ -29,6 +29,7 @@
 #include <errno.h>          /* errno */
 #include <assert.h>

+#include "timefn.h"         /* UTIL_time_t, UTIL_clockSpanMicro, UTIL_getTime */
 #include "mem.h"            /* read */
 #include "error_private.h"
 #include "dibio.h"
@@ -24,13 +24,14 @@
 *  Includes
 ***************************************/
 #include "platform.h"   /* Large Files support, SET_BINARY_MODE */
-#include "util.h"       /* UTIL_getFileSize, UTIL_isRegularFile */
+#include "util.h"       /* UTIL_getFileSize, UTIL_isRegularFile, UTIL_isSameFile */
 #include <stdio.h>      /* fprintf, fopen, fread, _fileno, stdin, stdout */
 #include <stdlib.h>     /* malloc, free */
 #include <string.h>     /* strcmp, strlen */
 #include <assert.h>
 #include <errno.h>      /* errno */
 #include <signal.h>
+#include "timefn.h"     /* UTIL_getTime, UTIL_clockSpanMicro */

 #if defined (_MSC_VER)
 #  include <sys/stat.h>
@@ -79,23 +80,29 @@
 /*-*************************************
 *  Macros
 ***************************************/
+
+struct FIO_display_prefs_s {
+    int displayLevel;   /* 0 : no display;  1: errors;  2: + result + interaction + warnings;  3: + progression;  4: + information */
+    U32 noProgress;
+};
+
+static FIO_display_prefs_t g_display_prefs = {2, 0};
+
 #define DISPLAY(...)         fprintf(stderr, __VA_ARGS__)
 #define DISPLAYOUT(...)      fprintf(stdout, __VA_ARGS__)
-#define DISPLAYLEVEL(l, ...) { if (g_displayLevel>=l) { DISPLAY(__VA_ARGS__); } }
-static int g_displayLevel = 2;   /* 0 : no display;  1: errors;  2: + result + interaction + warnings;  3: + progression;  4: + information */
-void FIO_setNotificationLevel(unsigned level) { g_displayLevel=level; }
+#define DISPLAYLEVEL(l, ...) { if (g_display_prefs.displayLevel>=l) { DISPLAY(__VA_ARGS__); } }

 static const U64 g_refreshRate = SEC_TO_MICRO / 6;
 static UTIL_time_t g_displayClock = UTIL_TIME_INITIALIZER;

-#define READY_FOR_UPDATE() (!g_noProgress && UTIL_clockSpanMicro(g_displayClock) > g_refreshRate)
+#define READY_FOR_UPDATE() (!g_display_prefs.noProgress && UTIL_clockSpanMicro(g_displayClock) > g_refreshRate)
 #define DELAY_NEXT_UPDATE() { g_displayClock = UTIL_getTime(); }
 #define DISPLAYUPDATE(l, ...) {                              \
-        if (g_displayLevel>=l && !g_noProgress) {            \
-            if (READY_FOR_UPDATE() || (g_displayLevel>=4)) { \
+        if (g_display_prefs.displayLevel>=l && !g_display_prefs.noProgress) {            \
+            if (READY_FOR_UPDATE() || (g_display_prefs.displayLevel>=4)) { \
                DELAY_NEXT_UPDATE();                         \
                DISPLAY(__VA_ARGS__);                        \
-                if (g_displayLevel>=4) fflush(stderr);       \
+                if (g_display_prefs.displayLevel>=4) fflush(stderr);       \
    }   }   }

 #undef MIN  /* in case it would be already defined */
@@ -168,7 +175,7 @@ static void clearHandler(void)

 #if !defined(BACKTRACE_ENABLE)
 /* automatic detector : backtrace enabled by default on linux+glibc and osx */
-#  if (defined(__linux__) && defined(__GLIBC__)) \
+#  if (defined(__linux__) && (defined(__GLIBC__) && !defined(__UCLIBC__))) \
     || (defined(__APPLE__) && defined(__MACH__))
 #    define BACKTRACE_ENABLE 1
 #  else
@@ -189,7 +196,7 @@ static void ABRThandler(int sig) {
    const char* name;
    void* addrlist[MAX_STACK_FRAMES];
    char** symbollist;
-    U32 addrlen, i;
+    int addrlen, i;

    switch (sig) {
        case SIGABRT: name = "SIGABRT"; break;
@@ -237,10 +244,13 @@ void FIO_addAbortHandler()
 ***************************************************************/
 #if defined(_MSC_VER) && _MSC_VER >= 1400
 #   define LONG_SEEK _fseeki64
+#   define LONG_TELL _ftelli64
 #elif !defined(__64BIT__) && (PLATFORM_POSIX_VERSION >= 200112L) /* No point defining Large file for 64 bit */
 #  define LONG_SEEK fseeko
+#  define LONG_TELL ftello
 #elif defined(__MINGW32__) && !defined(__STRICT_ANSI__) && !defined(__NO_MINGW_LFS) && defined(__MSVCRT__)
 #   define LONG_SEEK fseeko64
+#   define LONG_TELL ftello64
 #elif defined(_WIN32) && !defined(__DJGPP__)
 #   include <windows.h>
    static int LONG_SEEK(FILE* file, __int64 offset, int origin) {
@@ -259,102 +269,198 @@ void FIO_addAbortHandler()
        else
            return -1;
    }
+    static __int64 LONG_TELL(FILE* file) {
+        LARGE_INTEGER off, newOff;
+        off.QuadPart = 0;
+        newOff.QuadPart = 0;
+        SetFilePointerEx((HANDLE) _get_osfhandle(_fileno(file)), off, &newOff, FILE_CURRENT);
+        return newOff.QuadPart;
+    }
 #else
 #   define LONG_SEEK fseek
+#   define LONG_TELL ftell
 #endif


 /*-*************************************
-*  Local Parameters - Not thread safe
+*  Parameters: Typedefs
 ***************************************/
-static FIO_compressionType_t g_compressionType = FIO_zstdCompression;
-void FIO_setCompressionType(FIO_compressionType_t compressionType) { g_compressionType = compressionType; }
-static U32 g_overwrite = 0;
-void FIO_overwriteMode(void) { g_overwrite = 1; }
-static U32 g_sparseFileSupport = ZSTD_SPARSE_DEFAULT;   /* 0: no sparse allowed; 1: auto (file yes, stdout no); 2: force sparse */
-void FIO_setSparseWrite(unsigned sparse) { g_sparseFileSupport = sparse; }
-static U32 g_dictIDFlag = 1;
-void FIO_setDictIDFlag(unsigned dictIDFlag) { g_dictIDFlag = dictIDFlag; }
-static U32 g_checksumFlag = 1;
-void FIO_setChecksumFlag(unsigned checksumFlag) { g_checksumFlag = checksumFlag; }
-static U32 g_removeSrcFile = 0;
-void FIO_setRemoveSrcFile(unsigned flag) { g_removeSrcFile = (flag>0); }
-static unsigned g_memLimit = 0;
-void FIO_setMemLimit(unsigned memLimit) { g_memLimit = memLimit; }
-static unsigned g_nbWorkers = 1;
-void FIO_setNbWorkers(unsigned nbWorkers) {
+
+struct FIO_prefs_s {
+
+    /* Algorithm preferences */
+    FIO_compressionType_t compressionType;
+    U32 sparseFileSupport;   /* 0: no sparse allowed; 1: auto (file yes, stdout no); 2: force sparse */
+    int dictIDFlag;
+    int checksumFlag;
+    int blockSize;
+    int overlapLog;
+    U32 adaptiveMode;
+    int rsyncable;
+    int minAdaptLevel;
+    int maxAdaptLevel;
+    int ldmFlag;
+    int ldmHashLog;
+    int ldmMinMatch;
+    int ldmBucketSizeLog;
+    int ldmHashRateLog;
+    size_t targetCBlockSize;
+    ZSTD_literalCompressionMode_e literalCompressionMode;
+
+    /* IO preferences */
+    U32 removeSrcFile;
+    U32 overwrite;
+
+    /* Computation resources preferences */
+    unsigned memLimit;
+    int nbWorkers;
+};
+
+
+/*-*************************************
+*  Parameters: Initialization
+***************************************/
+
+#define FIO_OVERLAP_LOG_NOTSET 9999
+#define FIO_LDM_PARAM_NOTSET 9999
+
+
+FIO_prefs_t* FIO_createPreferences(void)
+{
+    FIO_prefs_t* const ret = (FIO_prefs_t*)malloc(sizeof(FIO_prefs_t));
+    if (!ret) EXM_THROW(21, "Allocation error : not enough memory");
+
+    ret->compressionType = FIO_zstdCompression;
+    ret->overwrite = 0;
+    ret->sparseFileSupport = ZSTD_SPARSE_DEFAULT;
+    ret->dictIDFlag = 1;
+    ret->checksumFlag = 1;
+    ret->removeSrcFile = 0;
+    ret->memLimit = 0;
+    ret->nbWorkers = 1;
+    ret->blockSize = 0;
+    ret->overlapLog = FIO_OVERLAP_LOG_NOTSET;
+    ret->adaptiveMode = 0;
+    ret->rsyncable = 0;
+    ret->minAdaptLevel = -50;   /* initializing this value requires a constant, so ZSTD_minCLevel() doesn't work */
+    ret->maxAdaptLevel = 22;   /* initializing this value requires a constant, so ZSTD_maxCLevel() doesn't work */
+    ret->ldmFlag = 0;
+    ret->ldmHashLog = 0;
+    ret->ldmMinMatch = 0;
+    ret->ldmBucketSizeLog = FIO_LDM_PARAM_NOTSET;
+    ret->ldmHashRateLog = FIO_LDM_PARAM_NOTSET;
+    ret->targetCBlockSize = 0;
+    ret->literalCompressionMode = ZSTD_lcm_auto;
+    return ret;
+}
+
+void FIO_freePreferences(FIO_prefs_t* const prefs)
+{
+    free(prefs);
+}
+
+
+/*-*************************************
+*  Parameters: Display Options
+***************************************/
+
+void FIO_setNotificationLevel(int level) { g_display_prefs.displayLevel=level; }
+
+void FIO_setNoProgress(unsigned noProgress) { g_display_prefs.noProgress = noProgress; }
+
+
+/*-*************************************
+*  Parameters: Setters
+***************************************/
+
+void FIO_setCompressionType(FIO_prefs_t* const prefs, FIO_compressionType_t compressionType) { prefs->compressionType = compressionType; }
+
+void FIO_overwriteMode(FIO_prefs_t* const prefs) { prefs->overwrite = 1; }
+
+void FIO_setSparseWrite(FIO_prefs_t* const prefs, unsigned sparse) { prefs->sparseFileSupport = sparse; }
+
+void FIO_setDictIDFlag(FIO_prefs_t* const prefs, int dictIDFlag) { prefs->dictIDFlag = dictIDFlag; }
+
+void FIO_setChecksumFlag(FIO_prefs_t* const prefs, int checksumFlag) { prefs->checksumFlag = checksumFlag; }
+
+void FIO_setRemoveSrcFile(FIO_prefs_t* const prefs, unsigned flag) { prefs->removeSrcFile = (flag>0); }
+
+void FIO_setMemLimit(FIO_prefs_t* const prefs, unsigned memLimit) { prefs->memLimit = memLimit; }
+
+void FIO_setNbWorkers(FIO_prefs_t* const prefs, int nbWorkers) {
 #ifndef ZSTD_MULTITHREAD
    if (nbWorkers > 0) DISPLAYLEVEL(2, "Note : multi-threading is disabled \n");
 #endif
-    g_nbWorkers = nbWorkers;
+    prefs->nbWorkers = nbWorkers;
 }
-static U32 g_blockSize = 0;
-void FIO_setBlockSize(unsigned blockSize) {
-    if (blockSize && g_nbWorkers==0)
+
+void FIO_setBlockSize(FIO_prefs_t* const prefs, int blockSize) {
+    if (blockSize && prefs->nbWorkers==0)
        DISPLAYLEVEL(2, "Setting block size is useless in single-thread mode \n");
-    g_blockSize = blockSize;
+    prefs->blockSize = blockSize;
 }
-#define FIO_OVERLAP_LOG_NOTSET 9999
-static unsigned g_overlapLog = FIO_OVERLAP_LOG_NOTSET;
-void FIO_setOverlapLog(unsigned overlapLog){
-    if (overlapLog && g_nbWorkers==0)
+
+void FIO_setOverlapLog(FIO_prefs_t* const prefs, int overlapLog){
+    if (overlapLog && prefs->nbWorkers==0)
        DISPLAYLEVEL(2, "Setting overlapLog is useless in single-thread mode \n");
-    g_overlapLog = overlapLog;
+    prefs->overlapLog = overlapLog;
 }
-static U32 g_adaptiveMode = 0;
-void FIO_setAdaptiveMode(unsigned adapt) {
-    if ((adapt>0) && (g_nbWorkers==0))
+
+void FIO_setAdaptiveMode(FIO_prefs_t* const prefs, unsigned adapt) {
+    if ((adapt>0) && (prefs->nbWorkers==0))
        EXM_THROW(1, "Adaptive mode is not compatible with single thread mode \n");
-    g_adaptiveMode = adapt;
+    prefs->adaptiveMode = adapt;
 }
-static U32 g_rsyncable = 0;
-void FIO_setRsyncable(unsigned rsyncable) {
-    if ((rsyncable>0) && (g_nbWorkers==0))
+
+void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable) {
+    if ((rsyncable>0) && (prefs->nbWorkers==0))
        EXM_THROW(1, "Rsyncable mode is not compatible with single thread mode \n");
-    g_rsyncable = rsyncable;
+    prefs->rsyncable = rsyncable;
 }
-static int g_minAdaptLevel = -50;   /* initializing this value requires a constant, so ZSTD_minCLevel() doesn't work */
-void FIO_setAdaptMin(int minCLevel)
+
+void FIO_setTargetCBlockSize(FIO_prefs_t* const prefs, size_t targetCBlockSize) {
+    prefs->targetCBlockSize = targetCBlockSize;
+}
+
+void FIO_setLiteralCompressionMode(
+        FIO_prefs_t* const prefs,
+        ZSTD_literalCompressionMode_e mode) {
+    prefs->literalCompressionMode = mode;
+}
+
+void FIO_setAdaptMin(FIO_prefs_t* const prefs, int minCLevel)
 {
 #ifndef ZSTD_NOCOMPRESS
    assert(minCLevel >= ZSTD_minCLevel());
 #endif
-    g_minAdaptLevel = minCLevel;
+    prefs->minAdaptLevel = minCLevel;
 }
-static int g_maxAdaptLevel = 22;   /* initializing this value requires a constant, so ZSTD_maxCLevel() doesn't work */
-void FIO_setAdaptMax(int maxCLevel)
+
+void FIO_setAdaptMax(FIO_prefs_t* const prefs, int maxCLevel)
 {
-    g_maxAdaptLevel = maxCLevel;
+    prefs->maxAdaptLevel = maxCLevel;
 }

-static U32 g_ldmFlag = 0;
-void FIO_setLdmFlag(unsigned ldmFlag) {
-    g_ldmFlag = (ldmFlag>0);
-}
-static U32 g_ldmHashLog = 0;
-void FIO_setLdmHashLog(unsigned ldmHashLog) {
-    g_ldmHashLog = ldmHashLog;
-}
-static U32 g_ldmMinMatch = 0;
-void FIO_setLdmMinMatch(unsigned ldmMinMatch) {
-    g_ldmMinMatch = ldmMinMatch;
+void FIO_setLdmFlag(FIO_prefs_t* const prefs, unsigned ldmFlag) {
+    prefs->ldmFlag = (ldmFlag>0);
 }

-#define FIO_LDM_PARAM_NOTSET 9999
-static U32 g_ldmBucketSizeLog = FIO_LDM_PARAM_NOTSET;
-void FIO_setLdmBucketSizeLog(unsigned ldmBucketSizeLog) {
-    g_ldmBucketSizeLog = ldmBucketSizeLog;
+void FIO_setLdmHashLog(FIO_prefs_t* const prefs, int ldmHashLog) {
+    prefs->ldmHashLog = ldmHashLog;
 }

-static U32 g_ldmHashRateLog = FIO_LDM_PARAM_NOTSET;
-void FIO_setLdmHashRateLog(unsigned ldmHashRateLog) {
-    g_ldmHashRateLog = ldmHashRateLog;
-}
-static U32 g_noProgress = 0;
-void FIO_setNoProgress(unsigned noProgress) {
-    g_noProgress = noProgress;
+void FIO_setLdmMinMatch(FIO_prefs_t* const prefs, int ldmMinMatch) {
+    prefs->ldmMinMatch = ldmMinMatch;
 }

+void FIO_setLdmBucketSizeLog(FIO_prefs_t* const prefs, int ldmBucketSizeLog) {
+    prefs->ldmBucketSizeLog = ldmBucketSizeLog;
+}
+
+
+void FIO_setLdmHashRateLog(FIO_prefs_t* const prefs, int ldmHashRateLog) {
+    prefs->ldmHashRateLog = ldmHashRateLog;
+}


 /*-*************************************
@@ -410,45 +516,27 @@ static FILE* FIO_openSrcFile(const char* srcFileName)
 /** FIO_openDstFile() :
 *  condition : `dstFileName` must be non-NULL.
 * @result : FILE* to `dstFileName`, or NULL if it fails */
-static FILE* FIO_openDstFile(const char* srcFileName, const char* dstFileName)
+static FILE* FIO_openDstFile(FIO_prefs_t* const prefs, const char* srcFileName, const char* dstFileName)
 {
    assert(dstFileName != NULL);
    if (!strcmp (dstFileName, stdoutmark)) {
        DISPLAYLEVEL(4,"Using stdout for output \n");
        SET_BINARY_MODE(stdout);
-        if (g_sparseFileSupport == 1) {
-            g_sparseFileSupport = 0;
+        if (prefs->sparseFileSupport == 1) {
+            prefs->sparseFileSupport = 0;
            DISPLAYLEVEL(4, "Sparse File Support is automatically disabled on stdout ; try --sparse \n");
        }
        return stdout;
    }

-    /* ensure dst is not the same file as src */
-    if (srcFileName != NULL) {
-#ifdef _MSC_VER
-        /* note : Visual does not support file identification by inode.
-         *        The following work-around is limited to detecting exact name repetition only,
-         *        aka `filename` is considered different from `subdir/../filename` */
-        if (!strcmp(srcFileName, dstFileName)) {
-            DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n");
-            return NULL;
-        }
-#else
-        stat_t srcStat;
-        stat_t dstStat;
-        if (UTIL_getFileStat(srcFileName, &srcStat)
-            && UTIL_getFileStat(dstFileName, &dstStat)) {
-            if (srcStat.st_dev == dstStat.st_dev
-                && srcStat.st_ino == dstStat.st_ino) {
-                DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n");
-                return NULL;
-            }
-        }
-#endif
+    /* ensure dst is not the same as src */
+    if (srcFileName != NULL && UTIL_isSameFile(srcFileName, dstFileName)) {
+        DISPLAYLEVEL(1, "zstd: Refusing to open an output file which will overwrite the input file \n");
+        return NULL;
    }

-    if (g_sparseFileSupport == 1) {
-        g_sparseFileSupport = ZSTD_SPARSE_DEFAULT;
+    if (prefs->sparseFileSupport == 1) {
+        prefs->sparseFileSupport = ZSTD_SPARSE_DEFAULT;
    }

    if (UTIL_isRegularFile(dstFileName)) {
@@ -460,8 +548,8 @@ static FILE* FIO_openDstFile(const char* srcFileName, const char* dstFileName)
        }
        if (fCheck != NULL) {  /* dst file exists, authorization prompt */
            fclose(fCheck);
-            if (!g_overwrite) {
-                if (g_displayLevel <= 1) {
+            if (!prefs->overwrite) {
+                if (g_display_prefs.displayLevel <= 1) {
                    /* No interaction possible */
                    DISPLAY("zstd: %s already exists; not overwritten  \n",
                            dstFileName);
@@ -482,8 +570,11 @@ static FILE* FIO_openDstFile(const char* srcFileName, const char* dstFileName)
    }   }

    {   FILE* const f = fopen( dstFileName, "wb" );
-        if (f == NULL)
+        if (f == NULL) {
            DISPLAYLEVEL(1, "zstd: %s: %s\n", dstFileName, strerror(errno));
+        } else {
+            chmod(dstFileName, 00600);
+        }
        return f;
    }
 }
@@ -536,10 +627,12 @@ typedef struct {
    size_t srcBufferSize;
    void*  dstBuffer;
    size_t dstBufferSize;
+    const char* dictFileName;
    ZSTD_CStream* cctx;
 } cRess_t;

-static cRess_t FIO_createCResources(const char* dictFileName, int cLevel,
+static cRess_t FIO_createCResources(FIO_prefs_t* const prefs,
+                                    const char* dictFileName, int cLevel,
                                    U64 srcSize,
                                    ZSTD_compressionParameters comprParams) {
    cRess_t ress;
@@ -562,43 +655,47 @@ static cRess_t FIO_createCResources(const char* dictFileName, int cLevel,
        size_t const dictBuffSize = FIO_createDictBuffer(&dictBuffer, dictFileName);   /* works with dictFileName==NULL */
        if (dictFileName && (dictBuffer==NULL))
            EXM_THROW(32, "allocation error : can't create dictBuffer");
+        ress.dictFileName = dictFileName;

-        if (g_adaptiveMode && !g_ldmFlag && !comprParams.windowLog)
+        if (prefs->adaptiveMode && !prefs->ldmFlag && !comprParams.windowLog)
            comprParams.windowLog = ADAPT_WINDOWLOG_DEFAULT;

        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_contentSizeFlag, 1) );  /* always enable content size when available (note: supposed to be default) */
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_dictIDFlag, g_dictIDFlag) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, g_checksumFlag) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_dictIDFlag, prefs->dictIDFlag) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, prefs->checksumFlag) );
        /* compression level */
        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, cLevel) );
+        /* max compressed block size */
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetCBlockSize, (int)prefs->targetCBlockSize) );
        /* long distance matching */
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_enableLongDistanceMatching, g_ldmFlag) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashLog, g_ldmHashLog) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmMinMatch, g_ldmMinMatch) );
-        if (g_ldmBucketSizeLog != FIO_LDM_PARAM_NOTSET) {
-            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmBucketSizeLog, g_ldmBucketSizeLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_enableLongDistanceMatching, prefs->ldmFlag) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashLog, prefs->ldmHashLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmMinMatch, prefs->ldmMinMatch) );
+        if (prefs->ldmBucketSizeLog != FIO_LDM_PARAM_NOTSET) {
+            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmBucketSizeLog, prefs->ldmBucketSizeLog) );
        }
-        if (g_ldmHashRateLog != FIO_LDM_PARAM_NOTSET) {
-            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashRateLog, g_ldmHashRateLog) );
+        if (prefs->ldmHashRateLog != FIO_LDM_PARAM_NOTSET) {
+            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashRateLog, prefs->ldmHashRateLog) );
        }
        /* compression parameters */
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_windowLog, comprParams.windowLog) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_chainLog, comprParams.chainLog) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_hashLog, comprParams.hashLog) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_searchLog, comprParams.searchLog) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_minMatch, comprParams.minMatch) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetLength, comprParams.targetLength) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_windowLog, (int)comprParams.windowLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_chainLog, (int)comprParams.chainLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_hashLog, (int)comprParams.hashLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_searchLog, (int)comprParams.searchLog) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_minMatch, (int)comprParams.minMatch) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetLength, (int)comprParams.targetLength) );
        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_strategy, comprParams.strategy) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_literalCompressionMode, (int)prefs->literalCompressionMode) );
        /* multi-threading */
 #ifdef ZSTD_MULTITHREAD
-        DISPLAYLEVEL(5,"set nb workers = %u \n", g_nbWorkers);
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_nbWorkers, g_nbWorkers) );
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_jobSize, g_blockSize) );
-        if (g_overlapLog != FIO_OVERLAP_LOG_NOTSET) {
-            DISPLAYLEVEL(3,"set overlapLog = %u \n", g_overlapLog);
-            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_overlapLog, g_overlapLog) );
+        DISPLAYLEVEL(5,"set nb workers = %u \n", prefs->nbWorkers);
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_nbWorkers, prefs->nbWorkers) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_jobSize, prefs->blockSize) );
+        if (prefs->overlapLog != FIO_OVERLAP_LOG_NOTSET) {
+            DISPLAYLEVEL(3,"set overlapLog = %u \n", prefs->overlapLog);
+            CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_overlapLog, prefs->overlapLog) );
        }
-        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_rsyncable, g_rsyncable) );
+        CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_rsyncable, prefs->rsyncable) );
 #endif
        /* dictionary */
        CHECK( ZSTD_CCtx_setPledgedSrcSize(ress.cctx, srcSize) );  /* set the value temporarily for dictionary loading, to adapt compression parameters */
@@ -774,15 +871,19 @@ FIO_compressLzmaFrame(cRess_t* ress,
 #endif

 #ifdef ZSTD_LZ4COMPRESS
+
 #if LZ4_VERSION_NUMBER <= 10600
 #define LZ4F_blockLinked blockLinked
 #define LZ4F_max64KB max64KB
 #endif
+
 static int FIO_LZ4_GetBlockSize_FromBlockId (int id) { return (1 << (8 + (2 * id))); }
+
 static unsigned long long
 FIO_compressLz4Frame(cRess_t* ress,
                     const char* srcFileName, U64 const srcFileSize,
-                     int compressionLevel, U64* readsize)
+                     int compressionLevel, int checksumFlag,
+                     U64* readsize)
 {
    const size_t blockSize = FIO_LZ4_GetBlockSize_FromBlockId(LZ4F_max64KB);
    unsigned long long inFileSize = 0, outFileSize = 0;
@@ -802,7 +903,7 @@ FIO_compressLz4Frame(cRess_t* ress,
    prefs.compressionLevel = compressionLevel;
    prefs.frameInfo.blockMode = LZ4F_blockLinked;
    prefs.frameInfo.blockSizeID = LZ4F_max64KB;
-    prefs.frameInfo.contentChecksumFlag = (contentChecksum_t)g_checksumFlag;
+    prefs.frameInfo.contentChecksumFlag = (contentChecksum_t)checksumFlag;
 #if LZ4_VERSION_NUMBER >= 10600
    prefs.frameInfo.contentSize = (srcFileSize==UTIL_FILESIZE_UNKNOWN) ? 0 : srcFileSize;
 #endif
@@ -876,7 +977,8 @@ FIO_compressLz4Frame(cRess_t* ress,


 static unsigned long long
-FIO_compressZstdFrame(const cRess_t* ressPtr,
+FIO_compressZstdFrame(FIO_prefs_t* const prefs,
+                      const cRess_t* ressPtr,
                      const char* srcFileName, U64 fileSize,
                      int compressionLevel, U64* readsize)
 {
@@ -947,7 +1049,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
                double const cShare = (double)zfp.produced / (zfp.consumed + !zfp.consumed/*avoid div0*/) * 100;

                /* display progress notifications */
-                if (g_displayLevel >= 3) {
+                if (g_display_prefs.displayLevel >= 3) {
                    DISPLAYUPDATE(3, "\r(L%i) Buffered :%4u MB - Consumed :%4u MB - Compressed :%4u MB => %.2f%% ",
                                compressionLevel,
                                (unsigned)((zfp.ingested - zfp.consumed) >> 20),
@@ -963,7 +1065,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
                }

                /* adaptive mode : statistics measurement and speed correction */
-                if (g_adaptiveMode) {
+                if (prefs->adaptiveMode) {

                    /* check output speed */
                    if (zfp.currentJobID > 1) {  /* only possible if nbWorkers >= 1 */
@@ -971,12 +1073,12 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
                        unsigned long long newlyProduced = zfp.produced - previous_zfp_update.produced;
                        unsigned long long newlyFlushed = zfp.flushed - previous_zfp_update.flushed;
                        assert(zfp.produced >= previous_zfp_update.produced);
-                        assert(g_nbWorkers >= 1);
+                        assert(prefs->nbWorkers >= 1);

                        /* test if compression is blocked
                         * either because output is slow and all buffers are full
                         * or because input is slow and no job can start while waiting for at least one buffer to be filled.
-                         * note : excluse starting part, since currentJobID > 1 */
+                         * note : exclude starting part, since currentJobID > 1 */
                        if ( (zfp.consumed == previous_zfp_update.consumed)   /* no data compressed : no data available, or no more buffer to compress to, OR compression is really slow (compression of a single block is slower than update rate)*/
                          && (zfp.nbActiveWorkers == 0)                       /* confirmed : no compression ongoing */
                          ) {
@@ -1000,7 +1102,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
                        DISPLAYLEVEL(6, "compression level adaptation check \n")

                        /* check input speed */
-                        if (zfp.currentJobID > g_nbWorkers+1) {   /* warm up period, to fill all workers */
+                        if (zfp.currentJobID > (unsigned)(prefs->nbWorkers+1)) {   /* warm up period, to fill all workers */
                            if (inputBlocked <= 0) {
                                DISPLAYLEVEL(6, "input is never blocked => input is slower than ingestion \n");
                                speedChange = slower;
@@ -1032,14 +1134,14 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
                            DISPLAYLEVEL(6, "slower speed , higher compression \n")
                            compressionLevel ++;
                            if (compressionLevel > ZSTD_maxCLevel()) compressionLevel = ZSTD_maxCLevel();
-                            if (compressionLevel > g_maxAdaptLevel) compressionLevel = g_maxAdaptLevel;
+                            if (compressionLevel > prefs->maxAdaptLevel) compressionLevel = prefs->maxAdaptLevel;
                            compressionLevel += (compressionLevel == 0);   /* skip 0 */
                            ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, compressionLevel);
                        }
                        if (speedChange == faster) {
                            DISPLAYLEVEL(6, "faster speed , lighter compression \n")
                            compressionLevel --;
-                            if (compressionLevel < g_minAdaptLevel) compressionLevel = g_minAdaptLevel;
+                            if (compressionLevel < prefs->minAdaptLevel) compressionLevel = prefs->minAdaptLevel;
                            compressionLevel -= (compressionLevel == 0);   /* skip 0 */
                            ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, compressionLevel);
                        }
@@ -1069,20 +1171,23 @@ FIO_compressZstdFrame(const cRess_t* ressPtr,
 *            1 : missing or pb opening srcFileName
 */
 static int
-FIO_compressFilename_internal(cRess_t ress,
+FIO_compressFilename_internal(FIO_prefs_t* const prefs,
+                              cRess_t ress,
                              const char* dstFileName, const char* srcFileName,
                              int compressionLevel)
 {
+    UTIL_time_t const timeStart = UTIL_getTime();
+    clock_t const cpuStart = clock();
    U64 readsize = 0;
    U64 compressedfilesize = 0;
    U64 const fileSize = UTIL_getFileSize(srcFileName);
    DISPLAYLEVEL(5, "%s: %u bytes \n", srcFileName, (unsigned)fileSize);

    /* compression format selection */
-    switch (g_compressionType) {
+    switch (prefs->compressionType) {
        default:
        case FIO_zstdCompression:
-            compressedfilesize = FIO_compressZstdFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize);
+            compressedfilesize = FIO_compressZstdFrame(prefs, &ress, srcFileName, fileSize, compressionLevel, &readsize);
            break;

        case FIO_gzipCompression:
@@ -1098,7 +1203,7 @@ FIO_compressFilename_internal(cRess_t ress,
        case FIO_xzCompression:
        case FIO_lzmaCompression:
 #ifdef ZSTD_LZMACOMPRESS
-            compressedfilesize = FIO_compressLzmaFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize, g_compressionType==FIO_lzmaCompression);
+            compressedfilesize = FIO_compressLzmaFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize, prefs->compressionType==FIO_lzmaCompression);
 #else
            (void)compressionLevel;
            EXM_THROW(20, "zstd: %s: file cannot be compressed as xz/lzma (zstd compiled without ZSTD_LZMACOMPRESS) -- ignored \n",
@@ -1108,7 +1213,7 @@ FIO_compressFilename_internal(cRess_t ress,

        case FIO_lz4Compression:
 #ifdef ZSTD_LZ4COMPRESS
-            compressedfilesize = FIO_compressLz4Frame(&ress, srcFileName, fileSize, compressionLevel, &readsize);
+            compressedfilesize = FIO_compressLz4Frame(&ress, srcFileName, fileSize, compressionLevel, prefs->checksumFlag, &readsize);
 #else
            (void)compressionLevel;
            EXM_THROW(20, "zstd: %s: file cannot be compressed as lz4 (zstd compiled without ZSTD_LZ4COMPRESS) -- ignored \n",
@@ -1125,6 +1230,15 @@ FIO_compressFilename_internal(cRess_t ress,
        (unsigned long long)readsize, (unsigned long long) compressedfilesize,
         dstFileName);

+    /* Elapsed Time and CPU Load */
+    {   clock_t const cpuEnd = clock();
+        double const cpuLoad_s = (double)(cpuEnd - cpuStart) / CLOCKS_PER_SEC;
+        U64 const timeLength_ns = UTIL_clockSpanNano(timeStart);
+        double const timeLength_s = (double)timeLength_ns / 1000000000;
+        double const cpuLoad_pct = (cpuLoad_s / timeLength_s) * 100;
+        DISPLAYLEVEL(4, "%-20s : Completed in %.2f sec  (cpu load : %.0f%%)\n",
+                        srcFileName, timeLength_s, cpuLoad_pct);
+    }
    return 0;
 }

@@ -1138,7 +1252,8 @@ FIO_compressFilename_internal(cRess_t ress,
 *  @return : 0 : compression completed correctly,
 *            1 : pb
 */
-static int FIO_compressFilename_dstFile(cRess_t ress,
+static int FIO_compressFilename_dstFile(FIO_prefs_t* const prefs,
+                                        cRess_t ress,
                                        const char* dstFileName,
                                        const char* srcFileName,
                                        int compressionLevel)
@@ -1153,7 +1268,7 @@ static int FIO_compressFilename_dstFile(cRess_t ress,
    if (ress.dstFile == NULL) {
        closeDstFile = 1;
        DISPLAYLEVEL(6, "FIO_compressFilename_dstFile: opening dst: %s", dstFileName);
-        ress.dstFile = FIO_openDstFile(srcFileName, dstFileName);
+        ress.dstFile = FIO_openDstFile(prefs, srcFileName, dstFileName);
        if (ress.dstFile==NULL) return 1;  /* could not open dstFileName */
        /* Must only be added after FIO_openDstFile() succeeds.
         * Otherwise we may delete the destination file if it already exists,
@@ -1166,7 +1281,7 @@ static int FIO_compressFilename_dstFile(cRess_t ress,
            transfer_permissions = 1;
    }

-    result = FIO_compressFilename_internal(ress, dstFileName, srcFileName, compressionLevel);
+    result = FIO_compressFilename_internal(prefs, ress, dstFileName, srcFileName, compressionLevel);

    if (closeDstFile) {
        FILE* const dstFile = ress.dstFile;
@@ -1199,27 +1314,34 @@ static int FIO_compressFilename_dstFile(cRess_t ress,
 *            1 : missing or pb opening srcFileName
 */
 static int
-FIO_compressFilename_srcFile(cRess_t ress,
+FIO_compressFilename_srcFile(FIO_prefs_t* const prefs,
+                             cRess_t ress,
                             const char* dstFileName,
                             const char* srcFileName,
                             int compressionLevel)
 {
    int result;

-    /* File check */
+    /* ensure src is not a directory */
    if (UTIL_isDirectory(srcFileName)) {
        DISPLAYLEVEL(1, "zstd: %s is a directory -- ignored \n", srcFileName);
        return 1;
    }

+    /* ensure src is not the same as dict (if present) */
+    if (ress.dictFileName != NULL && UTIL_isSameFile(srcFileName, ress.dictFileName)) {
+        DISPLAYLEVEL(1, "zstd: cannot use %s as an input file and dictionary \n", srcFileName);
+        return 1;
+    }
+
    ress.srcFile = FIO_openSrcFile(srcFileName);
    if (ress.srcFile == NULL) return 1;   /* srcFile could not be opened */

-    result = FIO_compressFilename_dstFile(ress, dstFileName, srcFileName, compressionLevel);
+    result = FIO_compressFilename_dstFile(prefs, ress, dstFileName, srcFileName, compressionLevel);

    fclose(ress.srcFile);
    ress.srcFile = NULL;
-    if ( g_removeSrcFile   /* --rm */
+    if ( prefs->removeSrcFile   /* --rm */
      && result == 0       /* success */
      && strcmp(srcFileName, stdinmark)   /* exception : don't erase stdin */
      ) {
@@ -1234,19 +1356,17 @@ FIO_compressFilename_srcFile(cRess_t ress,
 }


-int FIO_compressFilename(const char* dstFileName, const char* srcFileName,
+int FIO_compressFilename(FIO_prefs_t* const prefs,
+                         const char* dstFileName, const char* srcFileName,
                         const char* dictFileName, int compressionLevel,
                         ZSTD_compressionParameters comprParams)
 {
-    clock_t const start = clock();
    U64 const fileSize = UTIL_getFileSize(srcFileName);
    U64 const srcSize = (fileSize == UTIL_FILESIZE_UNKNOWN) ? ZSTD_CONTENTSIZE_UNKNOWN : fileSize;

-    cRess_t const ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, comprParams);
-    int const result = FIO_compressFilename_srcFile(ress, dstFileName, srcFileName, compressionLevel);
+    cRess_t const ress = FIO_createCResources(prefs, dictFileName, compressionLevel, srcSize, comprParams);
+    int const result = FIO_compressFilename_srcFile(prefs, ress, dstFileName, srcFileName, compressionLevel);

-    double const seconds = (double)(clock() - start) / CLOCKS_PER_SEC;
-    DISPLAYLEVEL(4, "Completed in %.2f sec \n", seconds);

    FIO_freeCResources(ress);
    return result;
@@ -1288,7 +1408,8 @@ FIO_determineCompressedName(const char* srcFileName, const char* suffix)
 * into one destination (outFileName)
 * or into one file each (outFileName == NULL, but suffix != NULL).
 */
-int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFiles,
+int FIO_compressMultipleFilenames(FIO_prefs_t* const prefs,
+                                  const char** inFileNamesTable, unsigned nbFiles,
                                  const char* outFileName, const char* suffix,
                                  const char* dictFileName, int compressionLevel,
                                  ZSTD_compressionParameters comprParams)
@@ -1297,19 +1418,19 @@ int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFile
    U64 const firstFileSize = UTIL_getFileSize(inFileNamesTable[0]);
    U64 const firstSrcSize = (firstFileSize == UTIL_FILESIZE_UNKNOWN) ? ZSTD_CONTENTSIZE_UNKNOWN : firstFileSize;
    U64 const srcSize = (nbFiles != 1) ? ZSTD_CONTENTSIZE_UNKNOWN : firstSrcSize ;
-    cRess_t ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, comprParams);
+    cRess_t ress = FIO_createCResources(prefs, dictFileName, compressionLevel, srcSize, comprParams);

    /* init */
    assert(outFileName != NULL || suffix != NULL);

    if (outFileName != NULL) {   /* output into a single destination (stdout typically) */
-        ress.dstFile = FIO_openDstFile(NULL, outFileName);
+        ress.dstFile = FIO_openDstFile(prefs, NULL, outFileName);
        if (ress.dstFile == NULL) {  /* could not open outFileName */
            error = 1;
        } else {
            unsigned u;
            for (u=0; u<nbFiles; u++)
-                error |= FIO_compressFilename_srcFile(ress, outFileName, inFileNamesTable[u], compressionLevel);
+                error |= FIO_compressFilename_srcFile(prefs, ress, outFileName, inFileNamesTable[u], compressionLevel);
            if (fclose(ress.dstFile))
                EXM_THROW(29, "Write error (%s) : cannot properly close %s",
                            strerror(errno), outFileName);
@@ -1320,7 +1441,7 @@ int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFile
        for (u=0; u<nbFiles; u++) {
            const char* const srcFileName = inFileNamesTable[u];
            const char* const dstFileName = FIO_determineCompressedName(srcFileName, suffix);  /* cannot fail */
-            error |= FIO_compressFilename_srcFile(ress, dstFileName, srcFileName, compressionLevel);
+            error |= FIO_compressFilename_srcFile(prefs, ress, dstFileName, srcFileName, compressionLevel);
    }   }

    FIO_freeCResources(ress);
@@ -1346,7 +1467,7 @@ typedef struct {
    FILE*  dstFile;
 } dRess_t;

-static dRess_t FIO_createDResources(const char* dictFileName)
+static dRess_t FIO_createDResources(FIO_prefs_t* const prefs, const char* dictFileName)
 {
    dRess_t ress;
    memset(&ress, 0, sizeof(ress));
@@ -1355,7 +1476,7 @@ static dRess_t FIO_createDResources(const char* dictFileName)
    ress.dctx = ZSTD_createDStream();
    if (ress.dctx==NULL)
        EXM_THROW(60, "Error: %s : can't create ZSTD_DStream", strerror(errno));
-    CHECK( ZSTD_DCtx_setMaxWindowSize(ress.dctx, g_memLimit) );
+    CHECK( ZSTD_DCtx_setMaxWindowSize(ress.dctx, prefs->memLimit) );
    ress.srcBufferSize = ZSTD_DStreamInSize();
    ress.srcBuffer = malloc(ress.srcBufferSize);
    ress.dstBufferSize = ZSTD_DStreamOutSize();
@@ -1383,7 +1504,7 @@ static void FIO_freeDResources(dRess_t ress)

 /** FIO_fwriteSparse() :
 *   @return : storedSkips, to be provided to next call to FIO_fwriteSparse() of LZ4IO_fwriteSparseEnd() */
-static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSize, unsigned storedSkips)
+static unsigned FIO_fwriteSparse(FIO_prefs_t* const prefs, FILE* file, const void* buffer, size_t bufferSize, unsigned storedSkips)
 {
    const size_t* const bufferT = (const size_t*)buffer;   /* Buffer is supposed malloc'ed, hence aligned on size_t */
    size_t bufferSizeT = bufferSize / sizeof(size_t);
@@ -1391,7 +1512,7 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi
    const size_t* ptrT = bufferT;
    static const size_t segmentSizeT = (32 KB) / sizeof(size_t);   /* 0-test re-attempted every 32 KB */

-    if (!g_sparseFileSupport) {  /* normal write */
+    if (!prefs->sparseFileSupport) {  /* normal write */
        size_t const sizeCheck = fwrite(buffer, 1, bufferSize, file);
        if (sizeCheck != bufferSize)
            EXM_THROW(70, "Write error : %s (cannot write decoded block)",
@@ -1444,7 +1565,7 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi
                if (seekResult)
                    EXM_THROW(74, "Sparse skip error ; try --no-sparse");
                storedSkips = 0;
-                {   size_t const sizeCheck = fwrite(restPtr, 1, restEnd - restPtr, file);
+                {   size_t const sizeCheck = fwrite(restPtr, 1, (size_t)(restEnd - restPtr), file);
                    if (sizeCheck != (size_t)(restEnd - restPtr))
                        EXM_THROW(75, "Write error : cannot write decoded end of block");
    }   }   }   }
@@ -1452,10 +1573,12 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi
    return storedSkips;
 }

-static void FIO_fwriteSparseEnd(FILE* file, unsigned storedSkips)
+static void
+FIO_fwriteSparseEnd(FIO_prefs_t* const prefs, FILE* file, unsigned storedSkips)
 {
    if (storedSkips>0) {
-        assert(g_sparseFileSupport > 0);  /* storedSkips>0 implies sparse support is enabled */
+        assert(prefs->sparseFileSupport > 0);  /* storedSkips>0 implies sparse support is enabled */
+        (void)prefs;   /* assert can be disabled, in which case prefs becomes unused */
        if (LONG_SEEK(file, storedSkips-1, SEEK_CUR) != 0)
            EXM_THROW(69, "Final skip error (sparse file support)");
        /* last zero must be explicitly written,
@@ -1469,7 +1592,10 @@ static void FIO_fwriteSparseEnd(FILE* file, unsigned storedSkips)

 /** FIO_passThrough() : just copy input into output, for compatibility with gzip -df mode
    @return : 0 (no error) */
-static unsigned FIO_passThrough(FILE* foutput, FILE* finput, void* buffer, size_t bufferSize, size_t alreadyLoaded)
+static int FIO_passThrough(FIO_prefs_t* const prefs,
+                           FILE* foutput, FILE* finput,
+                           void* buffer, size_t bufferSize,
+                           size_t alreadyLoaded)
 {
    size_t const blockSize = MIN(64 KB, bufferSize);
    size_t readFromInput = 1;
@@ -1484,10 +1610,10 @@ static unsigned FIO_passThrough(FILE* foutput, FILE* finput, void* buffer, size_

    while (readFromInput) {
        readFromInput = fread(buffer, 1, blockSize, finput);
-        storedSkips = FIO_fwriteSparse(foutput, buffer, readFromInput, storedSkips);
+        storedSkips = FIO_fwriteSparse(prefs, foutput, buffer, readFromInput, storedSkips);
    }

-    FIO_fwriteSparseEnd(foutput, storedSkips);
+    FIO_fwriteSparseEnd(prefs, foutput, storedSkips);
    return 0;
 }

@@ -1506,7 +1632,7 @@ static unsigned FIO_highbit64(unsigned long long v)

 /* FIO_zstdErrorHelp() :
 * detailed error message when requested window size is too large */
-static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName)
+static void FIO_zstdErrorHelp(FIO_prefs_t* const prefs, dRess_t* ress, size_t err, char const* srcFileName)
 {
    ZSTD_frameHeader header;

@@ -1519,9 +1645,9 @@ static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName
    if (err == 0) {
        unsigned long long const windowSize = header.windowSize;
        unsigned const windowLog = FIO_highbit64(windowSize) + ((windowSize & (windowSize - 1)) != 0);
-        assert(g_memLimit > 0);
+        assert(prefs->memLimit > 0);
        DISPLAYLEVEL(1, "%s : Window size larger than maximum : %llu > %u\n",
-                        srcFileName, windowSize, g_memLimit);
+                        srcFileName, windowSize, prefs->memLimit);
        if (windowLog <= ZSTD_WINDOWLOG_MAX) {
            unsigned const windowMB = (unsigned)((windowSize >> 20) + ((windowSize & ((1 MB) - 1)) != 0));
            assert(windowSize < (U64)(1ULL << 52));   /* ensure now overflow for windowMB */
@@ -1538,7 +1664,9 @@ static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName
 *  @return : size of decoded zstd frame, or an error code
 */
 #define FIO_ERROR_FRAME_DECODING   ((unsigned long long)(-2))
-static unsigned long long FIO_decompressZstdFrame(dRess_t* ress,
+static unsigned long long FIO_decompressZstdFrame(
+                                       FIO_prefs_t* const prefs,
+                                       dRess_t* ress,
                                       FILE* finput,
                                       const char* srcFileName,
                                       U64 alreadyDecoded)
@@ -1567,12 +1695,12 @@ static unsigned long long FIO_decompressZstdFrame(dRess_t* ress,
        if (ZSTD_isError(readSizeHint)) {
            DISPLAYLEVEL(1, "%s : Decoding error (36) : %s \n",
                            srcFileName, ZSTD_getErrorName(readSizeHint));
-            FIO_zstdErrorHelp(ress, readSizeHint, srcFileName);
+            FIO_zstdErrorHelp(prefs, ress, readSizeHint, srcFileName);
            return FIO_ERROR_FRAME_DECODING;
        }

        /* Write block */
-        storedSkips = FIO_fwriteSparse(ress->dstFile, ress->dstBuffer, outBuff.pos, storedSkips);
+        storedSkips = FIO_fwriteSparse(prefs, ress->dstFile, ress->dstBuffer, outBuff.pos, storedSkips);
        frameSize += outBuff.pos;
        DISPLAYUPDATE(2, "\r%-20.20s : %u MB...     ",
                         srcFileName, (unsigned)((alreadyDecoded+frameSize)>>20) );
@@ -1603,7 +1731,7 @@ static unsigned long long FIO_decompressZstdFrame(dRess_t* ress,
                ress->srcBufferLoaded += readSize;
    }   }   }

-    FIO_fwriteSparseEnd(ress->dstFile, storedSkips);
+    FIO_fwriteSparseEnd(prefs, ress->dstFile, storedSkips);

    return frameSize;
 }
@@ -1834,7 +1962,7 @@ static unsigned long long FIO_decompressLz4Frame(dRess_t* ress,
 * @return : 0 : OK
 *           1 : error
 */
-static int FIO_decompressFrames(dRess_t ress, FILE* srcFile,
+static int FIO_decompressFrames(FIO_prefs_t* const prefs, dRess_t ress, FILE* srcFile,
                        const char* dstFileName, const char* srcFileName)
 {
    unsigned readSomething = 0;
@@ -1862,7 +1990,7 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile,
            return 1;
        }
        if (ZSTD_isFrame(buf, ress.srcBufferLoaded)) {
-            unsigned long long const frameSize = FIO_decompressZstdFrame(&ress, srcFile, srcFileName, filesize);
+            unsigned long long const frameSize = FIO_decompressZstdFrame(prefs, &ress, srcFile, srcFileName, filesize);
            if (frameSize == FIO_ERROR_FRAME_DECODING) return 1;
            filesize += frameSize;
        } else if (buf[0] == 31 && buf[1] == 139) { /* gz magic number */
@@ -1893,9 +2021,11 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile,
            DISPLAYLEVEL(1, "zstd: %s: lz4 file cannot be uncompressed (zstd compiled without HAVE_LZ4) -- ignored \n", srcFileName);
            return 1;
 #endif
-        } else if ((g_overwrite) && !strcmp (dstFileName, stdoutmark)) {  /* pass-through mode */
-            return FIO_passThrough(ress.dstFile, srcFile,
-                                   ress.srcBuffer, ress.srcBufferSize, ress.srcBufferLoaded);
+        } else if ((prefs->overwrite) && !strcmp (dstFileName, stdoutmark)) {  /* pass-through mode */
+            return FIO_passThrough(prefs,
+                                   ress.dstFile, srcFile,
+                                   ress.srcBuffer, ress.srcBufferSize,
+                                   ress.srcBufferLoaded);
        } else {
            DISPLAYLEVEL(1, "zstd: %s: unsupported format \n", srcFileName);
            return 1;
@@ -1915,7 +2045,8 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile,
    @return : 0 : OK
              1 : operation aborted
 */
-static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile,
+static int FIO_decompressDstFile(FIO_prefs_t* const prefs,
+                                 dRess_t ress, FILE* srcFile,
                                 const char* dstFileName, const char* srcFileName)
 {
    int result;
@@ -1926,7 +2057,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile,
    if (ress.dstFile == NULL) {
        releaseDstFile = 1;

-        ress.dstFile = FIO_openDstFile(srcFileName, dstFileName);
+        ress.dstFile = FIO_openDstFile(prefs, srcFileName, dstFileName);
        if (ress.dstFile==0) return 1;

        /* Must only be added after FIO_openDstFile() succeeds.
@@ -1941,7 +2072,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile,
    }


-    result = FIO_decompressFrames(ress, srcFile, dstFileName, srcFileName);
+    result = FIO_decompressFrames(prefs, ress, srcFile, dstFileName, srcFileName);

    if (releaseDstFile) {
        FILE* const dstFile = ress.dstFile;
@@ -1974,7 +2105,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile,
    @return : 0 : OK
              1 : error
 */
-static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const char* srcFileName)
+static int FIO_decompressSrcFile(FIO_prefs_t* const prefs, dRess_t ress, const char* dstFileName, const char* srcFileName)
 {
    FILE* srcFile;
    int result;
@@ -1988,14 +2119,14 @@ static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const ch
    if (srcFile==NULL) return 1;
    ress.srcBufferLoaded = 0;

-    result = FIO_decompressDstFile(ress, srcFile, dstFileName, srcFileName);
+    result = FIO_decompressDstFile(prefs, ress, srcFile, dstFileName, srcFileName);

    /* Close file */
    if (fclose(srcFile)) {
        DISPLAYLEVEL(1, "zstd: %s: %s \n", srcFileName, strerror(errno));  /* error should not happen */
        return 1;
    }
-    if ( g_removeSrcFile  /* --rm */
+    if ( prefs->removeSrcFile  /* --rm */
      && (result==0)      /* decompression successful */
      && strcmp(srcFileName, stdinmark) ) /* not stdin */ {
        /* We must clear the handler, since after this point calling it would
@@ -2012,12 +2143,13 @@ static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const ch



-int FIO_decompressFilename(const char* dstFileName, const char* srcFileName,
+int FIO_decompressFilename(FIO_prefs_t* const prefs,
+                           const char* dstFileName, const char* srcFileName,
                           const char* dictFileName)
 {
-    dRess_t const ress = FIO_createDResources(dictFileName);
+    dRess_t const ress = FIO_createDResources(prefs, dictFileName);

-    int const decodingError = FIO_decompressSrcFile(ress, dstFileName, srcFileName);
+    int const decodingError = FIO_decompressSrcFile(prefs, ress, dstFileName, srcFileName);

    FIO_freeDResources(ress);
    return decodingError;
@@ -2094,19 +2226,20 @@ FIO_determineDstName(const char* srcFileName)


 int
-FIO_decompressMultipleFilenames(const char* srcNamesTable[], unsigned nbFiles,
+FIO_decompressMultipleFilenames(FIO_prefs_t* const prefs,
+                                const char* srcNamesTable[], unsigned nbFiles,
                                const char* outFileName,
                                const char* dictFileName)
 {
    int error = 0;
-    dRess_t ress = FIO_createDResources(dictFileName);
+    dRess_t ress = FIO_createDResources(prefs, dictFileName);

    if (outFileName) {
        unsigned u;
-        ress.dstFile = FIO_openDstFile(NULL, outFileName);
+        ress.dstFile = FIO_openDstFile(prefs, NULL, outFileName);
        if (ress.dstFile == 0) EXM_THROW(71, "cannot open %s", outFileName);
        for (u=0; u<nbFiles; u++)
-            error |= FIO_decompressSrcFile(ress, outFileName, srcNamesTable[u]);
+            error |= FIO_decompressSrcFile(prefs, ress, outFileName, srcNamesTable[u]);
        if (fclose(ress.dstFile))
            EXM_THROW(72, "Write error : %s : cannot properly close output file",
                        strerror(errno));
@@ -2117,7 +2250,7 @@ FIO_decompressMultipleFilenames(const char* srcNamesTable[], unsigned nbFiles,
            const char* const dstFileName = FIO_determineDstName(srcFileName);
            if (dstFileName == NULL) { error=1; continue; }

-            error |= FIO_decompressSrcFile(ress, dstFileName, srcFileName);
+            error |= FIO_decompressSrcFile(prefs, ress, dstFileName, srcFileName);
        }
    }

@@ -2142,7 +2275,13 @@ typedef struct {
    U32 nbFiles;
 } fileInfo_t;

-typedef enum { info_success=0, info_frame_error=1, info_not_zstd=2, info_file_error=3 } InfoError;
+typedef enum {
+  info_success=0,
+  info_frame_error=1,
+  info_not_zstd=2,
+  info_file_error=3,
+  info_truncated_input=4,
+} InfoError;

 #define ERROR_IF(c,n,...) {             \
    if (c) {                           \
@@ -2164,6 +2303,12 @@ FIO_analyzeFrames(fileInfo_t* info, FILE* const srcFile)
              && (numBytesRead == 0)
              && (info->compressedSize > 0)
              && (info->compressedSize != UTIL_FILESIZE_UNKNOWN) ) {
+                unsigned long long file_position = (unsigned long long) LONG_TELL(srcFile);
+                unsigned long long file_size = (unsigned long long) info->compressedSize;
+                ERROR_IF(file_position != file_size, info_truncated_input,
+                  "Error: seeked to position %llu, which is beyond file size of %llu\n",
+                  file_position,
+                  file_size);
                break;  /* correct end of file => success */
            }
            ERROR_IF(feof(srcFile), info_not_zstd, "Error: reached end of file with incomplete frame");
@@ -2332,20 +2477,28 @@ FIO_listFile(fileInfo_t* total, const char* inFileName, int displayLevel)
    fileInfo_t info;
    memset(&info, 0, sizeof(info));
    {   InfoError const error = getFileInfo(&info, inFileName);
-        if (error == info_frame_error) {
-            /* display error, but provide output */
-            DISPLAYLEVEL(1, "Error while parsing %s \n", inFileName);
-        }
-        else if (error == info_not_zstd) {
-            DISPLAYOUT("File %s not compressed by zstd \n", inFileName);
-            if (displayLevel > 2) DISPLAYOUT("\n");
-            return 1;
-        }
-        else if (error == info_file_error) {
-            /* error occurred while opening the file */
-            if (displayLevel > 2) DISPLAYOUT("\n");
-            return 1;
+        switch (error) {
+            case info_frame_error:
+                /* display error, but provide output */
+                DISPLAYLEVEL(1, "Error while parsing \"%s\" \n", inFileName);
+                break;
+            case info_not_zstd:
+                DISPLAYOUT("File \"%s\" not compressed by zstd \n", inFileName);
+                if (displayLevel > 2) DISPLAYOUT("\n");
+                return 1;
+            case info_file_error:
+                /* error occurred while opening the file */
+                if (displayLevel > 2) DISPLAYOUT("\n");
+                return 1;
+            case info_truncated_input:
+                DISPLAYOUT("File \"%s\" is truncated \n", inFileName);
+                if (displayLevel > 2) DISPLAYOUT("\n");
+                return 1;
+            case info_success:
+            default:
+                break;
        }
+
        displayInfo(inFileName, &info, displayLevel);
        *total = FIO_addFInfo(*total, info);
        assert(error == info_success || error == info_frame_error);
@@ -42,44 +42,56 @@ extern "C" {
 ***************************************/
 typedef enum { FIO_zstdCompression, FIO_gzipCompression, FIO_xzCompression, FIO_lzmaCompression, FIO_lz4Compression } FIO_compressionType_t;

+typedef struct FIO_prefs_s FIO_prefs_t;
+
+FIO_prefs_t* FIO_createPreferences(void);
+void FIO_freePreferences(FIO_prefs_t* const prefs);
+
+typedef struct FIO_display_prefs_s FIO_display_prefs_t;

 /*-*************************************
 *  Parameters
 ***************************************/
-void FIO_setCompressionType(FIO_compressionType_t compressionType);
-void FIO_overwriteMode(void);
-void FIO_setAdaptiveMode(unsigned adapt);
-void FIO_setAdaptMin(int minCLevel);
-void FIO_setAdaptMax(int maxCLevel);
-void FIO_setBlockSize(unsigned blockSize);
-void FIO_setChecksumFlag(unsigned checksumFlag);
-void FIO_setDictIDFlag(unsigned dictIDFlag);
-void FIO_setLdmBucketSizeLog(unsigned ldmBucketSizeLog);
-void FIO_setLdmFlag(unsigned ldmFlag);
-void FIO_setLdmHashRateLog(unsigned ldmHashRateLog);
-void FIO_setLdmHashLog(unsigned ldmHashLog);
-void FIO_setLdmMinMatch(unsigned ldmMinMatch);
-void FIO_setMemLimit(unsigned memLimit);
-void FIO_setNbWorkers(unsigned nbWorkers);
-void FIO_setNotificationLevel(unsigned level);
-void FIO_setOverlapLog(unsigned overlapLog);
-void FIO_setRemoveSrcFile(unsigned flag);
-void FIO_setSparseWrite(unsigned sparse);  /**< 0: no sparse; 1: disable on stdout; 2: always enabled */
-void FIO_setRsyncable(unsigned rsyncable);
-void FIO_setNoProgress(unsigned noProgress);
+void FIO_setCompressionType(FIO_prefs_t* const prefs, FIO_compressionType_t compressionType);
+void FIO_overwriteMode(FIO_prefs_t* const prefs);
+void FIO_setAdaptiveMode(FIO_prefs_t* const prefs, unsigned adapt);
+void FIO_setAdaptMin(FIO_prefs_t* const prefs, int minCLevel);
+void FIO_setAdaptMax(FIO_prefs_t* const prefs, int maxCLevel);
+void FIO_setBlockSize(FIO_prefs_t* const prefs, int blockSize);
+void FIO_setChecksumFlag(FIO_prefs_t* const prefs, int checksumFlag);
+void FIO_setDictIDFlag(FIO_prefs_t* const prefs, int dictIDFlag);
+void FIO_setLdmBucketSizeLog(FIO_prefs_t* const prefs, int ldmBucketSizeLog);
+void FIO_setLdmFlag(FIO_prefs_t* const prefs, unsigned ldmFlag);
+void FIO_setLdmHashRateLog(FIO_prefs_t* const prefs, int ldmHashRateLog);
+void FIO_setLdmHashLog(FIO_prefs_t* const prefs, int ldmHashLog);
+void FIO_setLdmMinMatch(FIO_prefs_t* const prefs, int ldmMinMatch);
+void FIO_setMemLimit(FIO_prefs_t* const prefs, unsigned memLimit);
+void FIO_setNbWorkers(FIO_prefs_t* const prefs, int nbWorkers);
+void FIO_setOverlapLog(FIO_prefs_t* const prefs, int overlapLog);
+void FIO_setRemoveSrcFile(FIO_prefs_t* const prefs, unsigned flag);
+void FIO_setSparseWrite(FIO_prefs_t* const prefs, unsigned sparse);  /**< 0: no sparse; 1: disable on stdout; 2: always enabled */
+void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable);
+void FIO_setTargetCBlockSize(FIO_prefs_t* const prefs, size_t targetCBlockSize);
+void FIO_setLiteralCompressionMode(
+        FIO_prefs_t* const prefs,
+        ZSTD_literalCompressionMode_e mode);

+void FIO_setNoProgress(unsigned noProgress);
+void FIO_setNotificationLevel(int level);

 /*-*************************************
 *  Single File functions
 ***************************************/
 /** FIO_compressFilename() :
    @return : 0 == ok;  1 == pb with src file. */
-int FIO_compressFilename (const char* outfilename, const char* infilename, const char* dictFileName,
+int FIO_compressFilename (FIO_prefs_t* const prefs,
+                          const char* outfilename, const char* infilename, const char* dictFileName,
                          int compressionLevel, ZSTD_compressionParameters comprParams);

 /** FIO_decompressFilename() :
    @return : 0 == ok;  1 == pb with src file. */
-int FIO_decompressFilename (const char* outfilename, const char* infilename, const char* dictFileName);
+int FIO_decompressFilename (FIO_prefs_t* const prefs,
+                            const char* outfilename, const char* infilename, const char* dictFileName);

 int FIO_listMultipleFiles(unsigned numFiles, const char** filenameTable, int displayLevel);

@@ -89,14 +101,16 @@ int FIO_listMultipleFiles(unsigned numFiles, const char** filenameTable, int dis
 ***************************************/
 /** FIO_compressMultipleFilenames() :
    @return : nb of missing files */
-int FIO_compressMultipleFilenames(const char** srcNamesTable, unsigned nbFiles,
+int FIO_compressMultipleFilenames(FIO_prefs_t* const prefs,
+                                  const char** srcNamesTable, unsigned nbFiles,
                                  const char* outFileName, const char* suffix,
                                  const char* dictFileName, int compressionLevel,
                                  ZSTD_compressionParameters comprParams);

 /** FIO_decompressMultipleFilenames() :
    @return : nb of missing or skipped files */
-int FIO_decompressMultipleFilenames(const char** srcNamesTable, unsigned nbFiles,
+int FIO_decompressMultipleFilenames(FIO_prefs_t* const prefs,
+                                    const char** srcNamesTable, unsigned nbFiles,
                                    const char* outFileName,
                                    const char* dictFileName);

@@ -87,8 +87,8 @@ extern "C" {
 * The following list of build macros tries to "guess" if target OS is likely unix-like, and therefore can #include <unistd.h>
 */
 #  elif !defined(_WIN32) \
-     && (defined(__unix__) || defined(__unix) \
-     || defined(__midipix__) || defined(__VMS) || defined(__HAIKU__))
+     && ( defined(__unix__) || defined(__unix) \
+       || defined(__midipix__) || defined(__VMS) || defined(__HAIKU__) )

 #    if defined(__linux__) || defined(__linux)
 #      ifndef _POSIX_C_SOURCE
@@ -108,6 +108,7 @@ extern "C" {

 #endif   /* PLATFORM_POSIX_VERSION */

+
 /*-*********************************************
 *  Detect if isatty() and fileno() are available
 ************************************************/
@@ -0,0 +1,168 @@
+/*
+ * Copyright (c) 2019-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+/* ===  Dependencies  === */
+
+#include "timefn.h"
+
+
+/*-****************************************
+*  Time functions
+******************************************/
+
+#if defined(_WIN32)   /* Windows */
+
+#include <stdlib.h>   /* abort */
+#include <stdio.h>    /* perror */
+
+UTIL_time_t UTIL_getTime(void) { UTIL_time_t x; QueryPerformanceCounter(&x); return x; }
+
+PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd)
+{
+    static LARGE_INTEGER ticksPerSecond;
+    static int init = 0;
+    if (!init) {
+        if (!QueryPerformanceFrequency(&ticksPerSecond)) {
+            perror("timefn::QueryPerformanceFrequency");
+            abort();
+        }
+        init = 1;
+    }
+    return 1000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart;
+}
+
+PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd)
+{
+    static LARGE_INTEGER ticksPerSecond;
+    static int init = 0;
+    if (!init) {
+        if (!QueryPerformanceFrequency(&ticksPerSecond)) {
+            perror("timefn::QueryPerformanceFrequency");
+            abort();
+        }
+        init = 1;
+    }
+    return 1000000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart;
+}
+
+
+
+#elif defined(__APPLE__) && defined(__MACH__)
+
+UTIL_time_t UTIL_getTime(void) { return mach_absolute_time(); }
+
+PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd)
+{
+    static mach_timebase_info_data_t rate;
+    static int init = 0;
+    if (!init) {
+        mach_timebase_info(&rate);
+        init = 1;
+    }
+    return (((clockEnd - clockStart) * (PTime)rate.numer) / ((PTime)rate.denom))/1000ULL;
+}
+
+PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd)
+{
+    static mach_timebase_info_data_t rate;
+    static int init = 0;
+    if (!init) {
+        mach_timebase_info(&rate);
+        init = 1;
+    }
+    return ((clockEnd - clockStart) * (PTime)rate.numer) / ((PTime)rate.denom);
+}
+
+
+
+#elif (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L) /* C11 */) \
+    && defined(TIME_UTC) /* C11 requires timespec_get, but FreeBSD 11 lacks it, while still claiming C11 compliance */
+
+#include <stdlib.h>   /* abort */
+#include <stdio.h>    /* perror */
+
+UTIL_time_t UTIL_getTime(void)
+{
+    /* time must be initialized, othersize it may fail msan test.
+     * No good reason, likely a limitation of timespec_get() for some target */
+    UTIL_time_t time = UTIL_TIME_INITIALIZER;
+    if (timespec_get(&time, TIME_UTC) != TIME_UTC) {
+        perror("timefn::timespec_get");
+        abort();
+    }
+    return time;
+}
+
+static UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end)
+{
+    UTIL_time_t diff;
+    if (end.tv_nsec < begin.tv_nsec) {
+        diff.tv_sec = (end.tv_sec - 1) - begin.tv_sec;
+        diff.tv_nsec = (end.tv_nsec + 1000000000ULL) - begin.tv_nsec;
+    } else {
+        diff.tv_sec = end.tv_sec - begin.tv_sec;
+        diff.tv_nsec = end.tv_nsec - begin.tv_nsec;
+    }
+    return diff;
+}
+
+PTime UTIL_getSpanTimeMicro(UTIL_time_t begin, UTIL_time_t end)
+{
+    UTIL_time_t const diff = UTIL_getSpanTime(begin, end);
+    PTime micro = 0;
+    micro += 1000000ULL * diff.tv_sec;
+    micro += diff.tv_nsec / 1000ULL;
+    return micro;
+}
+
+PTime UTIL_getSpanTimeNano(UTIL_time_t begin, UTIL_time_t end)
+{
+    UTIL_time_t const diff = UTIL_getSpanTime(begin, end);
+    PTime nano = 0;
+    nano += 1000000000ULL * diff.tv_sec;
+    nano += diff.tv_nsec;
+    return nano;
+}
+
+
+
+#else   /* relies on standard C90 (note : clock_t measurements can be wrong when using multi-threading) */
+
+UTIL_time_t UTIL_getTime(void) { return clock(); }
+PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; }
+PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; }
+
+#endif
+
+
+
+/* returns time span in microseconds */
+PTime UTIL_clockSpanMicro(UTIL_time_t clockStart )
+{
+    UTIL_time_t const clockEnd = UTIL_getTime();
+    return UTIL_getSpanTimeMicro(clockStart, clockEnd);
+}
+
+/* returns time span in microseconds */
+PTime UTIL_clockSpanNano(UTIL_time_t clockStart )
+{
+    UTIL_time_t const clockEnd = UTIL_getTime();
+    return UTIL_getSpanTimeNano(clockStart, clockEnd);
+}
+
+void UTIL_waitForNextTick(void)
+{
+    UTIL_time_t const clockStart = UTIL_getTime();
+    UTIL_time_t clockEnd;
+    do {
+        clockEnd = UTIL_getTime();
+    } while (UTIL_getSpanTimeNano(clockStart, clockEnd) == 0);
+}
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef TIME_FN_H_MODULE_287987
+#define TIME_FN_H_MODULE_287987
+
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+
+/*-****************************************
+*  Dependencies
+******************************************/
+#include <sys/types.h>    /* utime */
+#if defined(_MSC_VER)
+#  include <sys/utime.h>  /* utime */
+#else
+#  include <utime.h>      /* utime */
+#endif
+#include <time.h>         /* clock_t, clock, CLOCKS_PER_SEC */
+
+
+
+/*-****************************************
+*  Local Types
+******************************************/
+
+#if !defined (__VMS) && (defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) )
+# include <stdint.h>
+  typedef uint64_t           PTime;  /* Precise Time */
+#else
+  typedef unsigned long long PTime;  /* does not support compilers without long long support */
+#endif
+
+
+
+/*-****************************************
+*  Time functions
+******************************************/
+#if defined(_WIN32)   /* Windows */
+
+    #include <Windows.h>   /* LARGE_INTEGER */
+    typedef LARGE_INTEGER UTIL_time_t;
+    #define UTIL_TIME_INITIALIZER { { 0, 0 } }
+
+#elif defined(__APPLE__) && defined(__MACH__)
+
+    #include <mach/mach_time.h>
+    typedef PTime UTIL_time_t;
+    #define UTIL_TIME_INITIALIZER 0
+
+#elif (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L) /* C11 */) \
+    && defined(TIME_UTC) /* C11 requires timespec_get, but FreeBSD 11 lacks it, while still claiming C11 compliance */
+
+    typedef struct timespec UTIL_time_t;
+    #define UTIL_TIME_INITIALIZER { 0, 0 }
+
+#else   /* relies on standard C90 (note : clock_t measurements can be wrong when using multi-threading) */
+
+    typedef clock_t UTIL_time_t;
+    #define UTIL_TIME_INITIALIZER 0
+
+#endif
+
+
+UTIL_time_t UTIL_getTime(void);
+PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd);
+PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd);
+
+#define SEC_TO_MICRO ((PTime)1000000)
+PTime UTIL_clockSpanMicro(UTIL_time_t clockStart);
+PTime UTIL_clockSpanNano(UTIL_time_t clockStart);
+
+void UTIL_waitForNextTick(void);
+
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif /* TIME_FN_H_MODULE_287987 */
@@ -87,20 +87,31 @@ U32 UTIL_isDirectory(const char* infilename)
    return 0;
 }

+int UTIL_isSameFile(const char* file1, const char* file2)
+{
+#if defined(_MSC_VER)
+    /* note : Visual does not support file identification by inode.
+     *        The following work-around is limited to detecting exact name repetition only,
+     *        aka `filename` is considered different from `subdir/../filename` */
+    return !strcmp(file1, file2);
+#else
+    stat_t file1Stat;
+    stat_t file2Stat;
+    return UTIL_getFileStat(file1, &file1Stat)
+        && UTIL_getFileStat(file2, &file2Stat)
+        && (file1Stat.st_dev == file2Stat.st_dev)
+        && (file1Stat.st_ino == file2Stat.st_ino);
+#endif
+}
+
 U32 UTIL_isLink(const char* infilename)
 {
 /* macro guards, as defined in : https://linux.die.net/man/2/lstat */
-#ifndef __STRICT_ANSI__
-#if defined(_BSD_SOURCE) \
-    || (defined(_XOPEN_SOURCE) && (_XOPEN_SOURCE >= 500)) \
-    || (defined(_XOPEN_SOURCE) && defined(_XOPEN_SOURCE_EXTENDED)) \
-    || (defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L)) \
-    || (defined(__APPLE__) && defined(__MACH__))
+#if PLATFORM_POSIX_VERSION >= 200112L
    int r;
    stat_t statbuf;
    r = lstat(infilename, &statbuf);
    if (!r && S_ISLNK(statbuf.st_mode)) return 1;
-#endif
 #endif
    (void)infilename;
    return 0;
@@ -234,6 +245,7 @@ int UTIL_prepareFileList(const char *dirName, char** bufStart, size_t* pos, char

        if (!followLinks && UTIL_isLink(path)) {
            UTIL_DISPLAYLEVEL(2, "Warning : %s is a symbolic link, ignoring\n", path);
+            free(path);
            continue;
        }

@@ -333,146 +345,18 @@ UTIL_createFileList(const char **inputNames, unsigned inputNamesNb,
    return fileTable;
 }

+
 /*-****************************************
 *  Console log
 ******************************************/
 int g_utilDisplayLevel;


+
 /*-****************************************
-*  Time functions
+*  count the number of physical cores
 ******************************************/
-#if defined(_WIN32)   /* Windows */

-UTIL_time_t UTIL_getTime(void) { UTIL_time_t x; QueryPerformanceCounter(&x); return x; }
-
-U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd)
-{
-    static LARGE_INTEGER ticksPerSecond;
-    static int init = 0;
-    if (!init) {
-        if (!QueryPerformanceFrequency(&ticksPerSecond))
-            UTIL_DISPLAYLEVEL(1, "ERROR: QueryPerformanceFrequency() failure\n");
-        init = 1;
-    }
-    return 1000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart;
-}
-
-U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd)
-{
-    static LARGE_INTEGER ticksPerSecond;
-    static int init = 0;
-    if (!init) {
-        if (!QueryPerformanceFrequency(&ticksPerSecond))
-            UTIL_DISPLAYLEVEL(1, "ERROR: QueryPerformanceFrequency() failure\n");
-        init = 1;
-    }
-    return 1000000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart;
-}
-
-#elif defined(__APPLE__) && defined(__MACH__)
-
-UTIL_time_t UTIL_getTime(void) { return mach_absolute_time(); }
-
-U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd)
-{
-    static mach_timebase_info_data_t rate;
-    static int init = 0;
-    if (!init) {
-        mach_timebase_info(&rate);
-        init = 1;
-    }
-    return (((clockEnd - clockStart) * (U64)rate.numer) / ((U64)rate.denom))/1000ULL;
-}
-
-U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd)
-{
-    static mach_timebase_info_data_t rate;
-    static int init = 0;
-    if (!init) {
-        mach_timebase_info(&rate);
-        init = 1;
-    }
-    return ((clockEnd - clockStart) * (U64)rate.numer) / ((U64)rate.denom);
-}
-
-#elif (PLATFORM_POSIX_VERSION >= 200112L) \
-   && (defined(__UCLIBC__)                \
-      || (defined(__GLIBC__)              \
-          && ((__GLIBC__ == 2 && __GLIBC_MINOR__ >= 17) \
-             || (__GLIBC__ > 2))))
-
-UTIL_time_t UTIL_getTime(void)
-{
-    UTIL_time_t time;
-    if (clock_gettime(CLOCK_MONOTONIC, &time))
-        UTIL_DISPLAYLEVEL(1, "ERROR: Failed to get time\n");   /* we could also exit() */
-    return time;
-}
-
-UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end)
-{
-    UTIL_time_t diff;
-    if (end.tv_nsec < begin.tv_nsec) {
-        diff.tv_sec = (end.tv_sec - 1) - begin.tv_sec;
-        diff.tv_nsec = (end.tv_nsec + 1000000000ULL) - begin.tv_nsec;
-    } else {
-        diff.tv_sec = end.tv_sec - begin.tv_sec;
-        diff.tv_nsec = end.tv_nsec - begin.tv_nsec;
-    }
-    return diff;
-}
-
-U64 UTIL_getSpanTimeMicro(UTIL_time_t begin, UTIL_time_t end)
-{
-    UTIL_time_t const diff = UTIL_getSpanTime(begin, end);
-    U64 micro = 0;
-    micro += 1000000ULL * diff.tv_sec;
-    micro += diff.tv_nsec / 1000ULL;
-    return micro;
-}
-
-U64 UTIL_getSpanTimeNano(UTIL_time_t begin, UTIL_time_t end)
-{
-    UTIL_time_t const diff = UTIL_getSpanTime(begin, end);
-    U64 nano = 0;
-    nano += 1000000000ULL * diff.tv_sec;
-    nano += diff.tv_nsec;
-    return nano;
-}
-
-#else   /* relies on standard C (note : clock_t measurements can be wrong when using multi-threading) */
-
-UTIL_time_t UTIL_getTime(void) { return clock(); }
-U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; }
-U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; }
-
-#endif
-
-/* returns time span in microseconds */
-U64 UTIL_clockSpanMicro(UTIL_time_t clockStart )
-{
-    UTIL_time_t const clockEnd = UTIL_getTime();
-    return UTIL_getSpanTimeMicro(clockStart, clockEnd);
-}
-
-/* returns time span in microseconds */
-U64 UTIL_clockSpanNano(UTIL_time_t clockStart )
-{
-    UTIL_time_t const clockEnd = UTIL_getTime();
-    return UTIL_getSpanTimeNano(clockStart, clockEnd);
-}
-
-void UTIL_waitForNextTick(void)
-{
-    UTIL_time_t const clockStart = UTIL_getTime();
-    UTIL_time_t clockEnd;
-    do {
-        clockEnd = UTIL_getTime();
-    } while (UTIL_getSpanTimeNano(clockStart, clockEnd) == 0);
-}
-
-/* count the number of physical cores */
 #if defined(_WIN32) || defined(WIN32)

 #include <windows.h>
@@ -640,10 +524,42 @@ failed:
    }
 }

-#elif defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__)
+#elif defined(__FreeBSD__)

-/* Use apple-provided syscall
- * see: man 3 sysctl */
+#include <sys/param.h>
+#include <sys/sysctl.h>
+
+/* Use physical core sysctl when available
+ * see: man 4 smp, man 3 sysctl */
+int UTIL_countPhysicalCores(void)
+{
+    static int numPhysicalCores = 0; /* freebsd sysctl is native int sized */
+    if (numPhysicalCores != 0) return numPhysicalCores;
+
+#if __FreeBSD_version >= 1300008
+    {   size_t size = sizeof(numPhysicalCores);
+        int ret = sysctlbyname("kern.smp.cores", &numPhysicalCores, &size, NULL, 0);
+        if (ret == 0) return numPhysicalCores;
+        if (errno != ENOENT) {
+            perror("zstd: can't get number of physical cpus");
+            exit(1);
+        }
+        /* sysctl not present, fall through to older sysconf method */
+    }
+#endif
+
+    numPhysicalCores = (int)sysconf(_SC_NPROCESSORS_ONLN);
+    if (numPhysicalCores == -1) {
+        /* value not queryable, fall back on 1 */
+        numPhysicalCores = 1;
+    }
+    return numPhysicalCores;
+}
+
+#elif defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__)
+
+/* Use POSIX sysconf
+ * see: man 3 sysconf */
 int UTIL_countPhysicalCores(void)
 {
    static int numPhysicalCores = 0;
@@ -112,52 +112,6 @@ extern int g_utilDisplayLevel;
 #define UTIL_DISPLAYLEVEL(l, ...) { if (g_utilDisplayLevel>=l) { UTIL_DISPLAY(__VA_ARGS__); } }


-/*-****************************************
-*  Time functions
-******************************************/
-#if defined(_WIN32)   /* Windows */
-
-    #define UTIL_TIME_INITIALIZER { { 0, 0 } }
-    typedef LARGE_INTEGER UTIL_time_t;
-
-#elif defined(__APPLE__) && defined(__MACH__)
-
-    #include <mach/mach_time.h>
-    #define UTIL_TIME_INITIALIZER 0
-    typedef U64 UTIL_time_t;
-
-#elif (PLATFORM_POSIX_VERSION >= 200112L) \
-   && (defined(__UCLIBC__)                \
-      || (defined(__GLIBC__)              \
-          && ((__GLIBC__ == 2 && __GLIBC_MINOR__ >= 17) \
-             || (__GLIBC__ > 2))))
-
-    #define UTIL_TIME_INITIALIZER { 0, 0 }
-    typedef struct timespec UTIL_freq_t;
-    typedef struct timespec UTIL_time_t;
-
-    UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end);
-
-#else   /* relies on standard C (note : clock_t measurements can be wrong when using multi-threading) */
-
-    typedef clock_t UTIL_time_t;
-    #define UTIL_TIME_INITIALIZER 0
-
-#endif
-
-UTIL_time_t UTIL_getTime(void);
-U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd);
-U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd);
-
-#define SEC_TO_MICRO 1000000
-
-/* returns time span in microseconds */
-U64 UTIL_clockSpanMicro(UTIL_time_t clockStart);
-
-/* returns time span in microseconds */
-U64 UTIL_clockSpanNano(UTIL_time_t clockStart);
-void UTIL_waitForNextTick(void);
-
 /*-****************************************
 *  File functions
 ******************************************/
@@ -174,6 +128,7 @@ int UTIL_isRegularFile(const char* infilename);
 int UTIL_setFileStat(const char* filename, stat_t* statbuf);
 U32 UTIL_isDirectory(const char* infilename);
 int UTIL_getFileStat(const char* infilename, stat_t* statbuf);
+int UTIL_isSameFile(const char* file1, const char* file2);

 U32 UTIL_isLink(const char* infilename);
 #define UTIL_FILESIZE_UNKNOWN  ((U64)(-1))
@@ -1,5 +1,5 @@
 .
-.TH "ZSTD" "1" "December 2018" "zstd 1.3.8" "User Commands"
+.TH "ZSTD" "1" "July 2019" "zstd 1.4.2" "User Commands"
 .
 .SH "NAME"
 \fBzstd\fR \- zstd, zstdmt, unzstd, zstdcat \- Compress or decompress \.zst files
@@ -164,7 +164,7 @@ keep source file(s) after successful compression or decompression\. This is the
 .
 .TP
 \fB\-r\fR
-operate recursively on dictionaries
+operate recursively on directories
 .
 .TP
 \fB\-\-format=FORMAT\fR
@@ -187,6 +187,10 @@ verbose mode
 suppress warnings, interactivity, and notifications\. specify twice to suppress errors too\.
 .
 .TP
+\fB\-\-no\-progress\fR
+do not display the progress bar, but keep all other messages\.
+.
+.TP
 \fB\-C\fR, \fB\-\-[no\-]check\fR
 add integrity check computed from uncompressed data (default: enabled)
 .
@@ -225,11 +229,11 @@ Split input files in blocks of size # (default: no split)
 A dictionary ID is a locally unique ID that a decoder can use to verify it is using the right dictionary\. By default, zstd will create a 4\-bytes random number ID\. It\'s possible to give a precise number instead\. Short numbers have an advantage : an ID < 256 will only need 1 byte in the compressed frame header, and an ID < 65536 will only need 2 bytes\. This compares favorably to 4 bytes default\. However, it\'s up to the dictionary manager to not assign twice the same ID to 2 different dictionaries\.
 .
 .TP
-\fB\-\-train\-cover[=k#,d=#,steps=#,split=#]\fR
-Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or split <= 0, then the default value of 100 is used\. Requires that \fId\fR <= \fIk\fR\.
+\fB\-\-train\-cover[=k#,d=#,steps=#,split=#,shrink[=#]]\fR
+Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or split <= 0, then the default value of 100 is used\. Requires that \fId\fR <= \fIk\fR\. If \fIshrink\fR flag is not used, then the default value for \fIshrinkDict\fR of 0 is used\. If \fIshrink\fR is not specified, then the default value for \fIshrinkDictMaxRegression\fR of 1 is used\.
 .
 .IP
-Selects segments of size \fIk\fR with highest score to put in the dictionary\. The score of a segment is computed by the sum of the frequencies of all the subsegments of size \fId\fR\. Generally \fId\fR should be in the range [6, 8], occasionally up to 16, but the algorithm will run faster with d <= \fI8\fR\. Good values for \fIk\fR vary widely based on the input data, but a safe range is [2 * \fId\fR, 2000]\. If \fIsplit\fR is 100, all input samples are used for both training and testing to find optimal \fId\fR and \fIk\fR to build dictionary\. Supports multithreading if \fBzstd\fR is compiled with threading support\.
+Selects segments of size \fIk\fR with highest score to put in the dictionary\. The score of a segment is computed by the sum of the frequencies of all the subsegments of size \fId\fR\. Generally \fId\fR should be in the range [6, 8], occasionally up to 16, but the algorithm will run faster with d <= \fI8\fR\. Good values for \fIk\fR vary widely based on the input data, but a safe range is [2 * \fId\fR, 2000]\. If \fIsplit\fR is 100, all input samples are used for both training and testing to find optimal \fId\fR and \fIk\fR to build dictionary\. Supports multithreading if \fBzstd\fR is compiled with threading support\. Having \fIshrink\fR enabled takes a truncated dictionary of minimum size and doubles in size until compression ratio of the truncated dictionary is at most \fIshrinkDictMaxRegression%\fR worse than the compression ratio of the largest dictionary\.
 .
 .IP
 Examples:
@@ -249,6 +253,12 @@ Examples:
 .IP
 \fBzstd \-\-train\-cover=k=50,split=60 FILEs\fR
 .
+.IP
+\fBzstd \-\-train\-cover=shrink FILEs\fR
+.
+.IP
+\fBzstd \-\-train\-cover=shrink=2 FILEs\fR
+.
 .TP
 \fB\-\-train\-fastcover[=k#,d=#,f=#,steps=#,split=#,accel=#]\fR
 Same as cover but with extra parameters \fIf\fR and \fIaccel\fR and different default value of split If \fIsplit\fR is not specified, then it tries \fIsplit\fR = 75\. If \fIf\fR is not specified, then it tries \fIf\fR = 20\. Requires that 0 < \fIf\fR < 32\. If \fIaccel\fR is not specified, then it tries \fIaccel\fR = 1\. Requires that 0 < \fIaccel\fR <= 10\. Requires that \fId\fR = 6 or \fId\fR = 8\.
@@ -178,7 +178,7 @@ the last one takes effect.
    keep source file(s) after successful compression or decompression.
    This is the default behavior.
 * `-r`:
-    operate recursively on dictionaries
+    operate recursively on directories
 * `--format=FORMAT`:
    compress and decompress in other formats. If compiled with
    support, zstd can compress to or decompress from other compression algorithm
@@ -244,13 +244,15 @@ Compression of small files similar to the sample set will be greatly improved.
    This compares favorably to 4 bytes default.
    However, it's up to the dictionary manager to not assign twice the same ID to
    2 different dictionaries.
-* `--train-cover[=k#,d=#,steps=#,split=#]`:
+* `--train-cover[=k#,d=#,steps=#,split=#,shrink[=#]]`:
    Select parameters for the default dictionary builder algorithm named cover.
    If _d_ is not specified, then it tries _d_ = 6 and _d_ = 8.
    If _k_ is not specified, then it tries _steps_ values in the range [50, 2000].
    If _steps_ is not specified, then the default value of 40 is used.
    If _split_ is not specified or split <= 0, then the default value of 100 is used.
    Requires that _d_ <= _k_.
+    If _shrink_ flag is not used, then the default value for _shrinkDict_ of 0 is used.
+    If _shrink_ is not specified, then the default value for _shrinkDictMaxRegression_ of 1 is used.

    Selects segments of size _k_ with highest score to put in the dictionary.
    The score of a segment is computed by the sum of the frequencies of all the
@@ -262,6 +264,9 @@ Compression of small files similar to the sample set will be greatly improved.
    If _split_ is 100, all input samples are used for both training and testing
    to find optimal _d_ and _k_ to build dictionary.
    Supports multithreading if `zstd` is compiled with threading support.
+    Having _shrink_ enabled takes a truncated dictionary of minimum size and doubles
+    in size until compression ratio of the truncated dictionary is at most
+    _shrinkDictMaxRegression%_ worse than the compression ratio of the largest dictionary.

    Examples:

@@ -275,6 +280,10 @@ Compression of small files similar to the sample set will be greatly improved.

    `zstd --train-cover=k=50,split=60 FILEs`

+    `zstd --train-cover=shrink FILEs`
+
+    `zstd --train-cover=shrink=2 FILEs`
+
 * `--train-fastcover[=k#,d=#,f=#,steps=#,split=#,accel=#]`:
    Same as cover but with extra parameters _f_ and _accel_ and different default value of split
    If _split_ is not specified, then it tries _split_ = 75.
@@ -141,6 +141,7 @@ static int usage_advanced(const char* programName)
    DISPLAY( "--long[=#]: enable long distance matching with given window log (default: %u)\n", g_defaultMaxWindowLog);
    DISPLAY( "--fast[=#]: switch to ultra fast compression level (default: %u)\n", 1);
    DISPLAY( "--adapt : dynamically adapt compression level to I/O conditions \n");
+    DISPLAY( "--target-compressed-block-size=# : make compressed block near targeted size \n");
 #ifdef ZSTD_MULTITHREAD
    DISPLAY( " -T#    : spawns # compression threads (default: 1, 0==# cores) \n");
    DISPLAY( " -B#    : select size of each job (default: 0==automatic) \n");
@@ -148,6 +149,7 @@ static int usage_advanced(const char* programName)
 #endif
    DISPLAY( "--no-dictID : don't write dictID into header (dictionary compression)\n");
    DISPLAY( "--[no-]check : integrity check (default: enabled) \n");
+    DISPLAY( "--[no-]compress-literals : force (un)compressed literals \n");
 #endif
 #ifdef UTIL_HAS_CREATEFILELIST
    DISPLAY( " -r     : operate recursively on directories \n");
@@ -178,8 +180,8 @@ static int usage_advanced(const char* programName)
    DISPLAY( "\n");
    DISPLAY( "Dictionary builder : \n");
    DISPLAY( "--train ## : create a dictionary from a training set of files \n");
-    DISPLAY( "--train-cover[=k=#,d=#,steps=#,split=#] : use the cover algorithm with optional args\n");
-    DISPLAY( "--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,accel=#] : use the fast cover algorithm with optional args\n");
+    DISPLAY( "--train-cover[=k=#,d=#,steps=#,split=#,shrink[=#]] : use the cover algorithm with optional args\n");
+    DISPLAY( "--train-fastcover[=k=#,d=#,f=#,steps=#,split=#,accel=#,shrink[=#]] : use the fast cover algorithm with optional args\n");
    DISPLAY( "--train-legacy[=s=#] : use the legacy algorithm with selectivity (default: %u)\n", g_defaultSelectivityLevel);
    DISPLAY( " -o file : `file` is dictionary name (default: %s) \n", g_defaultDictName);
    DISPLAY( "--maxdict=# : limit dictionary to specified size (default: %u) \n", g_defaultMaxDictSize);
@@ -241,18 +243,20 @@ static void errorOut(const char* msg)
 * @return 1 if an overflow error occurs */
 static int readU32FromCharChecked(const char** stringPtr, unsigned* value)
 {
-    static unsigned const max = (((unsigned)(-1)) / 10) - 1;
    unsigned result = 0;
    while ((**stringPtr >='0') && (**stringPtr <='9')) {
-        if (result > max) return 1; // overflow error
-        result *= 10, result += **stringPtr - '0', (*stringPtr)++ ;
+        unsigned const max = (((unsigned)(-1)) / 10) - 1;
+        if (result > max) return 1; /* overflow error */
+        result *= 10;
+        result += (unsigned)(**stringPtr - '0');
+        (*stringPtr)++ ;
    }
    if ((**stringPtr=='K') || (**stringPtr=='M')) {
        unsigned const maxK = ((unsigned)(-1)) >> 10;
-        if (result > maxK) return 1; // overflow error
+        if (result > maxK) return 1; /* overflow error */
        result <<= 10;
        if (**stringPtr=='M') {
-            if (result > maxK) return 1; // overflow error
+            if (result > maxK) return 1; /* overflow error */
            result <<= 10;
        }
        (*stringPtr)++;  /* skip `K` or `M` */
@@ -290,6 +294,8 @@ static unsigned longCommandWArg(const char** stringPtr, const char* longCommand)


 #ifndef ZSTD_NODICT
+
+static const unsigned kDefaultRegression = 1;
 /**
 * parseCoverParameters() :
 * reads cover parameters from *stringPtr (e.g. "--train-cover=k=48,d=8,steps=32") into *params
@@ -308,10 +314,23 @@ static unsigned parseCoverParameters(const char* stringPtr, ZDICT_cover_params_t
          params->splitPoint = (double)splitPercentage / 100.0;
          if (stringPtr[0]==',') { stringPtr++; continue; } else break;
        }
+        if (longCommandWArg(&stringPtr, "shrink")) {
+          params->shrinkDictMaxRegression = kDefaultRegression;
+          params->shrinkDict = 1;
+          if (stringPtr[0]=='=') {
+            stringPtr++;
+            params->shrinkDictMaxRegression = readU32FromChar(&stringPtr);
+          }
+          if (stringPtr[0]==',') {
+            stringPtr++;
+            continue;
+          }
+          else break;
+        }
        return 0;
    }
    if (stringPtr[0] != 0) return 0;
-    DISPLAYLEVEL(4, "cover: k=%u\nd=%u\nsteps=%u\nsplit=%u\n", params->k, params->d, params->steps, (unsigned)(params->splitPoint * 100));
+    DISPLAYLEVEL(4, "cover: k=%u\nd=%u\nsteps=%u\nsplit=%u\nshrink%u\n", params->k, params->d, params->steps, (unsigned)(params->splitPoint * 100), params->shrinkDictMaxRegression);
    return 1;
 }

@@ -335,16 +354,29 @@ static unsigned parseFastCoverParameters(const char* stringPtr, ZDICT_fastCover_
          params->splitPoint = (double)splitPercentage / 100.0;
          if (stringPtr[0]==',') { stringPtr++; continue; } else break;
        }
+        if (longCommandWArg(&stringPtr, "shrink")) {
+          params->shrinkDictMaxRegression = kDefaultRegression;
+          params->shrinkDict = 1;
+          if (stringPtr[0]=='=') {
+            stringPtr++;
+            params->shrinkDictMaxRegression = readU32FromChar(&stringPtr);
+          }
+          if (stringPtr[0]==',') {
+            stringPtr++;
+            continue;
+          }
+          else break;
+        }
        return 0;
    }
    if (stringPtr[0] != 0) return 0;
-    DISPLAYLEVEL(4, "cover: k=%u\nd=%u\nf=%u\nsteps=%u\nsplit=%u\naccel=%u\n", params->k, params->d, params->f, params->steps, (unsigned)(params->splitPoint * 100), params->accel);
+    DISPLAYLEVEL(4, "cover: k=%u\nd=%u\nf=%u\nsteps=%u\nsplit=%u\naccel=%u\nshrink=%u\n", params->k, params->d, params->f, params->steps, (unsigned)(params->splitPoint * 100), params->accel, params->shrinkDictMaxRegression);
    return 1;
 }

 /**
 * parseLegacyParameters() :
- * reads legacy dictioanry builter parameters from *stringPtr (e.g. "--train-legacy=selectivity=8") into *selectivity
+ * reads legacy dictionary builder parameters from *stringPtr (e.g. "--train-legacy=selectivity=8") into *selectivity
 * @return 1 means that legacy dictionary builder parameters were correct
 * @return 0 in case of malformed parameters
 */
@@ -364,6 +396,8 @@ static ZDICT_cover_params_t defaultCoverParams(void)
    params.d = 8;
    params.steps = 4;
    params.splitPoint = 1.0;
+    params.shrinkDict = 0;
+    params.shrinkDictMaxRegression = kDefaultRegression;
    return params;
 }

@@ -376,6 +410,8 @@ static ZDICT_fastCover_params_t defaultFastCoverParams(void)
    params.steps = 4;
    params.splitPoint = 0.75; /* different from default splitPoint of cover */
    params.accel = DEFAULT_ACCEL;
+    params.shrinkDict = 0;
+    params.shrinkDictMaxRegression = kDefaultRegression;
    return params;
 }
 #endif
@@ -483,7 +519,7 @@ static int init_cLevel(void) {

        if ((*ptr>='0') && (*ptr<='9')) {
            unsigned absLevel;
-            if (readU32FromCharChecked(&ptr, &absLevel)) { 
+            if (readU32FromCharChecked(&ptr, &absLevel)) {
                DISPLAYLEVEL(2, "Ignore environment variable setting %s=%s: numeric value too large\n", ENV_CLEVEL, env);
                return ZSTDCLI_CLEVEL_DEFAULT;
            } else if (*ptr == 0) {
@@ -536,6 +572,8 @@ int main(int argCount, const char* argv[])
    double compressibility = 0.5;
    unsigned bench_nbSeconds = 3;   /* would be better if this value was synchronized from bench */
    size_t blockSize = 0;
+
+    FIO_prefs_t* const prefs = FIO_createPreferences();
    zstd_operation_mode operation = zom_compress;
    ZSTD_compressionParameters compressionParams;
    int cLevel;
@@ -550,6 +588,7 @@ int main(int argCount, const char* argv[])
    const char* suffix = ZSTD_EXTENSION;
    unsigned maxDictSize = g_defaultMaxDictSize;
    unsigned dictID = 0;
+    size_t targetCBlockSize = 0;
    int dictCLevel = g_defaultDictCLevel;
    unsigned dictSelect = g_defaultSelectivityLevel;
 #ifdef UTIL_HAS_CREATEFILELIST
@@ -565,6 +604,7 @@ int main(int argCount, const char* argv[])
 #ifndef ZSTD_NOBENCH
    BMK_advancedParams_t benchParams = BMK_initAdvancedParams();
 #endif
+    ZSTD_literalCompressionMode_e literalCompressionMode = ZSTD_lcm_auto;


    /* init */
@@ -582,17 +622,17 @@ int main(int argCount, const char* argv[])
    /* preset behaviors */
    if (exeNameMatch(programName, ZSTD_ZSTDMT)) nbWorkers=0, singleThread=0;
    if (exeNameMatch(programName, ZSTD_UNZSTD)) operation=zom_decompress;
-    if (exeNameMatch(programName, ZSTD_CAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; }   /* supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_ZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; }  /* behave like zcat, also supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_GZ)) { suffix = GZ_EXTENSION; FIO_setCompressionType(FIO_gzipCompression); FIO_setRemoveSrcFile(1); }               /* behave like gzip */
-    if (exeNameMatch(programName, ZSTD_GUNZIP)) { operation=zom_decompress; FIO_setRemoveSrcFile(1); }                                                     /* behave like gunzip, also supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_GZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; } /* behave like gzcat, also supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_LZMA)) { suffix = LZMA_EXTENSION; FIO_setCompressionType(FIO_lzmaCompression); FIO_setRemoveSrcFile(1); }           /* behave like lzma */
-    if (exeNameMatch(programName, ZSTD_UNLZMA)) { operation=zom_decompress; FIO_setCompressionType(FIO_lzmaCompression); FIO_setRemoveSrcFile(1); }        /* behave like unlzma, also supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_XZ)) { suffix = XZ_EXTENSION; FIO_setCompressionType(FIO_xzCompression); FIO_setRemoveSrcFile(1); }                 /* behave like xz */
-    if (exeNameMatch(programName, ZSTD_UNXZ)) { operation=zom_decompress; FIO_setCompressionType(FIO_xzCompression); FIO_setRemoveSrcFile(1); }            /* behave like unxz, also supports multiple formats */
-    if (exeNameMatch(programName, ZSTD_LZ4)) { suffix = LZ4_EXTENSION; FIO_setCompressionType(FIO_lz4Compression); }                                       /* behave like lz4 */
-    if (exeNameMatch(programName, ZSTD_UNLZ4)) { operation=zom_decompress; FIO_setCompressionType(FIO_lz4Compression); }                                   /* behave like unlz4, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_CAT)) { operation=zom_decompress; FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; outFileName=stdoutmark; g_displayLevel=1; }     /* supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_ZCAT)) { operation=zom_decompress; FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; outFileName=stdoutmark; g_displayLevel=1; }    /* behave like zcat, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_GZ)) { suffix = GZ_EXTENSION; FIO_setCompressionType(prefs, FIO_gzipCompression); FIO_setRemoveSrcFile(prefs, 1); }        /* behave like gzip */
+    if (exeNameMatch(programName, ZSTD_GUNZIP)) { operation=zom_decompress; FIO_setRemoveSrcFile(prefs, 1); }                                                     /* behave like gunzip, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_GZCAT)) { operation=zom_decompress; FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; outFileName=stdoutmark; g_displayLevel=1; }   /* behave like gzcat, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_LZMA)) { suffix = LZMA_EXTENSION; FIO_setCompressionType(prefs, FIO_lzmaCompression); FIO_setRemoveSrcFile(prefs, 1); }    /* behave like lzma */
+    if (exeNameMatch(programName, ZSTD_UNLZMA)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_lzmaCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like unlzma, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_XZ)) { suffix = XZ_EXTENSION; FIO_setCompressionType(prefs, FIO_xzCompression); FIO_setRemoveSrcFile(prefs, 1); }          /* behave like xz */
+    if (exeNameMatch(programName, ZSTD_UNXZ)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_xzCompression); FIO_setRemoveSrcFile(prefs, 1); }     /* behave like unxz, also supports multiple formats */
+    if (exeNameMatch(programName, ZSTD_LZ4)) { suffix = LZ4_EXTENSION; FIO_setCompressionType(prefs, FIO_lz4Compression); }                                       /* behave like lz4 */
+    if (exeNameMatch(programName, ZSTD_UNLZ4)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_lz4Compression); }                                   /* behave like unlz4, also supports multiple formats */
    memset(&compressionParams, 0, sizeof(compressionParams));

    /* init crash handler */
@@ -623,40 +663,42 @@ int main(int argCount, const char* argv[])
                    if (!strcmp(argument, "--compress")) { operation=zom_compress; continue; }
                    if (!strcmp(argument, "--decompress")) { operation=zom_decompress; continue; }
                    if (!strcmp(argument, "--uncompress")) { operation=zom_decompress; continue; }
-                    if (!strcmp(argument, "--force")) { FIO_overwriteMode(); forceStdout=1; followLinks=1; continue; }
+                    if (!strcmp(argument, "--force")) { FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; continue; }
                    if (!strcmp(argument, "--version")) { g_displayOut=stdout; DISPLAY(WELCOME_MESSAGE); CLEAN_RETURN(0); }
                    if (!strcmp(argument, "--help")) { g_displayOut=stdout; CLEAN_RETURN(usage_advanced(programName)); }
                    if (!strcmp(argument, "--verbose")) { g_displayLevel++; continue; }
                    if (!strcmp(argument, "--quiet")) { g_displayLevel--; continue; }
                    if (!strcmp(argument, "--stdout")) { forceStdout=1; outFileName=stdoutmark; g_displayLevel-=(g_displayLevel==2); continue; }
                    if (!strcmp(argument, "--ultra")) { ultra=1; continue; }
-                    if (!strcmp(argument, "--check")) { FIO_setChecksumFlag(2); continue; }
-                    if (!strcmp(argument, "--no-check")) { FIO_setChecksumFlag(0); continue; }
-                    if (!strcmp(argument, "--sparse")) { FIO_setSparseWrite(2); continue; }
-                    if (!strcmp(argument, "--no-sparse")) { FIO_setSparseWrite(0); continue; }
+                    if (!strcmp(argument, "--check")) { FIO_setChecksumFlag(prefs, 2); continue; }
+                    if (!strcmp(argument, "--no-check")) { FIO_setChecksumFlag(prefs, 0); continue; }
+                    if (!strcmp(argument, "--sparse")) { FIO_setSparseWrite(prefs, 2); continue; }
+                    if (!strcmp(argument, "--no-sparse")) { FIO_setSparseWrite(prefs, 0); continue; }
                    if (!strcmp(argument, "--test")) { operation=zom_test; continue; }
                    if (!strcmp(argument, "--train")) { operation=zom_train; if (outFileName==NULL) outFileName=g_defaultDictName; continue; }
                    if (!strcmp(argument, "--maxdict")) { nextArgumentIsMaxDict=1; lastCommand=1; continue; }  /* kept available for compatibility with old syntax ; will be removed one day */
                    if (!strcmp(argument, "--dictID")) { nextArgumentIsDictID=1; lastCommand=1; continue; }  /* kept available for compatibility with old syntax ; will be removed one day */
-                    if (!strcmp(argument, "--no-dictID")) { FIO_setDictIDFlag(0); continue; }
-                    if (!strcmp(argument, "--keep")) { FIO_setRemoveSrcFile(0); continue; }
-                    if (!strcmp(argument, "--rm")) { FIO_setRemoveSrcFile(1); continue; }
+                    if (!strcmp(argument, "--no-dictID")) { FIO_setDictIDFlag(prefs, 0); continue; }
+                    if (!strcmp(argument, "--keep")) { FIO_setRemoveSrcFile(prefs, 0); continue; }
+                    if (!strcmp(argument, "--rm")) { FIO_setRemoveSrcFile(prefs, 1); continue; }
                    if (!strcmp(argument, "--priority=rt")) { setRealTimePrio = 1; continue; }
                    if (!strcmp(argument, "--adapt")) { adapt = 1; continue; }
                    if (longCommandWArg(&argument, "--adapt=")) { adapt = 1; if (!parseAdaptParameters(argument, &adaptMin, &adaptMax)) CLEAN_RETURN(badusage(programName)); continue; }
                    if (!strcmp(argument, "--single-thread")) { nbWorkers = 0; singleThread = 1; continue; }
-                    if (!strcmp(argument, "--format=zstd")) { suffix = ZSTD_EXTENSION; FIO_setCompressionType(FIO_zstdCompression); continue; }
+                    if (!strcmp(argument, "--format=zstd")) { suffix = ZSTD_EXTENSION; FIO_setCompressionType(prefs, FIO_zstdCompression); continue; }
 #ifdef ZSTD_GZCOMPRESS
-                    if (!strcmp(argument, "--format=gzip")) { suffix = GZ_EXTENSION; FIO_setCompressionType(FIO_gzipCompression); continue; }
+                    if (!strcmp(argument, "--format=gzip")) { suffix = GZ_EXTENSION; FIO_setCompressionType(prefs, FIO_gzipCompression); continue; }
 #endif
 #ifdef ZSTD_LZMACOMPRESS
-                    if (!strcmp(argument, "--format=lzma")) { suffix = LZMA_EXTENSION; FIO_setCompressionType(FIO_lzmaCompression);  continue; }
-                    if (!strcmp(argument, "--format=xz")) { suffix = XZ_EXTENSION; FIO_setCompressionType(FIO_xzCompression);  continue; }
+                    if (!strcmp(argument, "--format=lzma")) { suffix = LZMA_EXTENSION; FIO_setCompressionType(prefs, FIO_lzmaCompression);  continue; }
+                    if (!strcmp(argument, "--format=xz")) { suffix = XZ_EXTENSION; FIO_setCompressionType(prefs, FIO_xzCompression);  continue; }
 #endif
 #ifdef ZSTD_LZ4COMPRESS
-                    if (!strcmp(argument, "--format=lz4")) { suffix = LZ4_EXTENSION; FIO_setCompressionType(FIO_lz4Compression);  continue; }
+                    if (!strcmp(argument, "--format=lz4")) { suffix = LZ4_EXTENSION; FIO_setCompressionType(prefs, FIO_lz4Compression);  continue; }
 #endif
                    if (!strcmp(argument, "--rsyncable")) { rsyncable = 1; continue; }
+                    if (!strcmp(argument, "--compress-literals")) { literalCompressionMode = ZSTD_lcm_huffman; continue; }
+                    if (!strcmp(argument, "--no-compress-literals")) { literalCompressionMode = ZSTD_lcm_uncompressed; continue; }
                    if (!strcmp(argument, "--no-progress")) { FIO_setNoProgress(1); continue; }

                    /* long commands with arguments */
@@ -703,6 +745,7 @@ int main(int argCount, const char* argv[])
                    if (longCommandWArg(&argument, "--maxdict=")) { maxDictSize = readU32FromChar(&argument); continue; }
                    if (longCommandWArg(&argument, "--dictID=")) { dictID = readU32FromChar(&argument); continue; }
                    if (longCommandWArg(&argument, "--zstd=")) { if (!parseCompressionParameters(argument, &compressionParams)) CLEAN_RETURN(badusage(programName)); continue; }
+                    if (longCommandWArg(&argument, "--target-compressed-block-size=")) { targetCBlockSize = readU32FromChar(&argument); continue; }
                    if (longCommandWArg(&argument, "--long")) {
                        unsigned ldmWindowLog = 0;
                        ldmFlag = 1;
@@ -784,7 +827,7 @@ int main(int argCount, const char* argv[])
                    case 'D': nextEntryIsDictionary = 1; lastCommand = 1; argument++; break;

                        /* Overwrite */
-                    case 'f': FIO_overwriteMode(); forceStdout=1; followLinks=1; argument++; break;
+                    case 'f': FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; argument++; break;

                        /* Verbose mode */
                    case 'v': g_displayLevel++; argument++; break;
@@ -793,10 +836,10 @@ int main(int argCount, const char* argv[])
                    case 'q': g_displayLevel--; argument++; break;

                        /* keep source file (default) */
-                    case 'k': FIO_setRemoveSrcFile(0); argument++; break;
+                    case 'k': FIO_setRemoveSrcFile(prefs, 0); argument++; break;

                        /* Checksum */
-                    case 'C': FIO_setChecksumFlag(2); argument++; break;
+                    case 'C': FIO_setChecksumFlag(prefs, 2); argument++; break;

                        /* test compressed file */
                    case 't': operation=zom_test; argument++; break;
@@ -949,6 +992,8 @@ int main(int argCount, const char* argv[])
                filenameTable[fileNamesNb++] = filenameTable[u];
            }
        }
+        if (fileNamesNb == 0 && filenameIdx > 0)
+            CLEAN_RETURN(1);
        filenameIdx = fileNamesNb;
    }
    if (recursive) {  /* at this stage, filenameTable is a list of paths, which can contain both files and directories */
@@ -991,6 +1036,7 @@ int main(int argCount, const char* argv[])
        if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) {
            benchParams.ldmHashRateLog = g_ldmHashRateLog;
        }
+        benchParams.literalCompressionMode = literalCompressionMode;

        if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel();
        if (cLevelLast > ZSTD_maxCLevel()) cLevelLast = ZSTD_maxCLevel();
@@ -1057,7 +1103,7 @@ int main(int argCount, const char* argv[])
    }

 #ifndef ZSTD_NODECOMPRESS
-    if (operation==zom_test) { outFileName=nulmark; FIO_setRemoveSrcFile(0); }  /* test mode */
+    if (operation==zom_test) { outFileName=nulmark; FIO_setRemoveSrcFile(prefs, 0); }  /* test mode */
 #endif

    /* No input filename ==> use stdin and stdout */
@@ -1092,27 +1138,29 @@ int main(int argCount, const char* argv[])
    FIO_setNotificationLevel(g_displayLevel);
    if (operation==zom_compress) {
 #ifndef ZSTD_NOCOMPRESS
-        FIO_setNbWorkers(nbWorkers);
-        FIO_setBlockSize((U32)blockSize);
-        if (g_overlapLog!=OVERLAP_LOG_DEFAULT) FIO_setOverlapLog(g_overlapLog);
-        FIO_setLdmFlag(ldmFlag);
-        FIO_setLdmHashLog(g_ldmHashLog);
-        FIO_setLdmMinMatch(g_ldmMinMatch);
-        if (g_ldmBucketSizeLog != LDM_PARAM_DEFAULT) FIO_setLdmBucketSizeLog(g_ldmBucketSizeLog);
-        if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) FIO_setLdmHashRateLog(g_ldmHashRateLog);
-        FIO_setAdaptiveMode(adapt);
-        FIO_setAdaptMin(adaptMin);
-        FIO_setAdaptMax(adaptMax);
-        FIO_setRsyncable(rsyncable);
+        FIO_setNbWorkers(prefs, nbWorkers);
+        FIO_setBlockSize(prefs, (U32)blockSize);
+        if (g_overlapLog!=OVERLAP_LOG_DEFAULT) FIO_setOverlapLog(prefs, g_overlapLog);
+        FIO_setLdmFlag(prefs, ldmFlag);
+        FIO_setLdmHashLog(prefs, g_ldmHashLog);
+        FIO_setLdmMinMatch(prefs, g_ldmMinMatch);
+        if (g_ldmBucketSizeLog != LDM_PARAM_DEFAULT) FIO_setLdmBucketSizeLog(prefs, g_ldmBucketSizeLog);
+        if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) FIO_setLdmHashRateLog(prefs, g_ldmHashRateLog);
+        FIO_setAdaptiveMode(prefs, adapt);
+        FIO_setAdaptMin(prefs, adaptMin);
+        FIO_setAdaptMax(prefs, adaptMax);
+        FIO_setRsyncable(prefs, rsyncable);
+        FIO_setTargetCBlockSize(prefs, targetCBlockSize);
+        FIO_setLiteralCompressionMode(prefs, literalCompressionMode);
        if (adaptMin > cLevel) cLevel = adaptMin;
        if (adaptMax < cLevel) cLevel = adaptMax;

        if ((filenameIdx==1) && outFileName)
-          operationResult = FIO_compressFilename(outFileName, filenameTable[0], dictFileName, cLevel, compressionParams);
+          operationResult = FIO_compressFilename(prefs, outFileName, filenameTable[0], dictFileName, cLevel, compressionParams);
        else
-          operationResult = FIO_compressMultipleFilenames(filenameTable, filenameIdx, outFileName, suffix, dictFileName, cLevel, compressionParams);
+          operationResult = FIO_compressMultipleFilenames(prefs, filenameTable, filenameIdx, outFileName, suffix, dictFileName, cLevel, compressionParams);
 #else
-        (void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; /* not used when ZSTD_NOCOMPRESS set */
+        (void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; (void)literalCompressionMode; (void)targetCBlockSize; /* not used when ZSTD_NOCOMPRESS set */
        DISPLAY("Compression not supported \n");
 #endif
    } else {  /* decompression or test */
@@ -1124,17 +1172,19 @@ int main(int argCount, const char* argv[])
                memLimit = (U32)1 << (compressionParams.windowLog & 31);
            }
        }
-        FIO_setMemLimit(memLimit);
+        FIO_setMemLimit(prefs, memLimit);
        if (filenameIdx==1 && outFileName)
-            operationResult = FIO_decompressFilename(outFileName, filenameTable[0], dictFileName);
+            operationResult = FIO_decompressFilename(prefs, outFileName, filenameTable[0], dictFileName);
        else
-            operationResult = FIO_decompressMultipleFilenames(filenameTable, filenameIdx, outFileName, dictFileName);
+            operationResult = FIO_decompressMultipleFilenames(prefs, filenameTable, filenameIdx, outFileName, dictFileName);
 #else
        DISPLAY("Decompression not supported \n");
 #endif
    }

 _end:
+    FIO_freePreferences(prefs);
+
    if (main_pause) waitEnter();
 #ifdef UTIL_HAS_CREATEFILELIST
    if (extendedFileList)
@@ -22,8 +22,8 @@
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
 # THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

-grep=grep
-zcat=zstdcat
+grep=${GREP:-grep}
+zcat=${ZCAT:-zstdcat}

 endofopts=0
 pattern_found=0
@@ -31,12 +31,13 @@ grep_args=""
 hyphen=0
 silent=0

-prg=$(basename "$0")
+prog=${0##*/}

 # handle being called 'zegrep' or 'zfgrep'
-case "${prg}" in
-    *zegrep) grep_args="-E";;
-    *zfgrep) grep_args="-F";;
+case $prog in
+    *egrep*) prog=zegrep; grep_args='-E';;
+    *fgrep*) prog=zfgrep; grep_args='-F';;
+    *)       prog=zstdgrep;;
 esac

 # skip all options and pass them on to grep taking care of options
@@ -47,7 +48,7 @@ while [ "$#" -gt 0 ] && [ "${endofopts}" -eq 0 ]; do
    # from GNU grep-2.5.1 -- keep in sync!
        -[ABCDXdefm])
            if [ "$#" -lt 2 ]; then
-                printf '%s: missing argument for %s flag\n' "${prg}" "$1" >&2
+                printf '%s: missing argument for %s flag\n' "${prog}" "$1" >&2
                exit 1
            fi
            case "$1" in
@@ -57,6 +58,9 @@ while [ "$#" -gt 0 ] && [ "${endofopts}" -eq 0 ]; do
                    shift 2
                    break
                    ;;
+                -f)
+                    pattern_found=2
+                    ;;
                *)
                    ;;
            esac
@@ -94,7 +98,7 @@ if [ "${pattern_found}" -lt 1 ]; then
    elif [ "${hyphen}" -gt 0 ]; then
        pattern="-"
    else
-        printf '%s: missing pattern\n' "${prg}" >&2
+        printf '%s: missing pattern\n' "${prog}" >&2
        exit 1
    fi
 fi
@@ -113,16 +117,15 @@ else
    if [ "${silent}" -lt 1 ] && [ "$#" -gt 1 ]; then
        grep_args="-H ${grep_args}"
    fi
-    CUR_EXIT_CODE=0
-    EXIT_CODE=1
    set -f
    while [ "$#" -gt 0 ]; do
        # shellcheck disable=SC2086
-        "${zcat}" -fq -- "$1" | "${grep}" --label="${1}" ${grep_args} -- "${pattern}" -
-        CUR_EXIT_CODE=$?
-        if [ "${CUR_EXIT_CODE}" -eq 0 ] && [ "${EXIT_CODE}" -ne 1 ]; then
-            EXIT_CODE=0
+        if [ $pattern_found -eq 2 ]; then
+            "${zcat}" -fq -- "$1" | "${grep}" --label="${1}" ${grep_args} -- -
+        else
+            "${zcat}" -fq -- "$1" | "${grep}" --label="${1}" ${grep_args} -- "${pattern}" -
        fi
+        [ "$?" -ne 0 ] && EXIT_CODE=1
        shift
    done
    set +f
@@ -1,5 +1,5 @@
 .
-.TH "ZSTDGREP" "1" "December 2018" "zstd 1.3.8" "User Commands"
+.TH "ZSTDGREP" "1" "July 2019" "zstd 1.4.2" "User Commands"
 .
 .SH "NAME"
 \fBzstdgrep\fR \- print lines matching a pattern in zstandard\-compressed files
@@ -1,5 +1,5 @@
 .
-.TH "ZSTDLESS" "1" "December 2018" "zstd 1.3.8" "User Commands"
+.TH "ZSTDLESS" "1" "July 2019" "zstd 1.4.2" "User Commands"
 .
 .SH "NAME"
 \fBzstdless\fR \- view zstandard\-compressed files
@@ -55,6 +55,7 @@ _*
 tmp*
 *.zst
 *.gz
+!gzip/hufts-segv.gz
 result
 out
 *.zstd
@@ -33,7 +33,7 @@ endif
 CFLAGS     ?= -O3
 CFLAGS     += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow                 \
              -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-              -Wstrict-prototypes -Wundef -Wformat-security                   \
+              -Wstrict-prototypes -Wundef                                     \
              -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings      \
              -Wredundant-decls -Wmissing-prototypes
 CFLAGS     += $(DEBUGFLAGS) $(MOREFLAGS)
@@ -82,7 +82,7 @@ default: fullbench
 	@echo $(ZSTDMT_OBJECTS)

 all: fullbench fuzzer zstreamtest paramgrill datagen decodecorpus roundTripCrash \
-     fullbench-lib
+     fullbench-lib poolTests

 all32: fullbench32 fuzzer32 zstreamtest32

@@ -132,18 +132,18 @@ fullbench fullbench32 : CPPFLAGS += $(MULTITHREAD_CPP)
 fullbench fullbench32 : LDFLAGS += $(MULTITHREAD_LD)
 fullbench fullbench32 : DEBUGFLAGS = -DNDEBUG  # turn off assert() for speed measurements
 fullbench fullbench32 : $(ZSTD_FILES)
-fullbench fullbench32 : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c
+fullbench fullbench32 : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c fullbench.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

 fullbench-lib : CPPFLAGS += -DXXH_NAMESPACE=ZSTD_
 fullbench-lib : zstd-staticLib
-fullbench-lib : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c
+fullbench-lib : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c fullbench.c
 	$(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT) $(ZSTDDIR)/libzstd.a

 # note : broken : requires unavailable symbols
 fullbench-dll : zstd-dll
 fullbench-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd
-fullbench-dll: $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c
+fullbench-dll: $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c $(PRGDIR)/timefn.c fullbench.c
 #	$(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT) -DZSTD_DLL_IMPORT=1 $(ZSTDDIR)/dll/libzstd.dll
 	$(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT)

@@ -152,32 +152,32 @@ fuzzer  : LDFLAGS += $(MULTITHREAD_LD)
 fuzzer32: CFLAGS += -m32
 fuzzer  : $(ZSTDMT_OBJECTS)
 fuzzer32: $(ZSTD_FILES)
-fuzzer fuzzer32 : $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c fuzzer.c
+fuzzer fuzzer32 : $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c fuzzer.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

 fuzzer-dll : zstd-dll
 fuzzer-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd
-fuzzer-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/datagen.c fuzzer.c
+fuzzer-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c fuzzer.c
 	$(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT)

 zbufftest : CPPFLAGS += -I$(ZSTDDIR)/deprecated
 zbufftest : CFLAGS += -Wno-deprecated-declarations   # required to silence deprecation warnings
-zbufftest : $(ZSTD_OBJECTS) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c
+zbufftest : $(ZSTD_OBJECTS) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

 zbufftest32 : CPPFLAGS += -I$(ZSTDDIR)/deprecated
 zbufftest32 : CFLAGS += -Wno-deprecated-declarations -m32
-zbufftest32 : $(ZSTD_FILES) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c
+zbufftest32 : $(ZSTD_FILES) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

 zbufftest-dll : zstd-dll
 zbufftest-dll : CPPFLAGS += -I$(ZSTDDIR)/deprecated
 zbufftest-dll : CFLAGS += -Wno-deprecated-declarations   # required to silence deprecation warnings
 zbufftest-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd
-zbufftest-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c
+zbufftest-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c
 	$(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT)

-ZSTREAM_LOCAL_FILES := $(PRGDIR)/datagen.c $(PRGDIR)/util.c seqgen.c zstreamtest.c
+ZSTREAM_LOCAL_FILES := $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c seqgen.c zstreamtest.c
 ZSTREAM_PROPER_FILES := $(ZDICT_FILES) $(ZSTREAM_LOCAL_FILES)
 ZSTREAMFILES := $(ZSTD_FILES) $(ZSTREAM_PROPER_FILES)
 zstreamtest32 : CFLAGS += -m32
@@ -203,7 +203,7 @@ zstreamtest-dll : $(ZSTREAM_LOCAL_FILES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT)

 paramgrill : DEBUGFLAGS =  # turn off assert() by default for speed measurements
-paramgrill : $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/benchfn.c $(PRGDIR)/benchzstd.c $(PRGDIR)/datagen.c paramgrill.c
+paramgrill : $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c $(PRGDIR)/benchzstd.c $(PRGDIR)/datagen.c paramgrill.c
 	$(CC) $(FLAGS) $^ -lm -o $@$(EXT)

 datagen : $(PRGDIR)/datagen.c datagencli.c
@@ -215,6 +215,9 @@ roundTripCrash : $(ZSTD_OBJECTS) roundTripCrash.c
 longmatch  : $(ZSTD_OBJECTS) longmatch.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

+bigdict: $(ZSTDMT_OBJECTS) $(PRGDIR)/datagen.c bigdict.c
+	$(CC) $(FLAGS) $(MULTITHREAD) $^ -o $@$(EXT)
+
 invalidDictionaries : $(ZSTD_OBJECTS) invalidDictionaries.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

@@ -222,7 +225,7 @@ legacy : CPPFLAGS += -I$(ZSTDDIR)/legacy -DZSTD_LEGACY_SUPPORT=4
 legacy : $(ZSTD_FILES) $(wildcard $(ZSTDDIR)/legacy/*.c) legacy.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT)

-decodecorpus : $(filter-out zstdc_zstd_compress.o, $(ZSTD_OBJECTS)) $(ZDICT_FILES) $(PRGDIR)/util.c decodecorpus.c
+decodecorpus : $(filter-out zstdc_zstd_compress.o, $(ZSTD_OBJECTS)) $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c decodecorpus.c
 	$(CC) $(FLAGS) $^ -o $@$(EXT) -lm

 symbols  : symbols.c zstd-dll
@@ -233,7 +236,7 @@ else
 	$(CC) $(FLAGS) $< -o $@$(EXT) -Wl,-rpath=$(ZSTDDIR) $(ZSTDDIR)/libzstd.so   # broken on Mac
 endif

-poolTests : $(PRGDIR)/util.c poolTests.c $(ZSTDDIR)/common/pool.c $(ZSTDDIR)/common/threading.c $(ZSTDDIR)/common/zstd_common.c $(ZSTDDIR)/common/error_private.c
+poolTests : $(PRGDIR)/util.c $(PRGDIR)/timefn.c poolTests.c $(ZSTDDIR)/common/pool.c $(ZSTDDIR)/common/threading.c $(ZSTDDIR)/common/zstd_common.c $(ZSTDDIR)/common/error_private.c
 	$(CC) $(FLAGS) $(MULTITHREAD) $^ -o $@$(EXT)

 .PHONY: versionsTest
@@ -247,7 +250,7 @@ clean:
 	$(MAKE) -C $(ZSTDDIR) clean
 	$(MAKE) -C $(PRGDIR) clean
 	@$(RM) -fR $(TESTARTEFACT)
-	@$(RM) -f core *.o tmp* result* *.gcda dictionary *.zst \
+	@$(RM) -f core *.o tmp* *.tmp result* *.gcda dictionary *.zst \
        $(PRGDIR)/zstd$(EXT) $(PRGDIR)/zstd32$(EXT) \
        fullbench$(EXT) fullbench32$(EXT) \
        fullbench-lib$(EXT) fullbench-dll$(EXT) \
@@ -256,7 +259,7 @@ clean:
        zstreamtest$(EXT) zstreamtest32$(EXT) \
        datagen$(EXT) paramgrill$(EXT) roundTripCrash$(EXT) longmatch$(EXT) \
        symbols$(EXT) invalidDictionaries$(EXT) legacy$(EXT) poolTests$(EXT) \
-        decodecorpus$(EXT) checkTag$(EXT)
+        decodecorpus$(EXT) checkTag$(EXT) bigdict$(EXT)
 	@echo Cleaning completed


@@ -353,8 +356,15 @@ test-gzstd: gzstd
 	$(RM) *.gz *.zst README2.md gz_zstd zstd_gz hello.txt

 test-zstdgrep: gzstd
-	@echo a | $(PRGDIR)/zstd | $(PRGDIR)/zstdgrep a
-	@echo a | $(PRGDIR)/zstd | $(PRGDIR)/zstdgrep b && return 1 || return 0
+	-[ -f /tmp/zstdcat ] || ln -s $(PWD)/$(PRGDIR)/zstd /tmp/zstdcat
+	echo a | $(PRGDIR)/zstd | env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep a
+	echo a | $(PRGDIR)/zstd | env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep b && return 1 || return 0
+	-echo 'hello world' > test.txt && $(PRGDIR)/zstd test.txt
+	env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep hello test.txt.zst
+	env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep weird test.txt.zst && return 1 || return 0
+	-echo 'hello' > pattern.txt
+	env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep -f pattern.txt test.txt.zst
+	$(RM) test.txt test.txt.zst pattern.txt

 test-fullbench: fullbench datagen
 	$(QEMU_SYS) ./fullbench -i1
@@ -390,6 +400,9 @@ test-zstream32: zstreamtest32
 test-longmatch: longmatch
 	$(QEMU_SYS) ./longmatch

+test-bigdict: bigdict
+	$(QEMU_SYS) ./bigdict
+
 test-invalidDictionaries: invalidDictionaries
 	$(QEMU_SYS) ./invalidDictionaries

@@ -72,7 +72,7 @@ Command line tool to generate test .zst files.

 This tool will generate .zst files with checksums,
 as well as optionally output the corresponding correct uncompressed data for
-extra verfication.
+extra verification.

 Example:
 ```
@@ -123,7 +123,7 @@ Full list of arguments
                    Higher values will make optimizer run longer, more chances to find better solution.
    memLog    : Limits the log of the size of each memotable (1 per strategy). Will use hash tables when state space is larger than max size.
                    Setting memLog = 0 turns off memoization
- --display=   : specifiy which parameters are included in the output
+ --display=   : specify which parameters are included in the output
                    can use all --zstd parameter names and 'cParams' as a shorthand for all parameters used in ZSTD_compressionParameters
                    (Default: display all params available)
 -P#          : generated sample compressibility (when no file is provided)
@@ -0,0 +1,128 @@
+/*
+ * Copyright (c) 2017-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include <assert.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include "datagen.h"
+#include "mem.h"
+#define ZSTD_STATIC_LINKING_ONLY
+#include "zstd.h"
+
+static int
+compress(ZSTD_CCtx* cctx, ZSTD_DCtx* dctx,
+         void* dst, size_t dstCapacity,
+         void const* src, size_t srcSize,
+         void* roundtrip, ZSTD_EndDirective end)
+{
+    ZSTD_inBuffer in = {src, srcSize, 0};
+    ZSTD_outBuffer out = {dst, dstCapacity, 0};
+    int ended = 0;
+
+    while (!ended && (in.pos < in.size || out.pos > 0)) {
+        size_t rc;
+        out.pos = 0;
+        rc = ZSTD_compressStream2(cctx, &out, &in, end);
+        if (ZSTD_isError(rc))
+            return 1;
+        if (end == ZSTD_e_end && rc == 0)
+            ended = 1;
+        {
+            ZSTD_inBuffer rtIn = {dst, out.pos, 0};
+            ZSTD_outBuffer rtOut = {roundtrip, srcSize, 0};
+            rc = 1;
+            while (rtIn.pos < rtIn.size || rtOut.pos > 0) {
+                rtOut.pos = 0;
+                rc = ZSTD_decompressStream(dctx, &rtOut, &rtIn);
+                if (ZSTD_isError(rc)) {
+                    fprintf(stderr, "Decompression error: %s\n", ZSTD_getErrorName(rc));
+                    return 1;
+                }
+                if (rc == 0)
+                    break;
+            }
+            if (ended && rc != 0) {
+                fprintf(stderr, "Frame not finished!\n");
+                return 1;
+            }
+        }
+    }
+
+    return 0;
+}
+
+int main(int argc, const char** argv)
+{
+    ZSTD_CCtx* cctx = ZSTD_createCCtx();
+    ZSTD_DCtx* dctx = ZSTD_createDCtx();
+    const size_t dataSize = (size_t)1 << 30;
+    const size_t outSize = ZSTD_compressBound(dataSize);
+    const size_t bufferSize = (size_t)1 << 31;
+    char* buffer = (char*)malloc(bufferSize);
+    void* out = malloc(outSize);
+    void* roundtrip = malloc(dataSize);
+    (void)argc;
+    (void)argv;
+
+    if (!buffer || !out || !roundtrip || !cctx || !dctx) {
+        fprintf(stderr, "Allocation failure\n");
+        return 1;
+    }
+
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_windowLog, 31)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 1)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_overlapLog, 9)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_strategy, ZSTD_btopt)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_targetLength, 7)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_minMatch, 7)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_searchLog, 1)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 10)))
+        return 1;
+    if (ZSTD_isError(ZSTD_CCtx_setParameter(cctx, ZSTD_c_chainLog, 10)))
+        return 1;
+
+    if (ZSTD_isError(ZSTD_DCtx_setParameter(dctx, ZSTD_d_windowLogMax, 31)))
+        return 1;
+
+    RDG_genBuffer(buffer, bufferSize, 1.0, 0.0, 0xbeefcafe);
+
+    /* Compress 30 GB */
+    {
+        int i;
+        for (i = 0; i < 10; ++i) {
+            fprintf(stderr, "Compressing 1 GB\n");
+            if (compress(cctx, dctx, out, outSize, buffer, dataSize, roundtrip, ZSTD_e_continue))
+                return 1;
+        }
+    }
+    fprintf(stderr, "Compressing 1 GB\n");
+    if (compress(cctx, dctx, out, outSize, buffer, dataSize, roundtrip, ZSTD_e_end))
+        return 1;
+
+    fprintf(stderr, "Success!\n");
+
+    free(roundtrip);
+    free(out);
+    free(buffer);
+    ZSTD_freeDCtx(dctx);
+    ZSTD_freeCCtx(cctx);
+    return 0;
+}
@@ -16,6 +16,7 @@
 #include <string.h>

 #include "util.h"
+#include "timefn.h"   /* UTIL_clockSpanMicro, SEC_TO_MICRO, UTIL_TIME_INITIALIZER */
 #include "zstd.h"
 #include "zstd_internal.h"
 #include "mem.h"
@@ -513,7 +514,7 @@ static size_t writeLiteralsBlockCompressed(U32* seed, frame_t* frame, size_t con
        if ((RAND(seed) & 3) || !frame->stats.hufInit) {
            do {
                if (RAND(seed) & 3) {
-                    /* add 10 to ensure some compressability */
+                    /* add 10 to ensure some compressibility */
                    double const weight = ((RAND(seed) % 90) + 10) / 100.0;

                    DISPLAYLEVEL(5, "    distribution weight: %d%%\n",
@@ -839,16 +840,16 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
    {   unsigned max = MaxLL;
        size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, WKSP, sizeof(WKSP));   /* cannot fail */
        assert(!HIST_isError(mostFrequent));
-        if (mostFrequent == nbSeq) {
-            /* do RLE if we have the chance */
-            *op++ = llCodeTable[0];
-            FSE_buildCTable_rle(CTable_LitLength, (BYTE)max);
-            LLtype = set_rle;
-        } else if (frame->stats.fseInit && !(RAND(seed) & 3) &&
+        if (frame->stats.fseInit && !(RAND(seed) & 3) &&
                   isSymbolSubset(llCodeTable, nbSeq,
                                  frame->stats.litlengthSymbolSet, 35)) {
            /* maybe do repeat mode if we're allowed to */
            LLtype = set_repeat;
+        } else if (mostFrequent == nbSeq) {
+            /* do RLE if we have the chance */
+            *op++ = llCodeTable[0];
+            FSE_buildCTable_rle(CTable_LitLength, (BYTE)max);
+            LLtype = set_rle;
        } else if (!(RAND(seed) & 3)) {
            /* maybe use the default distribution */
            FSE_buildCTable_wksp(CTable_LitLength, LL_defaultNorm, MaxLL, LL_defaultNormLog, scratchBuffer, sizeof(scratchBuffer));
@@ -871,14 +872,14 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
    {   unsigned max = MaxOff;
        size_t const mostFrequent = HIST_countFast_wksp(count, &max, ofCodeTable, nbSeq, WKSP, sizeof(WKSP));   /* cannot fail */
        assert(!HIST_isError(mostFrequent));
-        if (mostFrequent == nbSeq) {
-            *op++ = ofCodeTable[0];
-            FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max);
-            Offtype = set_rle;
-        } else if (frame->stats.fseInit && !(RAND(seed) & 3) &&
+        if (frame->stats.fseInit && !(RAND(seed) & 3) &&
                   isSymbolSubset(ofCodeTable, nbSeq,
                                  frame->stats.offsetSymbolSet, 28)) {
            Offtype = set_repeat;
+        } else if (mostFrequent == nbSeq) {
+            *op++ = ofCodeTable[0];
+            FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max);
+            Offtype = set_rle;
        } else if (!(RAND(seed) & 3)) {
            FSE_buildCTable_wksp(CTable_OffsetBits, OF_defaultNorm, DefaultMaxOff, OF_defaultNormLog, scratchBuffer, sizeof(scratchBuffer));
            Offtype = set_basic;
@@ -899,14 +900,14 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
    {   unsigned max = MaxML;
        size_t const mostFrequent = HIST_countFast_wksp(count, &max, mlCodeTable, nbSeq, WKSP, sizeof(WKSP));   /* cannot fail */
        assert(!HIST_isError(mostFrequent));
-        if (mostFrequent == nbSeq) {
-            *op++ = *mlCodeTable;
-            FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max);
-            MLtype = set_rle;
-        } else if (frame->stats.fseInit && !(RAND(seed) & 3) &&
+        if (frame->stats.fseInit && !(RAND(seed) & 3) &&
                   isSymbolSubset(mlCodeTable, nbSeq,
                                  frame->stats.matchlengthSymbolSet, 52)) {
            MLtype = set_repeat;
+        } else if (mostFrequent == nbSeq) {
+            *op++ = *mlCodeTable;
+            FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max);
+            MLtype = set_rle;
        } else if (!(RAND(seed) & 3)) {
            /* sometimes do default distribution */
            FSE_buildCTable_wksp(CTable_MatchLength, ML_defaultNorm, MaxML, ML_defaultNormLog, scratchBuffer, sizeof(scratchBuffer));
@@ -938,7 +939,9 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
        FSE_CState_t  stateOffsetBits;
        FSE_CState_t  stateLitLength;

-        CHECK_E(BIT_initCStream(&blockStream, op, oend-op), dstSize_tooSmall); /* not enough space remaining */
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initCStream(&blockStream, op, oend-op)),
+            dstSize_tooSmall, "not enough space remaining");

        /* first symbols */
        FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
@@ -1047,8 +1050,8 @@ static void writeBlock(U32* seed, frame_t* frame, size_t contentSize,
        op += contentSize;
        blockType = 0;
        blockSize = contentSize;
-    } else if (blockTypeDesc == 1) {
-        /* RLE */
+    } else if (blockTypeDesc == 1 && frame->header.contentSize > 0) {
+        /* RLE (Don't create RLE block if frame content is 0 since block size of 1 may exceed max block size)*/
        BYTE const symbol = RAND(seed) & 0xff;

        op[0] = symbol;
@@ -15,8 +15,9 @@
 #include "util.h"        /* Compiler options, UTIL_GetFileSize */
 #include <stdlib.h>      /* malloc */
 #include <stdio.h>       /* fprintf, fopen, ftello64 */
-#include <assert.h>      /* assert */
+#include <assert.h>

+#include "timefn.h"      /* UTIL_clockSpanNano, UTIL_getTime */
 #include "mem.h"         /* U32 */
 #ifndef ZSTD_DLL_IMPORT
    #include "zstd_internal.h"   /* ZSTD_decodeSeqHeaders, ZSTD_blockHeaderSize, blockType_e, KB, MB */
@@ -30,8 +31,8 @@
 #include "zstd.h"        /* ZSTD_versionString */
 #include "util.h"        /* time functions */
 #include "datagen.h"
-#include "benchfn.h"       /* CustomBench*/
-#include "benchzstd.h"     /* MB_UNIT */
+#include "benchfn.h"     /* CustomBench */
+#include "benchzstd.h"   /* MB_UNIT */


 /*_************************************
@@ -50,7 +51,7 @@
 #define DEFAULT_CLEVEL 1

 #define COMPRESSIBILITY_DEFAULT 0.50
-static const size_t g_sampleSize = 10000000;
+static const size_t kSampleSizeDefault = 10000000;

 #define TIMELOOP_NANOSEC      (1*1000000000ULL) /* 1 second */

@@ -60,18 +61,12 @@ static const size_t g_sampleSize = 10000000;
 **************************************/
 #define DISPLAY(...)  fprintf(stderr, __VA_ARGS__)

+#define CONTROL(c)  { if (!(c)) { abort(); } }   /* like assert(), but cannot be disabled */

 /*_************************************
 *  Benchmark Parameters
 **************************************/
 static unsigned g_nbIterations = NBLOOPS;
-static double g_compressibility = COMPRESSIBILITY_DEFAULT;
-
-static void BMK_SetNbIterations(unsigned nbLoops)
-{
-    g_nbIterations = nbLoops;
-    DISPLAY("- %i iterations -\n", g_nbIterations);
-}


 /*_*******************************************************
@@ -105,12 +100,12 @@ static ZSTD_CCtx* g_zcc = NULL;
 static size_t
 local_ZSTD_compress(const void* src, size_t srcSize,
                    void* dst, size_t dstSize,
-                    void* buff2)
+                    void* payload)
 {
    ZSTD_parameters p;
    ZSTD_frameParameters f = { 1 /* contentSizeHeader*/, 0, 0 };
    p.fParams = f;
-    p.cParams = *(ZSTD_compressionParameters*)buff2;
+    p.cParams = *(ZSTD_compressionParameters*)payload;
    return ZSTD_compress_advanced (g_zcc, dst, dstSize, src, srcSize, NULL ,0, p);
    //return ZSTD_compress(dst, dstSize, src, srcSize, cLevel);
 }
@@ -131,7 +126,7 @@ extern size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* ctx, const void* src, size_t s
 static size_t local_ZSTD_decodeLiteralsBlock(const void* src, size_t srcSize, void* dst, size_t dstSize, void* buff2)
 {
    (void)src; (void)srcSize; (void)dst; (void)dstSize;
-    return ZSTD_decodeLiteralsBlock((ZSTD_DCtx*)g_zdc, buff2, g_cSize);
+    return ZSTD_decodeLiteralsBlock(g_zdc, buff2, g_cSize);
 }

 static size_t local_ZSTD_decodeSeqHeaders(const void* src, size_t srcSize, void* dst, size_t dstSize, void* buff2)
@@ -146,14 +141,14 @@ static ZSTD_CStream* g_cstream= NULL;
 static size_t
 local_ZSTD_compressStream(const void* src, size_t srcSize,
                          void* dst, size_t dstCapacity,
-                          void* buff2)
+                          void* payload)
 {
    ZSTD_outBuffer buffOut;
    ZSTD_inBuffer buffIn;
    ZSTD_parameters p;
    ZSTD_frameParameters f = {1 /* contentSizeHeader*/, 0, 0};
    p.fParams = f;
-    p.cParams = *(ZSTD_compressionParameters*)buff2;
+    p.cParams = *(ZSTD_compressionParameters*)payload;
    ZSTD_initCStream_advanced(g_cstream, NULL, 0, p, ZSTD_CONTENTSIZE_UNKNOWN);
    buffOut.dst = dst;
    buffOut.size = dstCapacity;
@@ -166,23 +161,39 @@ local_ZSTD_compressStream(const void* src, size_t srcSize,
    return buffOut.pos;
 }

+static size_t
+local_ZSTD_compressStream_freshCCtx(const void* src, size_t srcSize,
+                          void* dst, size_t dstCapacity,
+                          void* payload)
+{
+    ZSTD_CCtx* const cctx = ZSTD_createCCtx();
+    size_t r;
+    assert(cctx != NULL);
+
+    r = local_ZSTD_compressStream(src, srcSize, dst, dstCapacity, payload);
+
+    ZSTD_freeCCtx(cctx);
+
+    return r;
+}
+
 static size_t
 local_ZSTD_compress_generic_end(const void* src, size_t srcSize,
                                void* dst, size_t dstCapacity,
-                                void* buff2)
+                                void* payload)
 {
-    (void)buff2;
+    (void)payload;
    return ZSTD_compress2(g_cstream, dst, dstCapacity, src, srcSize);
 }

 static size_t
 local_ZSTD_compress_generic_continue(const void* src, size_t srcSize,
                                     void* dst, size_t dstCapacity,
-                                     void* buff2)
+                                     void* payload)
 {
    ZSTD_outBuffer buffOut;
    ZSTD_inBuffer buffIn;
-    (void)buff2;
+    (void)payload;
    buffOut.dst = dst;
    buffOut.size = dstCapacity;
    buffOut.pos = 0;
@@ -197,9 +208,9 @@ local_ZSTD_compress_generic_continue(const void* src, size_t srcSize,
 static size_t
 local_ZSTD_compress_generic_T2_end(const void* src, size_t srcSize,
                                   void* dst, size_t dstCapacity,
-                                   void* buff2)
+                                   void* payload)
 {
-    (void)buff2;
+    (void)payload;
    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_nbWorkers, 2);
    return ZSTD_compress2(g_cstream, dst, dstCapacity, src, srcSize);
 }
@@ -207,11 +218,11 @@ local_ZSTD_compress_generic_T2_end(const void* src, size_t srcSize,
 static size_t
 local_ZSTD_compress_generic_T2_continue(const void* src, size_t srcSize,
                                        void* dst, size_t dstCapacity,
-                                        void* buff2)
+                                        void* payload)
 {
    ZSTD_outBuffer buffOut;
    ZSTD_inBuffer buffIn;
-    (void)buff2;
+    (void)payload;
    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_nbWorkers, 2);
    buffOut.dst = dst;
    buffOut.size = dstCapacity;
@@ -247,27 +258,28 @@ local_ZSTD_decompressStream(const void* src, size_t srcSize,
 #ifndef ZSTD_DLL_IMPORT
 static size_t local_ZSTD_compressContinue(const void* src, size_t srcSize,
                                          void* dst, size_t dstCapacity,
-                                          void* buff2)
+                                          void* payload)
 {
    ZSTD_parameters p;
    ZSTD_frameParameters f = { 1 /* contentSizeHeader*/, 0, 0 };
    p.fParams = f;
-    p.cParams = *(ZSTD_compressionParameters*)buff2;
+    p.cParams = *(ZSTD_compressionParameters*)payload;
    ZSTD_compressBegin_advanced(g_zcc, NULL, 0, p, srcSize);
    return ZSTD_compressEnd(g_zcc, dst, dstCapacity, src, srcSize);
 }

 #define FIRST_BLOCK_SIZE 8
-static size_t local_ZSTD_compressContinue_extDict(const void* src, size_t srcSize,
-                                                  void* dst, size_t dstCapacity,
-                                                  void* buff2)
+static size_t
+local_ZSTD_compressContinue_extDict(const void* src, size_t srcSize,
+                                    void* dst, size_t dstCapacity,
+                                    void* payload)
 {
    BYTE firstBlockBuf[FIRST_BLOCK_SIZE];

    ZSTD_parameters p;
-    ZSTD_frameParameters f = { 1, 0, 0 };
+    ZSTD_frameParameters const f = { 1, 0, 0 };
    p.fParams = f;
-    p.cParams = *(ZSTD_compressionParameters*)buff2;
+    p.cParams = *(ZSTD_compressionParameters*)payload;
    ZSTD_compressBegin_advanced(g_zcc, NULL, 0, p, srcSize);
    memcpy(firstBlockBuf, src, FIRST_BLOCK_SIZE);

@@ -316,14 +328,14 @@ static size_t local_ZSTD_decompressContinue(const void* src, size_t srcSize,
 /*_*******************************************************
 *  Bench functions
 *********************************************************/
-static size_t benchMem(unsigned benchNb,
-                       const void* src, size_t srcSize,
-                       int cLevel, ZSTD_compressionParameters cparams)
+static int benchMem(unsigned benchNb,
+                    const void* src, size_t srcSize,
+                    int cLevel, ZSTD_compressionParameters cparams)
 {
    size_t dstBuffSize = ZSTD_compressBound(srcSize);
    BYTE*  dstBuff;
    void*  dstBuff2;
-    void*  buff2;
+    void*  payload;
    const char* benchName;
    BMK_benchFn_t benchFunction;
    int errorcode = 0;
@@ -360,6 +372,9 @@ static size_t benchMem(unsigned benchNb,
    case 42:
        benchFunction = local_ZSTD_decompressStream; benchName = "decompressStream";
        break;
+    case 43:
+        benchFunction = local_ZSTD_compressStream_freshCCtx; benchName = "compressStream_freshCCtx";
+        break;
    case 51:
        benchFunction = local_ZSTD_compress_generic_continue; benchName = "compress_generic, continue";
        break;
@@ -384,7 +399,7 @@ static size_t benchMem(unsigned benchNb,
        free(dstBuff); free(dstBuff2);
        return 12;
    }
-    buff2 = dstBuff2;
+    payload = dstBuff2;
    if (g_zcc==NULL) g_zcc = ZSTD_createCCtx();
    if (g_zdc==NULL) g_zdc = ZSTD_createDCtx();
    if (g_cstream==NULL) g_cstream = ZSTD_createCStream();
@@ -395,83 +410,88 @@ static size_t benchMem(unsigned benchNb,
          cparams->minMatch, cparams->targetLength, cparams->strategy); */

    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_compressionLevel, cLevel);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_windowLog, cparams.windowLog);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_hashLog, cparams.hashLog);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_chainLog, cparams.chainLog);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_searchLog, cparams.searchLog);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_minMatch, cparams.minMatch);
-    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_targetLength, cparams.targetLength);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_windowLog, (int)cparams.windowLog);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_hashLog, (int)cparams.hashLog);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_chainLog, (int)cparams.chainLog);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_searchLog, (int)cparams.searchLog);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_minMatch, (int)cparams.minMatch);
+    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_targetLength, (int)cparams.targetLength);
    ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_strategy, cparams.strategy);


    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_compressionLevel, cLevel);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_windowLog, cparams.windowLog);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_hashLog, cparams.hashLog);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_chainLog, cparams.chainLog);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_searchLog, cparams.searchLog);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_minMatch, cparams.minMatch);
-    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_targetLength, cparams.targetLength);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_windowLog, (int)cparams.windowLog);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_hashLog, (int)cparams.hashLog);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_chainLog, (int)cparams.chainLog);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_searchLog, (int)cparams.searchLog);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_minMatch, (int)cparams.minMatch);
+    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_targetLength, (int)cparams.targetLength);
    ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_strategy, cparams.strategy);

    /* Preparation */
    switch(benchNb)
    {
    case 1:
-        buff2 = &cparams;
+        payload = &cparams;
        break;
    case 2:
-        g_cSize = ZSTD_compress(buff2, dstBuffSize, src, srcSize, cLevel);
+        g_cSize = ZSTD_compress(dstBuff2, dstBuffSize, src, srcSize, cLevel);
        break;
 #ifndef ZSTD_DLL_IMPORT
    case 11:
-        buff2 = &cparams;
+        payload = &cparams;
        break;
    case 12:
-        buff2 = &cparams;
+        payload = &cparams;
        break;
    case 13 :
-        g_cSize = ZSTD_compress(buff2, dstBuffSize, src, srcSize, cLevel);
+        g_cSize = ZSTD_compress(dstBuff2, dstBuffSize, src, srcSize, cLevel);
        break;
-    case 31:  /* ZSTD_decodeLiteralsBlock */
-        {   blockProperties_t bp;
-            ZSTD_frameHeader zfp;
-            size_t frameHeaderSize, skippedSize;
+    case 31:  /* ZSTD_decodeLiteralsBlock : starts literals block in dstBuff2 */
+        {   size_t frameHeaderSize;
            g_cSize = ZSTD_compress(dstBuff, dstBuffSize, src, srcSize, cLevel);
-            frameHeaderSize = ZSTD_getFrameHeader(&zfp, dstBuff, ZSTD_FRAMEHEADERSIZE_MIN);
-            if (frameHeaderSize==0) frameHeaderSize = ZSTD_FRAMEHEADERSIZE_MIN;
-            ZSTD_getcBlockSize(dstBuff+frameHeaderSize, dstBuffSize, &bp);  /* Get 1st block type */
-            if (bp.blockType != bt_compressed) {
-                DISPLAY("ZSTD_decodeLiteralsBlock : impossible to test on this sample (not compressible)\n");
-                goto _cleanOut;
+            frameHeaderSize = ZSTD_frameHeaderSize(dstBuff, ZSTD_FRAMEHEADERSIZE_PREFIX);
+            CONTROL(!ZSTD_isError(frameHeaderSize));
+            /* check block is compressible, hence contains a literals section */
+            {   blockProperties_t bp;
+                ZSTD_getcBlockSize(dstBuff+frameHeaderSize, dstBuffSize, &bp);  /* Get 1st block type */
+                if (bp.blockType != bt_compressed) {
+                    DISPLAY("ZSTD_decodeLiteralsBlock : impossible to test on this sample (not compressible)\n");
+                    goto _cleanOut;
+            }   }
+            {   size_t const skippedSize = frameHeaderSize + ZSTD_blockHeaderSize;
+                memcpy(dstBuff2, dstBuff+skippedSize, g_cSize-skippedSize);
            }
-            skippedSize = frameHeaderSize + ZSTD_blockHeaderSize;
-            memcpy(buff2, dstBuff+skippedSize, g_cSize-skippedSize);
            srcSize = srcSize > 128 KB ? 128 KB : srcSize;    /* speed relative to block */
            ZSTD_decompressBegin(g_zdc);
            break;
        }
    case 32:   /* ZSTD_decodeSeqHeaders */
        {   blockProperties_t bp;
-            ZSTD_frameHeader zfp;
            const BYTE* ip = dstBuff;
            const BYTE* iend;
-            size_t frameHeaderSize, cBlockSize;
-            ZSTD_compress(dstBuff, dstBuffSize, src, srcSize, cLevel);   /* it would be better to use direct block compression here */
-            g_cSize = ZSTD_compress(dstBuff, dstBuffSize, src, srcSize, cLevel);
-            frameHeaderSize = ZSTD_getFrameHeader(&zfp, dstBuff, ZSTD_FRAMEHEADERSIZE_MIN);
-            if (frameHeaderSize==0) frameHeaderSize = ZSTD_FRAMEHEADERSIZE_MIN;
-            ip += frameHeaderSize;   /* Skip frame Header */
-            cBlockSize = ZSTD_getcBlockSize(ip, dstBuffSize, &bp);   /* Get 1st block type */
-            if (bp.blockType != bt_compressed) {
-                DISPLAY("ZSTD_decodeSeqHeaders : impossible to test on this sample (not compressible)\n");
-                goto _cleanOut;
+            {   size_t const cSize = ZSTD_compress(dstBuff, dstBuffSize, src, srcSize, cLevel);
+                CONTROL(cSize > ZSTD_FRAMEHEADERSIZE_PREFIX);
            }
-            iend = ip + ZSTD_blockHeaderSize + cBlockSize;   /* End of first block */
-            ip += ZSTD_blockHeaderSize;                      /* skip block header */
+            /* Skip frame Header */
+            {   size_t const frameHeaderSize = ZSTD_frameHeaderSize(dstBuff, ZSTD_FRAMEHEADERSIZE_PREFIX);
+                CONTROL(!ZSTD_isError(frameHeaderSize));
+                ip += frameHeaderSize;
+            }
+            /* Find end of block */
+            {   size_t const cBlockSize = ZSTD_getcBlockSize(ip, dstBuffSize, &bp);   /* Get 1st block type */
+                if (bp.blockType != bt_compressed) {
+                    DISPLAY("ZSTD_decodeSeqHeaders : impossible to test on this sample (not compressible)\n");
+                    goto _cleanOut;
+                }
+                iend = ip + ZSTD_blockHeaderSize + cBlockSize;   /* End of first block */
+            }
+            ip += ZSTD_blockHeaderSize;    /* skip block header */
            ZSTD_decompressBegin(g_zdc);
-            ip += ZSTD_decodeLiteralsBlock(g_zdc, ip, iend-ip);   /* skip literal segment */
-            g_cSize = iend-ip;
-            memcpy(buff2, ip, g_cSize);   /* copy rest of block (it starts by SeqHeader) */
+            CONTROL(iend > ip);
+            ip += ZSTD_decodeLiteralsBlock(g_zdc, ip, (size_t)(iend-ip));   /* skip literal segment */
+            g_cSize = (size_t)(iend-ip);
+            memcpy(dstBuff2, ip, g_cSize);   /* copy rest of block (it starts by SeqHeader) */
            srcSize = srcSize > 128 KB ? 128 KB : srcSize;   /* speed relative to block */
            break;
        }
@@ -480,10 +500,13 @@ static size_t benchMem(unsigned benchNb,
        goto _cleanOut;
 #endif
    case 41 :
-        buff2 = &cparams;
+        payload = &cparams;
        break;
    case 42 :
-        g_cSize = ZSTD_compress(buff2, dstBuffSize, src, srcSize, cLevel);
+        g_cSize = ZSTD_compress(payload, dstBuffSize, src, srcSize, cLevel);
+        break;
+    case 43 :
+        payload = &cparams;
        break;

    /* test functions */
@@ -501,11 +524,11 @@ static size_t benchMem(unsigned benchNb,
        BMK_benchParams_t bp;
        BMK_runTime_t bestResult;
        bestResult.sumOfReturn = 0;
-        bestResult.nanoSecPerRun = (unsigned long long)(-1LL);
-        assert(tfs != NULL);
+        bestResult.nanoSecPerRun = (double)TIMELOOP_NANOSEC * 2000000000;  /* hopefully large enough : must be larger than any potential measurement */
+        CONTROL(tfs != NULL);

        bp.benchFn = benchFunction;
-        bp.benchPayload = buff2;
+        bp.benchPayload = payload;
        bp.initFn = NULL;
        bp.initPayload = NULL;
        bp.errorFn = ZSTD_isError;
@@ -553,21 +576,19 @@ _cleanOut:


 static int benchSample(U32 benchNb,
+                       size_t benchedSize, double compressibility,
                       int cLevel, ZSTD_compressionParameters cparams)
 {
-    size_t const benchedSize = g_sampleSize;
-    const char* const name = "Sample 10MiB";
-
    /* Allocation */
    void* const origBuff = malloc(benchedSize);
    if (!origBuff) { DISPLAY("\nError: not enough memory!\n"); return 12; }

    /* Fill buffer */
-    RDG_genBuffer(origBuff, benchedSize, g_compressibility, 0.0, 0);
+    RDG_genBuffer(origBuff, benchedSize, compressibility, 0.0, 0);

    /* bench */
    DISPLAY("\r%70s\r", "");
-    DISPLAY(" %s : \n", name);
+    DISPLAY(" Sample %u bytes : \n", (unsigned)benchedSize);
    if (benchNb) {
        benchMem(benchNb, origBuff, benchedSize, cLevel, cparams);
    } else {  /* 0 == run all tests */
@@ -654,7 +675,9 @@ static unsigned readU32FromChar(const char** stringPtr)
    while ((**stringPtr >='0') && (**stringPtr <='9')) {
        unsigned const max = (((unsigned)(-1)) / 10) - 1;
        if (result > max) ERROR_OUT(errorMsg);
-        result *= 10, result += **stringPtr - '0', (*stringPtr)++ ;
+        result *= 10;
+        result += (unsigned)(**stringPtr - '0');
+        (*stringPtr)++ ;
    }
    if ((**stringPtr=='K') || (**stringPtr=='M')) {
        unsigned const maxK = ((unsigned)(-1)) >> 10;
@@ -671,7 +694,7 @@ static unsigned readU32FromChar(const char** stringPtr)
    return result;
 }

-static unsigned longCommandWArg(const char** stringPtr, const char* longCommand)
+static int longCommandWArg(const char** stringPtr, const char* longCommand)
 {
    size_t const comSize = strlen(longCommand);
    int const result = !strncmp(*stringPtr, longCommand, comSize);
@@ -698,10 +721,11 @@ static int usage_advanced(const char* exename)
    usage(exename);
    DISPLAY( "\nAdvanced options :\n");
    DISPLAY( " -b#    : test only function # \n");
-    DISPLAY( " -i#    : iteration loops [1-9](default : %i)\n", NBLOOPS);
-    DISPLAY( " -P#    : sample compressibility (default : %.1f%%)\n", COMPRESSIBILITY_DEFAULT * 100);
    DISPLAY( " -l#    : benchmark functions at that compression level (default : %i)\n", DEFAULT_CLEVEL);
    DISPLAY( " --zstd : custom parameter selection. Format same as zstdcli \n");
+    DISPLAY( " -P#    : sample compressibility (default : %.1f%%)\n", COMPRESSIBILITY_DEFAULT * 100);
+    DISPLAY( " -B#    : sample size (default : %u)\n", (unsigned)kSampleSizeDefault);
+    DISPLAY( " -i#    : iteration loops [1-9](default : %i)\n", NBLOOPS);
    return 0;
 }

@@ -720,13 +744,15 @@ int main(int argc, const char** argv)
    U32 benchNb = 0, main_pause = 0;
    int cLevel = DEFAULT_CLEVEL;
    ZSTD_compressionParameters cparams = ZSTD_getCParams(cLevel, 0, 0);
+    size_t sampleSize = kSampleSizeDefault;
+    double compressibility = COMPRESSIBILITY_DEFAULT;

    DISPLAY(WELCOME_MESSAGE);
    if (argc<1) return badusage(exename);

    for (argNb=1; argNb<argc; argNb++) {
        const char* argument = argv[argNb];
-        assert(argument != NULL);
+        CONTROL(argument != NULL);

        if (longCommandWArg(&argument, "--zstd=")) {
            for ( ; ;) {
@@ -769,21 +795,29 @@ int main(int argc, const char** argv)
                    benchNb = readU32FromChar(&argument);
                    break;

-                    /* Modify Nb Iterations */
-                case 'i':
+                    /* Select compression level to use */
+                case 'l':
                    argument++;
-                    BMK_SetNbIterations((int)readU32FromChar(&argument));
+                    cLevel = (int)readU32FromChar(&argument);
+                    cparams = ZSTD_getCParams(cLevel, 0, 0);
                    break;

                    /* Select compressibility of synthetic sample */
                case 'P':
                    argument++;
-                    g_compressibility = (double)readU32FromChar(&argument) / 100.;
+                    compressibility = (double)readU32FromChar(&argument) / 100.;
                    break;
-                case 'l':
+
+                    /* Select size of synthetic sample */
+                case 'B':
                    argument++;
-                    cLevel = readU32FromChar(&argument);
-                    cparams = ZSTD_getCParams(cLevel, 0, 0);
+                    sampleSize = (size_t)readU32FromChar(&argument);
+                    break;
+
+                    /* Modify Nb Iterations */
+                case 'i':
+                    argument++;
+                    g_nbIterations = readU32FromChar(&argument);
                    break;

                    /* Unknown command */
@@ -800,7 +834,7 @@ int main(int argc, const char** argv)


    if (filenamesStart==0)   /* no input file */
-        result = benchSample(benchNb, cLevel, cparams);
+        result = benchSample(benchNb, sampleSize, compressibility, cLevel, cparams);
    else
        result = benchFiles(benchNb, argv+filenamesStart, argc-filenamesStart, cLevel, cparams);

@@ -26,17 +26,17 @@ ZSTDDIR = ../../lib
 PRGDIR = ../../programs

 FUZZ_CPPFLAGS := -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
-	-I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR) \
-	$(CPPFLAGS)
+	-I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(ZSTDDIR)/legacy \
+	-I$(PRGDIR) -DZSTD_MULTITHREAD -DZSTD_LEGACY_SUPPORT=1 $(CPPFLAGS)
 FUZZ_EXTRA_FLAGS := -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
 	-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-	-Wstrict-prototypes -Wundef -Wformat-security \
+	-Wstrict-prototypes -Wundef \
 	-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
 	-Wredundant-decls \
 	-g -fno-omit-frame-pointer
 FUZZ_CFLAGS := $(FUZZ_EXTRA_FLAGS) $(CFLAGS)
 FUZZ_CXXFLAGS := $(FUZZ_EXTRA_FLAGS) -std=c++11 $(CXXFLAGS)
-FUZZ_LDFLAGS := $(LDFLAGS)
+FUZZ_LDFLAGS := -pthread $(LDFLAGS)
 FUZZ_ARFLAGS := $(ARFLAGS)
 FUZZ_TARGET_FLAGS = $(FUZZ_CPPFLAGS) $(FUZZ_CXXFLAGS) $(FUZZ_LDFLAGS)

@@ -46,11 +46,15 @@ FUZZ_SRC := $(PRGDIR)/util.c zstd_helpers.c
 ZSTDCOMMON_SRC := $(ZSTDDIR)/common/*.c
 ZSTDCOMP_SRC   := $(ZSTDDIR)/compress/*.c
 ZSTDDECOMP_SRC := $(ZSTDDIR)/decompress/*.c
+ZSTDDICT_SRC := $(ZSTDDIR)/dictBuilder/*.c
+ZSTDLEGACY_SRC := $(ZSTDDIR)/legacy/*.c
 FUZZ_SRC       := \
 	$(FUZZ_SRC) \
 	$(ZSTDDECOMP_SRC) \
 	$(ZSTDCOMMON_SRC) \
-	$(ZSTDCOMP_SRC)
+	$(ZSTDCOMP_SRC) \
+	$(ZSTDDICT_SRC) \
+	$(ZSTDLEGACY_SRC)

 FUZZ_OBJ := $(patsubst %.c,%.o, $(wildcard $(FUZZ_SRC)))

@@ -65,7 +69,11 @@ FUZZ_TARGETS :=       \
 	block_round_trip  \
 	simple_decompress \
 	stream_decompress \
-	block_decompress
+	block_decompress  \
+	dictionary_round_trip \
+	dictionary_decompress \
+	zstd_frame_info \
+	simple_compress

 all: $(FUZZ_TARGETS)

@@ -90,11 +98,23 @@ stream_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) stream_decompress.o
 block_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) block_decompress.o
 	$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) block_decompress.o $(LIB_FUZZING_ENGINE) -o $@

+dictionary_round_trip: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_round_trip.o
+	$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_round_trip.o $(LIB_FUZZING_ENGINE) -o $@
+
+dictionary_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_decompress.o
+	$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_decompress.o $(LIB_FUZZING_ENGINE) -o $@
+
+simple_compress: $(FUZZ_HEADERS) $(FUZZ_OBJ) simple_compress.o
+	$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) simple_compress.o $(LIB_FUZZING_ENGINE) -o $@
+
+zstd_frame_info: $(FUZZ_HEADERS) $(FUZZ_OBJ) zstd_frame_info.o
+	$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) zstd_frame_info.o $(LIB_FUZZING_ENGINE) -o $@
+
 libregression.a: $(FUZZ_HEADERS) $(PRGDIR)/util.h $(PRGDIR)/util.c regression_driver.o
 	$(AR) $(FUZZ_ARFLAGS) $@ regression_driver.o

 # Install libfuzzer (not usable for MSAN testing)
-# Provided for convienence. To use this library run make libFuzzer and
+# Provided for convenience. To use this library run make libFuzzer and
 # set LDFLAGS=-L.
 .PHONY: libFuzzer
 libFuzzer:
@@ -112,6 +132,9 @@ corpora/%: corpora/%_seed_corpus.zip
 .PHONY: corpora
 corpora: $(patsubst %,corpora/%,$(FUZZ_TARGETS))

+.PHONY: seedcorpora
+seedcorpora: $(patsubst %,corpora/%_seed_corpus.zip,$(FUZZ_TARGETS))
+
 regressiontest: corpora
 	CC="$(CC)" CXX="$(CXX)" CFLAGS="$(CFLAGS)" CXXFLAGS="$(CXXFLAGS)" LDFLAGS="$(LDFLAGS)" $(PYTHON) ./fuzz.py build all
 	$(PYTHON) ./fuzz.py regression all
@@ -120,7 +143,9 @@ clean:
 	@$(MAKE) -C $(ZSTDDIR) clean
 	@$(RM) *.a *.o
 	@$(RM) simple_round_trip stream_round_trip simple_decompress \
-           stream_decompress block_decompress block_round_trip
+           stream_decompress block_decompress block_round_trip \
+           simple_compress dictionary_round_trip dictionary_decompress \
+           zstd_frame_info

 cleanall:
 	@$(RM) -r Fuzzer
@@ -37,8 +37,8 @@ The specific fuzzing engine is selected with `LIB_FUZZING_ENGINE` or
 `--lib-fuzzing-engine`, the default is `libregression.a`.
 It has flags that can easily set up sanitizers `--enable-{a,ub,m}san`, and
 coverage instrumentation `--enable-coverage`.
-It sets sane defaults which can be overriden with flags `--debug`,
-`--enable-ubsan-pointer-overlow`, etc.
+It sets sane defaults which can be overridden with flags `--debug`,
+`--enable-ubsan-pointer-overflow`, etc.
 Run `./fuzz.py build -h` for help.

 ### Running Fuzzers
@@ -1,2 +0,0 @@
-[libfuzzer]
-max_len = 8192
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ */
+
+/**
+ * This fuzz target attempts to decompress the fuzzed data with the dictionary
+ * decompression function to ensure the decompressor never crashes. It does not
+ * fuzz the dictionary.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "fuzz_helpers.h"
+#include "zstd_helpers.h"
+
+static ZSTD_DCtx *dctx = NULL;
+
+int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
+{
+    uint32_t seed = FUZZ_seed(&src, &size);
+    FUZZ_dict_t dict;
+    ZSTD_DDict* ddict = NULL;
+    int i;
+
+    if (!dctx) {
+        dctx = ZSTD_createDCtx();
+        FUZZ_ASSERT(dctx);
+    }
+    dict = FUZZ_train(src, size, &seed);
+    if (FUZZ_rand32(&seed, 0, 1) == 0) {
+        ddict = ZSTD_createDDict(dict.buff, dict.size);
+        FUZZ_ASSERT(ddict);
+    } else {
+        FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced(
+                dctx, dict.buff, dict.size,
+                (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
+                (ZSTD_dictContentType_e)FUZZ_rand32(&seed, 0, 2)));
+    }
+    /* Run it 10 times over 10 output sizes. Reuse the context and dict. */
+    for (i = 0; i < 10; ++i) {
+        size_t const bufSize = FUZZ_rand32(&seed, 0, 2 * size);
+        void* rBuf = malloc(bufSize);
+        FUZZ_ASSERT(rBuf);
+        if (ddict) {
+            ZSTD_decompress_usingDDict(dctx, rBuf, bufSize, src, size, ddict);
+        } else {
+            ZSTD_decompressDCtx(dctx, rBuf, bufSize, src, size);
+        }
+        free(rBuf);
+    }
+    free(dict.buff);
+    ZSTD_freeDDict(ddict);
+#ifndef STATEFUL_FUZZING
+    ZSTD_freeDCtx(dctx); dctx = NULL;
+#endif
+    return 0;
+}
@@ -0,0 +1,106 @@
+/*
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ */
+
+/**
+ * This fuzz target performs a zstd round-trip test (compress & decompress) with
+ * a dictionary, compares the result with the original, and calls abort() on
+ * corruption.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include "fuzz_helpers.h"
+#include "zstd_helpers.h"
+
+static const int kMaxClevel = 19;
+
+static ZSTD_CCtx *cctx = NULL;
+static ZSTD_DCtx *dctx = NULL;
+static uint32_t seed;
+
+static size_t roundTripTest(void *result, size_t resultCapacity,
+                            void *compressed, size_t compressedCapacity,
+                            const void *src, size_t srcSize)
+{
+    ZSTD_dictContentType_e dictContentType = ZSTD_dct_auto;
+    FUZZ_dict_t dict = FUZZ_train(src, srcSize, &seed);
+    size_t cSize;
+    if ((FUZZ_rand(&seed) & 15) == 0) {
+        int const cLevel = FUZZ_rand(&seed) % kMaxClevel;
+
+        cSize = ZSTD_compress_usingDict(cctx,
+                compressed, compressedCapacity,
+                src, srcSize,
+                dict.buff, dict.size,
+                cLevel);
+    } else {
+        dictContentType = FUZZ_rand32(&seed, 0, 2);
+        FUZZ_setRandomParameters(cctx, srcSize, &seed);
+        /* Disable checksum so we can use sizes smaller than compress bound. */
+        FUZZ_ZASSERT(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 0));
+        FUZZ_ZASSERT(ZSTD_CCtx_loadDictionary_advanced(
+                cctx, dict.buff, dict.size,
+                (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
+                dictContentType));
+        cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize);
+    }
+    FUZZ_ZASSERT(cSize);
+    FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced(
+        dctx, dict.buff, dict.size,
+        (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
+        dictContentType));
+    {
+        size_t const ret = ZSTD_decompressDCtx(
+                dctx, result, resultCapacity, compressed, cSize);
+        free(dict.buff);
+        return ret;
+    }
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
+{
+    size_t const rBufSize = size;
+    void* rBuf = malloc(rBufSize);
+    size_t cBufSize = ZSTD_compressBound(size);
+    void* cBuf;
+
+    seed = FUZZ_seed(&src, &size);
+    /* Half of the time fuzz with a 1 byte smaller output size.
+     * This will still succeed because we force the checksum to be disabled,
+     * giving us 4 bytes of overhead.
+     */
+    cBufSize -= FUZZ_rand32(&seed, 0, 1);
+    cBuf = malloc(cBufSize);
+
+    if (!cctx) {
+        cctx = ZSTD_createCCtx();
+        FUZZ_ASSERT(cctx);
+    }
+    if (!dctx) {
+        dctx = ZSTD_createDCtx();
+        FUZZ_ASSERT(dctx);
+    }
+
+    {
+        size_t const result =
+            roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size);
+        FUZZ_ZASSERT(result);
+        FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size");
+        FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!");
+    }
+    free(rBuf);
+    free(cBuf);
+#ifndef STATEFUL_FUZZING
+    ZSTD_freeCCtx(cctx); cctx = NULL;
+    ZSTD_freeDCtx(dctx); dctx = NULL;
+#endif
+    return 0;
+}
@@ -34,6 +34,10 @@ TARGETS = [
    'simple_decompress',
    'stream_decompress',
    'block_decompress',
+    'dictionary_round_trip',
+    'dictionary_decompress',
+    'zstd_frame_info',
+    'simple_compress',
 ]
 ALL_TARGETS = TARGETS + ['all']
 FUZZ_RNG_SEED_SIZE = 4
@@ -192,11 +196,21 @@ def build_parser(args):
        default=LIB_FUZZING_ENGINE,
        help=('The fuzzing engine to use e.g. /path/to/libFuzzer.a '
              "(default: $LIB_FUZZING_ENGINE='{})".format(LIB_FUZZING_ENGINE)))
-    parser.add_argument(
+
+    fuzz_group = parser.add_mutually_exclusive_group()
+    fuzz_group.add_argument(
        '--enable-coverage',
        dest='coverage',
        action='store_true',
        help='Enable coverage instrumentation (-fsanitize-coverage)')
+    fuzz_group.add_argument(
+        '--enable-fuzzer',
+        dest='fuzzer',
+        action='store_true',
+        help=('Enable clang fuzzer (-fsanitize=fuzzer). When enabled '
+              'LIB_FUZZING_ENGINE is ignored')
+    )
+
    parser.add_argument(
        '--enable-asan', dest='asan', action='store_true', help='Enable UBSAN')
    parser.add_argument(
@@ -327,13 +341,13 @@ def build_parser(args):
    args = parse_env_flags(args, ' '.join(
        [args.cppflags, args.cflags, args.cxxflags, args.ldflags]))

-    # Check option sanitiy
+    # Check option sanity
    if args.msan and (args.asan or args.ubsan):
        raise RuntimeError('MSAN may not be used with any other sanitizers')
    if args.msan_track_origins and not args.msan:
        raise RuntimeError('--enable-msan-track-origins requires MSAN')
    if args.ubsan_pointer_overflow and not args.ubsan:
-        raise RuntimeError('--enable-ubsan-pointer-overlow requires UBSAN')
+        raise RuntimeError('--enable-ubsan-pointer-overflow requires UBSAN')
    if args.sanitize_recover and not args.sanitize:
        raise RuntimeError('--enable-sanitize-recover but no sanitizers used')

@@ -364,13 +378,17 @@ def build(args):
        '-DFUZZ_RNG_SEED_SIZE={}'.format(args.fuzz_rng_seed_size),
    ]

-    mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)]
-
    # Set flags for options
+    assert not (args.fuzzer and args.coverage)
    if args.coverage:
        common_flags += [
            '-fsanitize-coverage=trace-pc-guard,indirect-calls,trace-cmp'
        ]
+    if args.fuzzer:
+        common_flags += ['-fsanitize=fuzzer']
+        args.lib_fuzzing_engine = ''
+
+    mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)]

    if args.sanitize_recover:
        recover_flags = ['-fsanitize-recover=all']
@@ -607,7 +625,7 @@ def regression(args):

 def gen_parser(args):
    description = """
-    Generate a seed corpus appropiate for TARGET with data generated with
+    Generate a seed corpus appropriate for TARGET with data generated with
    decodecorpus.
    The fuzz inputs are prepended with a seed before the zstd data, so the
    output of decodecorpus shouldn't be used directly.
@@ -55,7 +55,7 @@ extern "C" {
 #endif

 /**
- * Determininistically constructs a seed based on the fuzz input.
+ * Deterministically constructs a seed based on the fuzz input.
 * Consumes up to the first FUZZ_RNG_SEED_SIZE bytes of the input.
 */
 FUZZ_STATIC uint32_t FUZZ_seed(uint8_t const **src, size_t* size) {
@@ -40,8 +40,13 @@ int main(int argc, char const **argv) {
    size_t readSize;
    FILE *file;

-    /* Check that it is a regular file, and that the fileSize is valid */
-    FUZZ_ASSERT_MSG(UTIL_isRegularFile(fileName), fileName);
+    /* Check that it is a regular file, and that the fileSize is valid.
+     * If it is not a regular file, then it may have been deleted since we
+     * constructed the list, so just skip it.
+     */
+    if (!UTIL_isRegularFile(fileName)) {
+      continue;
+    }
    FUZZ_ASSERT_MSG(fileSize <= kMaxFileSize, fileName);
    /* Ensure we have a large enough buffer allocated */
    if (fileSize > bufferSize) {
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ */
+
+/**
+ * This fuzz target attempts to comprss the fuzzed data with the simple
+ * compression function with an output buffer that may be too small to
+ * ensure that the compressor never crashes.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "fuzz_helpers.h"
+#include "zstd.h"
+
+static ZSTD_CCtx *cctx = NULL;
+
+int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
+{
+    uint32_t seed = FUZZ_seed(&src, &size);
+    size_t const maxSize = ZSTD_compressBound(size);
+    int i;
+    if (!cctx) {
+        cctx = ZSTD_createCCtx();
+        FUZZ_ASSERT(cctx);
+    }
+    /* Run it 10 times over 10 output sizes. Reuse the context. */
+    for (i = 0; i < 10; ++i) {
+        int const level = (int)FUZZ_rand32(&seed, 0, 19 + 3) - 3; /* [-3, 19] */
+        size_t const bufSize = FUZZ_rand32(&seed, 0, maxSize);
+        void* rBuf = malloc(bufSize);
+        FUZZ_ASSERT(rBuf);
+        ZSTD_compressCCtx(cctx, rBuf, bufSize, src, size, level);
+        free(rBuf);
+    }
+
+#ifndef STATEFUL_FUZZING
+    ZSTD_freeCCtx(cctx); cctx = NULL;
+#endif
+    return 0;
+}
@@ -19,28 +19,24 @@
 #include "zstd.h"

 static ZSTD_DCtx *dctx = NULL;
-static void* rBuf = NULL;
-static size_t bufSize = 0;

 int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
 {
-    size_t neededBufSize;

-    FUZZ_seed(&src, &size);
-    neededBufSize = MAX(20 * size, (size_t)256 << 10);
-
-    /* Allocate all buffers and contexts if not already allocated */
-    if (neededBufSize > bufSize) {
-        free(rBuf);
-        rBuf = malloc(neededBufSize);
-        bufSize = neededBufSize;
-        FUZZ_ASSERT(rBuf);
-    }
+    uint32_t seed = FUZZ_seed(&src, &size);
+    int i;
    if (!dctx) {
        dctx = ZSTD_createDCtx();
        FUZZ_ASSERT(dctx);
    }
-    ZSTD_decompressDCtx(dctx, rBuf, neededBufSize, src, size);
+    /* Run it 10 times over 10 output sizes. Reuse the context. */
+    for (i = 0; i < 10; ++i) {
+        size_t const bufSize = FUZZ_rand32(&seed, 0, 2 * size);
+        void* rBuf = malloc(bufSize);
+        FUZZ_ASSERT(rBuf);
+        ZSTD_decompressDCtx(dctx, rBuf, bufSize, src, size);
+        free(rBuf);
+    }

 #ifndef STATEFUL_FUZZING
    ZSTD_freeDCtx(dctx); dctx = NULL;
@@ -25,9 +25,6 @@ static const int kMaxClevel = 19;

 static ZSTD_CCtx *cctx = NULL;
 static ZSTD_DCtx *dctx = NULL;
-static void* cBuf = NULL;
-static void* rBuf = NULL;
-static size_t bufSize = 0;
 static uint32_t seed;

 static size_t roundTripTest(void *result, size_t resultCapacity,
@@ -36,16 +33,8 @@ static size_t roundTripTest(void *result, size_t resultCapacity,
 {
    size_t cSize;
    if (FUZZ_rand(&seed) & 1) {
-        ZSTD_inBuffer in = {src, srcSize, 0};
-        ZSTD_outBuffer out = {compressed, compressedCapacity, 0};
-        size_t err;
-
-        ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
        FUZZ_setRandomParameters(cctx, srcSize, &seed);
-        err = ZSTD_compressStream2(cctx, &out, &in, ZSTD_e_end);
-        FUZZ_ZASSERT(err);
-        FUZZ_ASSERT(err == 0);
-        cSize = out.pos;
+        cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize);
    } else {
        int const cLevel = FUZZ_rand(&seed) % kMaxClevel;
        cSize = ZSTD_compressCCtx(
@@ -57,20 +46,21 @@ static size_t roundTripTest(void *result, size_t resultCapacity,

 int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
 {
-    size_t neededBufSize;
+    size_t const rBufSize = size;
+    void* rBuf = malloc(rBufSize);
+    size_t cBufSize = ZSTD_compressBound(size);
+    void* cBuf;

    seed = FUZZ_seed(&src, &size);
-    neededBufSize = ZSTD_compressBound(size);
+    /* Half of the time fuzz with a 1 byte smaller output size.
+     * This will still succeed because we don't use a dictionary, so the dictID
+     * field is empty, giving us 4 bytes of overhead.
+     */
+    cBufSize -= FUZZ_rand32(&seed, 0, 1);
+    cBuf = malloc(cBufSize);
+
+    FUZZ_ASSERT(cBuf && rBuf);

-    /* Allocate all buffers and contexts if not already allocated */
-    if (neededBufSize > bufSize) {
-        free(cBuf);
-        free(rBuf);
-        cBuf = malloc(neededBufSize);
-        rBuf = malloc(neededBufSize);
-        bufSize = neededBufSize;
-        FUZZ_ASSERT(cBuf && rBuf);
-    }
    if (!cctx) {
        cctx = ZSTD_createCCtx();
        FUZZ_ASSERT(cctx);
@@ -82,11 +72,13 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)

    {
        size_t const result =
-            roundTripTest(rBuf, neededBufSize, cBuf, neededBufSize, src, size);
+            roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size);
        FUZZ_ZASSERT(result);
        FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size");
        FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!");
    }
+    free(rBuf);
+    free(cBuf);
 #ifndef STATEFUL_FUZZING
    ZSTD_freeCCtx(cctx); cctx = NULL;
    ZSTD_freeDCtx(dctx); dctx = NULL;
@@ -62,9 +62,8 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
    if (!dstream) {
        dstream = ZSTD_createDStream();
        FUZZ_ASSERT(dstream);
-        FUZZ_ASSERT(!ZSTD_isError(ZSTD_initDStream(dstream)));
    } else {
-        FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream)));
+        FUZZ_ZASSERT(ZSTD_DCtx_reset(dstream, ZSTD_reset_session_only));
    }

    while (size > 0) {
@@ -73,7 +72,6 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
            ZSTD_outBuffer out = makeOutBuffer();
            size_t const rc = ZSTD_decompressStream(dstream, &out, &in);
            if (ZSTD_isError(rc)) goto error;
-            if (rc == 0) FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream)));
        }
    }

@@ -63,7 +63,7 @@ static size_t compress(uint8_t *dst, size_t capacity,
        ZSTD_inBuffer in = makeInBuffer(&src, &srcSize);
        /* Mode controls the action. If mode == -1 we pick a new mode */
        int mode = -1;
-        while (in.pos < in.size) {
+        while (in.pos < in.size || mode != -1) {
            ZSTD_outBuffer out = makeOutBuffer(dst, capacity);
            /* Previous action finished, pick a new mode. */
            if (mode == -1) mode = FUZZ_rand(&seed) % 10;
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ */
+
+/**
+ * This fuzz target fuzzes all of the helper functions that consume compressed
+ * input.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "fuzz_helpers.h"
+#include "zstd_helpers.h"
+
+int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
+{
+    ZSTD_frameHeader zfh;
+    /* Consume the seed to be compatible with the corpora of other decompression
+     * fuzzers.
+     */
+    FUZZ_seed(&src, &size);
+    /* You can fuzz any helper functions here that are fast, and take zstd
+     * compressed data as input. E.g. don't expect the input to be a dictionary,
+     * so don't fuzz ZSTD_getDictID_fromDict().
+     */
+    ZSTD_getFrameContentSize(src, size);
+    ZSTD_getDecompressedSize(src, size);
+    ZSTD_findFrameCompressedSize(src, size);
+    ZSTD_getDictID_fromFrame(src, size);
+    ZSTD_findDecompressedSize(src, size);
+    ZSTD_decompressBound(src, size);
+    ZSTD_frameHeaderSize(src, size);
+    ZSTD_isFrame(src, size);
+    ZSTD_getFrameHeader(&zfh, src, size);
+    ZSTD_getFrameHeader_advanced(&zfh, src, size, ZSTD_f_zstd1);
+    return 0;
+}
@@ -8,10 +8,14 @@
 */

 #define ZSTD_STATIC_LINKING_ONLY
+#define ZDICT_STATIC_LINKING_ONLY
+
+#include <string.h>

 #include "zstd_helpers.h"
 #include "fuzz_helpers.h"
 #include "zstd.h"
+#include "zdict.h"

 static void set(ZSTD_CCtx *cctx, ZSTD_cParameter param, int value)
 {
@@ -71,8 +75,7 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state)
    setRand(cctx, ZSTD_c_contentSizeFlag, 0, 1, state);
    setRand(cctx, ZSTD_c_checksumFlag, 0, 1, state);
    setRand(cctx, ZSTD_c_dictIDFlag, 0, 1, state);
-    setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state);
-    /* Select long distance matchig parameters */
+    /* Select long distance matching parameters */
    setRand(cctx, ZSTD_c_enableLongDistanceMatching, 0, 1, state);
    setRand(cctx, ZSTD_c_ldmHashLog, ZSTD_HASHLOG_MIN, 16, state);
    setRand(cctx, ZSTD_c_ldmMinMatch, ZSTD_LDM_MINMATCH_MIN,
@@ -81,4 +84,54 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state)
            state);
    setRand(cctx, ZSTD_c_ldmHashRateLog, ZSTD_LDM_HASHRATELOG_MIN,
            ZSTD_LDM_HASHRATELOG_MAX, state);
+    /* Set misc parameters */
+    setRand(cctx, ZSTD_c_nbWorkers, 0, 2, state);
+    setRand(cctx, ZSTD_c_rsyncable, 0, 1, state);
+    setRand(cctx, ZSTD_c_forceMaxWindow, 0, 1, state);
+    setRand(cctx, ZSTD_c_literalCompressionMode, 0, 2, state);
+    setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state);
+}
+
+FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state)
+{
+    size_t const dictSize = MAX(srcSize / 8, 1024);
+    size_t const totalSampleSize = dictSize * 11;
+    FUZZ_dict_t dict = { malloc(dictSize), dictSize };
+    char* const samples = (char*)malloc(totalSampleSize);
+    unsigned nbSamples = 100;
+    size_t* const samplesSizes = (size_t*)malloc(sizeof(size_t) * nbSamples);
+    size_t pos = 0;
+    size_t sample = 0;
+    ZDICT_fastCover_params_t params;
+    FUZZ_ASSERT(dict.buff && samples && samplesSizes);
+
+    for (sample = 0; sample < nbSamples; ++sample) {
+      size_t const remaining = totalSampleSize - pos;
+      size_t const offset = FUZZ_rand32(state, 0, MAX(srcSize, 1) - 1);
+      size_t const limit = MIN(srcSize - offset, remaining);
+      size_t const toCopy = MIN(limit, remaining / (nbSamples - sample));
+      memcpy(samples + pos, src + offset, toCopy);
+      pos += toCopy;
+      samplesSizes[sample] = toCopy;
+
+    }
+    memset(samples + pos, 0, totalSampleSize - pos);
+
+    memset(&params, 0, sizeof(params));
+    params.accel = 5;
+    params.k = 40;
+    params.d = 8;
+    params.f = 14;
+    params.zParams.compressionLevel = 1;
+    dict.size = ZDICT_trainFromBuffer_fastCover(dict.buff, dictSize,
+        samples, samplesSizes, nbSamples, params);
+    if (ZSTD_isError(dict.size)) {
+        free(dict.buff);
+        memset(&dict, 0, sizeof(dict));
+    }
+
+    free(samplesSizes);
+    free(samples);
+
+    return dict;
 }
@@ -14,6 +14,8 @@
 #ifndef ZSTD_HELPERS_H
 #define ZSTD_HELPERS_H

+#define ZSTD_STATIC_LINKING_ONLY
+
 #include "zstd.h"
 #include <stdint.h>

@@ -27,6 +29,17 @@ ZSTD_compressionParameters FUZZ_randomCParams(size_t srcSize, uint32_t *state);
 ZSTD_frameParameters FUZZ_randomFParams(uint32_t *state);
 ZSTD_parameters FUZZ_randomParams(size_t srcSize, uint32_t *state);

+typedef struct {
+  void* buff;
+  size_t size;
+} FUZZ_dict_t;
+
+/* Quickly train a dictionary from a source for fuzzing.
+ * NOTE: Don't use this to train production dictionaries, it is only optimized
+ * for speed, and doesn't care about dictionary quality.
+ */
+FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state);
+

 #ifdef __cplusplus
 }
@@ -38,6 +38,7 @@
 #define XXH_STATIC_LINKING_ONLY   /* XXH64_state_t */
 #include "xxhash.h"       /* XXH64 */
 #include "util.h"
+#include "timefn.h"       /* SEC_TO_MICRO, UTIL_time_t, UTIL_TIME_INITIALIZER, UTIL_clockSpanMicro, UTIL_getTime */


 /*-************************************
@@ -61,10 +62,12 @@ static U32 g_displayLevel = 2;
 static const U64 g_refreshRate = SEC_TO_MICRO / 6;
 static UTIL_time_t g_displayClock = UTIL_TIME_INITIALIZER;

-#define DISPLAYUPDATE(l, ...) if (g_displayLevel>=l) { \
-            if ((UTIL_clockSpanMicro(g_displayClock) > g_refreshRate) || (g_displayLevel>=4)) \
-            { g_displayClock = UTIL_getTime(); DISPLAY(__VA_ARGS__); \
-            if (g_displayLevel>=4) fflush(stderr); } }
+#define DISPLAYUPDATE(l, ...) \
+    if (g_displayLevel>=l) { \
+        if ((UTIL_clockSpanMicro(g_displayClock) > g_refreshRate) || (g_displayLevel>=4)) \
+        { g_displayClock = UTIL_getTime(); DISPLAY(__VA_ARGS__); \
+        if (g_displayLevel>=4) fflush(stderr); } \
+    }


 /*-*******************************************************
@@ -72,7 +75,7 @@ static UTIL_time_t g_displayClock = UTIL_TIME_INITIALIZER;
 *********************************************************/
 #undef MIN
 #undef MAX
-/* Declaring the function is it isn't unused */
+/* Declaring the function, to avoid -Wmissing-prototype */
 void FUZ_bug976(void);
 void FUZ_bug976(void)
 {   /* these constants shall not depend on MIN() macro */
@@ -124,12 +127,14 @@ static U32 FUZ_highbit32(U32 v32)
 #define CHECK(fn)  { CHECK_V(err, fn); }
 #define CHECKPLUS(var, fn, more)  { CHECK_V(var, fn); more; }

-#define CHECK_EQ(lhs, rhs) {                                      \
-    if ((lhs) != (rhs)) {                                         \
-        DISPLAY("Error L%u => %s != %s ", __LINE__, #lhs, #rhs);  \
+#define CHECK_OP(op, lhs, rhs) {                                  \
+    if (!((lhs) op (rhs))) {                                      \
+        DISPLAY("Error L%u => FAILED %s %s %s ", __LINE__, #lhs, #op, #rhs);  \
        goto _output_error;                                       \
    }                                                             \
 }
+#define CHECK_EQ(lhs, rhs) CHECK_OP(==, lhs, rhs)
+#define CHECK_LT(lhs, rhs) CHECK_OP(<, lhs, rhs)


 /*=============================================
@@ -244,7 +249,7 @@ static int FUZ_mallocTests_internal(unsigned seed, double compressibility, unsig

    /* advanced MT streaming API test */
    if (part <= 4)
-    {   unsigned nbThreads;
+    {   int nbThreads;
        for (nbThreads=1; nbThreads<=4; nbThreads++) {
            int compressionLevel;
            for (compressionLevel=1; compressionLevel<=6; compressionLevel++) {
@@ -258,7 +263,7 @@ static int FUZ_mallocTests_internal(unsigned seed, double compressibility, unsig
                CHECK_Z( ZSTD_compressStream2(cctx, &out, &in, ZSTD_e_continue) );
                while ( ZSTD_compressStream2(cctx, &out, &in, ZSTD_e_end) ) {}
                ZSTD_freeCCtx(cctx);
-                DISPLAYLEVEL(3, "compress_generic,-T%u,continue level %i : ",
+                DISPLAYLEVEL(3, "compress_generic,-T%i,continue level %i : ",
                                nbThreads, compressionLevel);
                FUZ_displayMallocStats(malcount);
    }   }   }
@@ -374,6 +379,20 @@ static int basicUnitTests(U32 seed, double compressibility)
    }
    DISPLAYLEVEL(3, "OK \n");

+    DISPLAYLEVEL(3, "test%3i : tight ZSTD_decompressBound test : ", testNb++);
+    {
+        unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize);
+        if (bound != CNBuffSize) goto _output_error;
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with invalid srcSize : ", testNb++);
+    {
+        unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize - 1);
+        if (bound != ZSTD_CONTENTSIZE_ERROR) goto _output_error;
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
    DISPLAYLEVEL(3, "test%3i : decompress %u bytes : ", testNb++, (unsigned)CNBuffSize);
    { size_t const r = ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize);
      if (r != CNBuffSize) goto _output_error; }
@@ -429,6 +448,27 @@ static int basicUnitTests(U32 seed, double compressibility)
      if (ZSTD_getErrorCode(r) != ZSTD_error_srcSize_wrong) goto _output_error; }
    DISPLAYLEVEL(3, "OK \n");

+    DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with content size missing : ", testNb++);
+    {   /* create compressed buffer with content size missing */
+        ZSTD_CCtx* cctx = ZSTD_createCCtx();
+        CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_contentSizeFlag, 0) );
+        CHECKPLUS(r, ZSTD_compress2(cctx,
+                            compressedBuffer, compressedBufferSize,
+                            CNBuffer, CNBuffSize),
+                  cSize=r );
+        ZSTD_freeCCtx(cctx);
+    }
+    {   /* ensure frame content size is missing */
+        ZSTD_frameHeader zfh;
+        size_t const ret = ZSTD_getFrameHeader(&zfh, compressedBuffer, compressedBufferSize);
+        if (ret != 0 || zfh.frameContentSize !=  ZSTD_CONTENTSIZE_UNKNOWN) goto _output_error;
+    }
+    {   /* ensure CNBuffSize <= decompressBound */
+        unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, compressedBufferSize);
+        if (CNBuffSize > bound) goto _output_error;
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
    DISPLAYLEVEL(3, "test%3d : check CCtx size after compressing empty input : ", testNb++);
    {   ZSTD_CCtx* const cctx = ZSTD_createCCtx();
        size_t const r = ZSTD_compressCCtx(cctx, compressedBuffer, compressedBufferSize, NULL, 0, 19);
@@ -730,13 +770,11 @@ static int basicUnitTests(U32 seed, double compressibility)
            DISPLAYLEVEL(3, "OK \n");

            DISPLAYLEVEL(3, "test%3i : init CCtx for small level %u (should work again) : ", testNb++, 1);
-            { size_t const r = ZSTD_compressBegin(staticCCtx, 1);
-              if (ZSTD_isError(r)) goto _output_error; }
+            CHECK( ZSTD_compressBegin(staticCCtx, 1) );
            DISPLAYLEVEL(3, "OK \n");

            DISPLAYLEVEL(3, "test%3i : init CStream for small level %u : ", testNb++, 1);
-            { size_t const r = ZSTD_initCStream(staticCCtx, 1);
-              if (ZSTD_isError(r)) goto _output_error; }
+            CHECK( ZSTD_initCStream(staticCCtx, 1) );
            DISPLAYLEVEL(3, "OK \n");

            DISPLAYLEVEL(3, "test%3i : init CStream with dictionary (should fail) : ", testNb++);
@@ -828,6 +866,59 @@ static int basicUnitTests(U32 seed, double compressibility)
        ZSTDMT_freeCCtx(mtctx);
    }

+    DISPLAYLEVEL(3, "test%3i : compress -T2 with/without literals compression : ", testNb++)
+    {   ZSTD_CCtx* cctx = ZSTD_createCCtx();
+        size_t cSize1, cSize2;
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 2) );
+        cSize1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize);
+        CHECK(cSize1);
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_literalCompressionMode, ZSTD_lcm_uncompressed) );
+        cSize2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize);
+        CHECK(cSize2);
+        CHECK_LT(cSize1, cSize2);
+        ZSTD_freeCCtx(cctx);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : Multithreaded ZSTD_compress2() with rsyncable : ", testNb++)
+    {   ZSTD_CCtx* cctx = ZSTD_createCCtx();
+        /* Set rsyncable and don't give the ZSTD_compressBound(CNBuffSize) so
+         * ZSTDMT is forced to not take the shortcut.
+         */
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 1) );
+        CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_rsyncable, 1) );
+        CHECK( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize - 1, CNBuffer, CNBuffSize) );
+        ZSTD_freeCCtx(cctx);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : setting multithreaded parameters : ", testNb++)
+    {   ZSTD_CCtx_params* params = ZSTD_createCCtxParams();
+        int value;
+        /* Check that the overlap log and job size are unset. */
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
+        CHECK_EQ(value, 0);
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
+        CHECK_EQ(value, 0);
+        /* Set and check the overlap log and job size. */
+        CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, 5) );
+        CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, 2 MB) );
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
+        CHECK_EQ(value, 5);
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
+        CHECK_EQ(value, 2 MB);
+        /* Set the number of workers and check the overlap log and job size. */
+        CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, 2) );
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
+        CHECK_EQ(value, 5);
+        CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
+        CHECK_EQ(value, 2 MB);
+        ZSTD_freeCCtxParams(params);
+
+    }
+    DISPLAYLEVEL(3, "OK \n");

    /* Simple API multiframe test */
    DISPLAYLEVEL(3, "test%3i : compress multiple frames : ", testNb++);
@@ -859,6 +950,11 @@ static int basicUnitTests(U32 seed, double compressibility)
        if (r != CNBuffSize / 2) goto _output_error; }
    DISPLAYLEVEL(3, "OK \n");

+    DISPLAYLEVEL(3, "test%3i : get tight decompressed bound of multiple frames : ", testNb++);
+    {   unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, cSize);
+        if (bound != CNBuffSize / 2) goto _output_error; }
+    DISPLAYLEVEL(3, "OK \n");
+
    DISPLAYLEVEL(3, "test%3i : decompress multiple frames : ", testNb++);
    {   CHECK_V(r, ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize));
        if (r != CNBuffSize / 2) goto _output_error; }
@@ -963,7 +1059,7 @@ static int basicUnitTests(U32 seed, double compressibility)
    /* Dictionary and dictBuilder tests */
    {   ZSTD_CCtx* const cctx = ZSTD_createCCtx();
        size_t const dictBufferCapacity = 16 KB;
-        void* dictBuffer = malloc(dictBufferCapacity);
+        void* const dictBuffer = malloc(dictBufferCapacity);
        size_t const totalSampleSize = 1 MB;
        size_t const sampleUnitSize = 8 KB;
        U32 const nbSamples = (U32)(totalSampleSize / sampleUnitSize);
@@ -1008,6 +1104,22 @@ static int basicUnitTests(U32 seed, double compressibility)
        }
        DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);

+        DISPLAYLEVEL(3, "test%3i : COVER dictBuilder with shrinkDict: ", testNb++);
+        { U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
+        {   ZDICT_cover_params_t coverParams;
+            memset(&coverParams, 0, sizeof(coverParams));
+            coverParams.steps = 8;
+            coverParams.nbThreads = 4;
+            coverParams.shrinkDict = 1;
+            coverParams.shrinkDictMaxRegression = 1;
+            dictSize = ZDICT_optimizeTrainFromBuffer_cover(
+                dictBuffer, dictBufferCapacity,
+                CNBuffer, samplesSizes, nbSamples/8,  /* less samples for faster tests */
+                &coverParams);
+            if (ZDICT_isError(dictSize)) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
+
        DISPLAYLEVEL(3, "test%3i : Multithreaded FASTCOVER dictBuilder : ", testNb++);
        { U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
        {   ZDICT_fastCover_params_t fastCoverParams;
@@ -1022,6 +1134,22 @@ static int basicUnitTests(U32 seed, double compressibility)
        }
        DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);

+        DISPLAYLEVEL(3, "test%3i : FASTCOVER dictBuilder with shrinkDict: ", testNb++);
+        { U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
+        {   ZDICT_fastCover_params_t fastCoverParams;
+            memset(&fastCoverParams, 0, sizeof(fastCoverParams));
+            fastCoverParams.steps = 8;
+            fastCoverParams.nbThreads = 4;
+            fastCoverParams.shrinkDict = 1;
+            fastCoverParams.shrinkDictMaxRegression = 1;
+            dictSize = ZDICT_optimizeTrainFromBuffer_fastCover(
+                dictBuffer, dictBufferCapacity,
+                CNBuffer, samplesSizes, nbSamples,
+                &fastCoverParams);
+            if (ZDICT_isError(dictSize)) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
+
        DISPLAYLEVEL(3, "test%3i : check dictID : ", testNb++);
        dictID = ZDICT_getDictID(dictBuffer, dictSize);
        if (dictID==0) goto _output_error;
@@ -1068,6 +1196,7 @@ static int basicUnitTests(U32 seed, double compressibility)
            ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize,
                                            ZSTD_dlm_byRef, ZSTD_dct_auto,
                                            cParams, ZSTD_defaultCMem);
+            assert(cdict != NULL);
            DISPLAYLEVEL(3, "(size : %u) : ", (unsigned)ZSTD_sizeof_CDict(cdict));
            cSize = ZSTD_compress_usingCDict(cctx, compressedBuffer, compressedBufferSize,
                                                 CNBuffer, CNBuffSize, cdict);
@@ -1125,8 +1254,11 @@ static int basicUnitTests(U32 seed, double compressibility)
        {   ZSTD_frameParameters const fParams = { 0 /* frameSize */, 1 /* checksum */, 1 /* noDictID*/ };
            ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
            ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, cParams, ZSTD_defaultCMem);
-            cSize = ZSTD_compress_usingCDict_advanced(cctx, compressedBuffer, compressedBufferSize,
-                                                 CNBuffer, CNBuffSize, cdict, fParams);
+            assert(cdict != NULL);
+            cSize = ZSTD_compress_usingCDict_advanced(cctx,
+                                                      compressedBuffer, compressedBufferSize,
+                                                      CNBuffer, CNBuffSize,
+                                                      cdict, fParams);
            ZSTD_freeCDict(cdict);
            if (ZSTD_isError(cSize)) goto _output_error;
        }
@@ -1139,7 +1271,8 @@ static int basicUnitTests(U32 seed, double compressibility)
        DISPLAYLEVEL(3, "OK (unknown)\n");

        DISPLAYLEVEL(3, "test%3i : frame built without dictID should be decompressible : ", testNb++);
-        {   ZSTD_DCtx* const dctx = ZSTD_createDCtx(); assert(dctx != NULL);
+        {   ZSTD_DCtx* const dctx = ZSTD_createDCtx();
+            assert(dctx != NULL);
            CHECKPLUS(r, ZSTD_decompress_usingDict(dctx,
                                           decodedBuffer, CNBuffSize,
                                           compressedBuffer, cSize,
@@ -1203,9 +1336,13 @@ static int basicUnitTests(U32 seed, double compressibility)
        {
            size_t ret;
            MEM_writeLE32((char*)dictBuffer+2, ZSTD_MAGIC_DICTIONARY);
+            /* Either operation is allowed to fail, but one must fail. */
            ret = ZSTD_CCtx_loadDictionary_advanced(
                    cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_auto);
-            if (!ZSTD_isError(ret)) goto _output_error;
+            if (!ZSTD_isError(ret)) {
+                ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100));
+                if (!ZSTD_isError(ret)) goto _output_error;
+            }
        }
        DISPLAYLEVEL(3, "OK \n");

@@ -1216,6 +1353,187 @@ static int basicUnitTests(U32 seed, double compressibility)
            ret = ZSTD_CCtx_loadDictionary_advanced(
                    cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_rawContent);
            if (ZSTD_isError(ret)) goto _output_error;
+            ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100));
+            if (ZSTD_isError(ret)) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : ZSTD_CCtx_refCDict() then set parameters : ", testNb++);
+        {   ZSTD_CDict* const cdict = ZSTD_createCDict(CNBuffer, dictSize, 1);
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 ));
+            CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 ));
+            ZSTD_freeCDict(cdict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading dictionary before setting parameters is the same as loading after : ", testNb++);
+        {
+            size_t size1, size2;
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) );
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
+            size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size1)) goto _output_error;
+
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
+            CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) );
+            size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size2)) goto _output_error;
+
+            if (size1 != size2) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the prefix : ", testNb++);
+        {
+            CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the cdict : ", testNb++);
+        {
+            ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
+            CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+            ZSTD_freeCDict(cdict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the prefix : ", testNb++);
+        {
+            ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
+            CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+            ZSTD_freeCDict(cdict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the dictionary : ", testNb++);
+        {
+            ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+            ZSTD_freeCDict(cdict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the dictionary : ", testNb++);
+        {
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the cdict : ", testNb++);
+        {
+            ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
+            CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
+            CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
+            ZSTD_freeCDict(cdict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loaded dictionary persists across reset session : ", testNb++);
+        {
+            size_t size1, size2;
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
+            size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size1)) goto _output_error;
+
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
+            size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size2)) goto _output_error;
+
+            if (size1 != size2) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : Loaded dictionary is cleared after resetting parameters : ", testNb++);
+        {
+            size_t size1, size2;
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
+            size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size1)) goto _output_error;
+
+            ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+            size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+            if (ZSTD_isError(size2)) goto _output_error;
+
+            if (size1 == size2) goto _output_error;
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
+        CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, dictBuffer, dictSize) );
+        cSize = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
+        CHECK_Z(cSize);
+        DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with dictionary : ", testNb++);
+        {
+            ZSTD_DCtx* dctx = ZSTD_createDCtx();
+            size_t ret;
+            /* We should fail to decompress without a dictionary. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
+            if (!ZSTD_isError(ret)) goto _output_error;
+            /* We should succeed to decompress with the dictionary. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictBuffer, dictSize) );
+            CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
+            /* The dictionary should presist across calls. */
+            CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
+            /* When we reset the context the dictionary is cleared. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
+            if (!ZSTD_isError(ret)) goto _output_error;
+            ZSTD_freeDCtx(dctx);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with ddict : ", testNb++);
+        {
+            ZSTD_DCtx* dctx = ZSTD_createDCtx();
+            ZSTD_DDict* ddict = ZSTD_createDDict(dictBuffer, dictSize);
+            size_t ret;
+            /* We should succeed to decompress with the ddict. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_DCtx_refDDict(dctx, ddict) );
+            CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
+            /* The ddict should presist across calls. */
+            CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
+            /* When we reset the context the ddict is cleared. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
+            if (!ZSTD_isError(ret)) goto _output_error;
+            ZSTD_freeDCtx(dctx);
+            ZSTD_freeDDict(ddict);
+        }
+        DISPLAYLEVEL(3, "OK \n");
+
+        DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with prefix : ", testNb++);
+        {
+            ZSTD_DCtx* dctx = ZSTD_createDCtx();
+            size_t ret;
+            /* We should succeed to decompress with the prefix. */
+            ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+            CHECK_Z( ZSTD_DCtx_refPrefix_advanced(dctx, dictBuffer, dictSize, ZSTD_dct_auto) );
+            CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
+            /* The prefix should be cleared after the first compression. */
+            ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
+            if (!ZSTD_isError(ret)) goto _output_error;
+            ZSTD_freeDCtx(dctx);
        }
        DISPLAYLEVEL(3, "OK \n");

@@ -2178,7 +2496,7 @@ static unsigned readU32FromChar(const char** stringPtr)
 *  If yes, @return 1 and advances *stringPtr to the position which immediately follows longCommand.
 *  @return 0 and doesn't modify *stringPtr otherwise.
 */
-static unsigned longCommandWArg(const char** stringPtr, const char* longCommand)
+static int longCommandWArg(const char** stringPtr, const char* longCommand)
 {
    size_t const comSize = strlen(longCommand);
    int const result = !strncmp(*stringPtr, longCommand, comSize);
@@ -2238,7 +2556,7 @@ int main(int argc, const char** argv)

                case 'i':
                    argument++; maxDuration = 0;
-                    nbTests = readU32FromChar(&argument);
+                    nbTests = (int)readU32FromChar(&argument);
                    break;

                case 'T':
@@ -2258,12 +2576,12 @@ int main(int argc, const char** argv)

                case 't':
                    argument++;
-                    testNb = readU32FromChar(&argument);
+                    testNb = (int)readU32FromChar(&argument);
                    break;

                case 'P':   /* compressibility % */
                    argument++;
-                    proba = readU32FromChar(&argument);
+                    proba = (int)readU32FromChar(&argument);
                    if (proba>100) proba = 100;
                    break;

@@ -16,10 +16,11 @@
 /*===========================================
 *   Dependencies
 *==========================================*/
-#include <stddef.h>     /* size_t */
-#include <stdlib.h>     /* malloc, free */
-#include <stdio.h>      /* fprintf */
-#include <string.h>     /* strlen */
+#include <stddef.h>              /* size_t */
+#include <stdlib.h>              /* malloc, free */
+#include <stdio.h>               /* fprintf */
+#include <string.h>              /* strlen */
+#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_decompressBound */
 #include "zstd.h"
 #include "zstd_errors.h"

@@ -74,6 +75,7 @@ static int testSimpleAPI(void)

 static int testStreamingAPI(void)
 {
+    int error_code = 0;
    size_t const outBuffSize = ZSTD_DStreamOutSize();
    char* const outBuff = malloc(outBuffSize);
    ZSTD_DStream* const stream = ZSTD_createDStream();
@@ -87,6 +89,7 @@ static int testStreamingAPI(void)
    }
    if (stream == NULL) {
        DISPLAY("ERROR: Could not create dstream\n");
+        free(outBuff);
        return 1;
    }

@@ -96,13 +99,15 @@ static int testStreamingAPI(void)
            size_t const ret = ZSTD_initDStream(stream);
            if (ZSTD_isError(ret)) {
                DISPLAY("ERROR: ZSTD_initDStream: %s\n", ZSTD_getErrorName(ret));
-                return 1;
+                error_code = 1;
+                break;
        }   }

        {   size_t const ret = ZSTD_decompressStream(stream, &output, &input);
            if (ZSTD_isError(ret)) {
                DISPLAY("ERROR: ZSTD_decompressStream: %s\n", ZSTD_getErrorName(ret));
-                return 1;
+                error_code = 1;
+                break;
            }

            if (ret == 0) {
@@ -111,7 +116,8 @@ static int testStreamingAPI(void)

        if (memcmp(outBuff, EXPECTED + outputPos, output.pos) != 0) {
            DISPLAY("ERROR: Wrong decoded output produced\n");
-            return 1;
+            error_code = 1;
+            break;
        }
        outputPos += output.pos;
        if (input.pos == input.size && output.pos < output.size) {
@@ -121,7 +127,34 @@ static int testStreamingAPI(void)

    free(outBuff);
    ZSTD_freeDStream(stream);
-    DISPLAY("Streaming API OK\n");
+    if (error_code == 0) DISPLAY("Streaming API OK\n");
+    return error_code;
+}
+
+static int testFrameDecoding(void)
+{
+    if (strlen(EXPECTED) > ZSTD_decompressBound(COMPRESSED, COMPRESSED_SIZE)) {
+        DISPLAY("ERROR: ZSTD_decompressBound: decompressed bound too small\n");
+        return 1;
+    }
+    {   const char* ip = COMPRESSED;
+        size_t remainingSize = COMPRESSED_SIZE;
+        while (1) {
+            size_t frameSize = ZSTD_findFrameCompressedSize(ip, remainingSize);
+            if (ZSTD_isError(frameSize)) {
+                DISPLAY("ERROR: ZSTD_findFrameCompressedSize: %s\n", ZSTD_getErrorName(frameSize));
+                return 1;
+            }
+            if (frameSize > remainingSize) {
+                DISPLAY("ERROR: ZSTD_findFrameCompressedSize: expected frameSize to align with src buffer");
+                return 1;
+            }
+            ip += frameSize;
+            remainingSize -= frameSize;
+            if (remainingSize == 0) break;
+        }
+    }
+    DISPLAY("Frame Decoding OK\n");
    return 0;
 }

@@ -131,6 +164,8 @@ int main(void)
        if (ret) return ret; }
    {   int const ret = testStreamingAPI();
        if (ret) return ret; }
+    {   int const ret = testFrameDecoding();
+        if (ret) return ret; }

    DISPLAY("OK\n");
    return 0;
@@ -19,6 +19,7 @@
 #include <math.h>      /* log */
 #include <assert.h>

+#include "timefn.h"    /* SEC_TO_MICRO, UTIL_time_t, UTIL_clockSpanMicro, UTIL_clockSpanNano, UTIL_getTime */
 #include "mem.h"
 #define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_parameters, ZSTD_estimateCCtxSize */
 #include "zstd.h"
@@ -141,7 +142,7 @@ static const char* g_shortParamNames[NUM_PARAMS] =
 /* maps value from { 0 to rangetable[param] - 1 } to valid paramvalues */
 static U32 rangeMap(varInds_t param, int ind)
 {
-    ind = MAX(MIN(ind, (int)rangetable[param] - 1), 0);
+    U32 const uind = (U32)MAX(MIN(ind, (int)rangetable[param] - 1), 0);
    switch(param) {
        case wlog_ind: /* using default: triggers -Wswitch-enum */
        case clog_ind:
@@ -149,11 +150,11 @@ static U32 rangeMap(varInds_t param, int ind)
        case slog_ind:
        case mml_ind:
        case strt_ind:
-            return mintable[param] + ind;
+            return mintable[param] + uind;
        case tlen_ind:
-            return tlen_table[ind];
+            return tlen_table[uind];
        case fadt_ind: /* 0, 1, 2 -> -1, 0, 1 */
-            return ind - 1;
+            return uind - 1;
        case NUM_PARAMS:
        default:;
    }
@@ -173,7 +174,7 @@ static int invRangeMap(varInds_t param, U32 value)
        case slog_ind:
        case mml_ind:
        case strt_ind:
-            return value - mintable[param];
+            return (int)(value - mintable[param]);
        case tlen_ind: /* bin search */
        {
            int lo = 0;
@@ -493,13 +494,15 @@ static void
 paramVariation(paramValues_t* ptr, memoTable_t* mtAll, const U32 nbChanges)
 {
    paramValues_t p;
-    U32 validated = 0;
+    int validated = 0;
    while (!validated) {
        U32 i;
        p = *ptr;
        for (i = 0 ; i < nbChanges ; i++) {
            const U32 changeID = (U32)FUZ_rand(&g_rand) % (mtAll[p.vals[strt_ind]].varLen << 1);
-            paramVaryOnce(mtAll[p.vals[strt_ind]].varArray[changeID >> 1], ((changeID & 1) << 1) - 1, &p);
+            paramVaryOnce(mtAll[p.vals[strt_ind]].varArray[changeID >> 1],
+                          (int)((changeID & 1) << 1) - 1,
+                          &p);
        }
        validated = paramValid(p);
    }
@@ -511,7 +514,7 @@ static paramValues_t randomParams(void)
 {
    varInds_t v; paramValues_t p;
    for(v = 0; v < NUM_PARAMS; v++) {
-        p.vals[v] = rangeMap(v, FUZ_rand(&g_rand) % rangetable[v]);
+        p.vals[v] = rangeMap(v, (int)(FUZ_rand(&g_rand) % rangetable[v]));
    }
    return p;
 }
@@ -606,8 +609,8 @@ compareResultLT(const BMK_benchResult_t result1, const BMK_benchResult_t result2

 static constraint_t relaxTarget(constraint_t target) {
    target.cMem = (U32)-1;
-    target.cSpeed *= ((double)g_strictness) / 100;
-    target.dSpeed *= ((double)g_strictness) / 100;
+    target.cSpeed = (target.cSpeed * g_strictness) / 100;
+    target.dSpeed = (target.dSpeed * g_strictness) / 100;
    return target;
 }

@@ -1232,7 +1235,7 @@ static int createBuffersFromMemory(buffers_t* buff, void * srcBuffer, const size
    return 0;
 }

-/* allocates buffer's arguments. returns success / failuere */
+/* allocates buffer's arguments. returns success / failure */
 static int createBuffers(buffers_t* buff, const char* const * const fileNamesTable,
                          size_t nbFiles) {
    size_t pos = 0;
@@ -1505,7 +1508,7 @@ createMemoTableArray(const paramValues_t p,
 }

 /* Sets pc to random unmeasured set of parameters */
-/* specifiy strategy */
+/* specify strategy */
 static void randomConstrainedParams(paramValues_t* pc, const memoTable_t* memoTableArray, const ZSTD_strategy st)
 {
    size_t j;
@@ -1570,7 +1573,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx,
    display_params_tested(*comprParams);
    memset(&bResult, 0, sizeof(bResult));

-    /* warmimg up memory */
+    /* warming up memory */
    for (i = 0; i < buf.nbBlocks; i++) {
        if (mode != BMK_decodeOnly) {
            RDG_genBuffer(dstPtrs[i], dstCapacities[i], 0.10, 0.50, 1);
@@ -1638,7 +1641,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx,
                return bOut;
            }
            {   BMK_runTime_t const rResult = BMK_extract_runTime(cOutcome);
-                bResult.cSpeed = (srcSize * TIMELOOP_NANOSEC) / rResult.nanoSecPerRun;
+                bResult.cSpeed = (unsigned long long)((double)srcSize * TIMELOOP_NANOSEC / rResult.nanoSecPerRun);
                bResult.cSize = rResult.sumOfReturn;
            }
            compressionCompleted = BMK_isCompleted_TimedFn(timeStateCompress);
@@ -1656,7 +1659,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx,
                return bOut;
            }
            {   BMK_runTime_t const rResult = BMK_extract_runTime(dOutcome);
-                bResult.dSpeed = (srcSize * TIMELOOP_NANOSEC) / rResult.nanoSecPerRun;
+                bResult.dSpeed = (unsigned long long)((double)srcSize * TIMELOOP_NANOSEC / rResult.nanoSecPerRun);
            }
            decompressionCompleted = BMK_isCompleted_TimedFn(timeStateDecompress);
        }
@@ -1734,8 +1737,8 @@ static int allBench(BMK_benchResult_t* resultPtr,

    /* optimistic assumption of benchres */
    {   BMK_benchResult_t resultMax = benchres;
-        resultMax.cSpeed *= uncertaintyConstantC * VARIANCE;
-        resultMax.dSpeed *= uncertaintyConstantD * VARIANCE;
+        resultMax.cSpeed = (unsigned long long)(resultMax.cSpeed * uncertaintyConstantC * VARIANCE);
+        resultMax.dSpeed = (unsigned long long)(resultMax.dSpeed * uncertaintyConstantD * VARIANCE);

        /* disregard infeasible results in feas mode */
        /* disregard if resultMax < winner in infeas mode */
@@ -1989,7 +1992,7 @@ BMK_selectRandomStart( FILE* f,

 /* BMK_generate_cLevelTable() :
 * test a large number of configurations
- * and distribute them accross compression levels according to speed conditions.
+ * and distribute them across compression levels according to speed conditions.
 * display and save all intermediate results into rfName = "grillResults.txt".
 * the function automatically stops after g_timeLimit_s.
 * this function cannot error, it directly exit() in case of problem.
@@ -2199,7 +2202,9 @@ static winnerInfo_t climbOnce(const constraint_t target,
                for (offset = -1; offset <= 1; offset += 2) {
                    CHECKTIME(winnerInfo);
                    candidateInfo.params = cparam;
-                    paramVaryOnce(mtAll[cparam.vals[strt_ind]].varArray[i], offset, &candidateInfo.params);
+                    paramVaryOnce(mtAll[cparam.vals[strt_ind]].varArray[i],
+                                  offset,
+                                  &candidateInfo.params);

                    if(paramValid(candidateInfo.params)) {
                        int res;
@@ -2265,7 +2270,7 @@ static winnerInfo_t climbOnce(const constraint_t target,

 /* Optimizes for a fixed strategy */

-/* flexible parameters: iterations of failed climbing (or if we do non-random, maybe this is when everything is close to visitied)
+/* flexible parameters: iterations of failed climbing (or if we do non-random, maybe this is when everything is close to visited)
   weight more on visit for bad results, less on good results/more on later results / ones with more failures.
   allocate memoTable here.
 */
@@ -2351,7 +2356,7 @@ static int nextStrategy(const int currentStrategy, const int bestStrategy)
 * cLevel - compression level to exceed (all solutions must be > lvl in cSpeed + ratio)
 */

-static int g_maxTries = 5;
+static unsigned g_maxTries = 5;
 #define TRY_DECAY 1

 static int
@@ -2424,9 +2429,9 @@ optimizeForSize(const char* const * const fileNamesTable, const size_t nbFiles,
        }

        g_lvltarget = winner.result;
-        g_lvltarget.cSpeed *= ((double)g_strictness) / 100;
-        g_lvltarget.dSpeed *= ((double)g_strictness) / 100;
-        g_lvltarget.cSize /= ((double)g_strictness) / 100;
+        g_lvltarget.cSpeed = (g_lvltarget.cSpeed * g_strictness) / 100;
+        g_lvltarget.dSpeed = (g_lvltarget.dSpeed * g_strictness) / 100;
+        g_lvltarget.cSize = (g_lvltarget.cSize * 100) / g_strictness;

        target.cSpeed = (U32)g_lvltarget.cSpeed;
        target.dSpeed = (U32)g_lvltarget.dSpeed;
@@ -2561,7 +2566,7 @@ _cleanUp:
 * @return 0 and doesn't modify *stringPtr otherwise.
 * from zstdcli.c
 */
-static unsigned longCommandWArg(const char** stringPtr, const char* longCommand)
+static int longCommandWArg(const char** stringPtr, const char* longCommand)
 {
    size_t const comSize = strlen(longCommand);
    int const result = !strncmp(*stringPtr, longCommand, comSize);
@@ -2588,7 +2593,10 @@ static unsigned readU32FromChar(const char** stringPtr)
    while ((**stringPtr >='0') && (**stringPtr <='9')) {
        unsigned const max = (((unsigned)(-1)) / 10) - 1;
        if (result > max) errorOut(errorMsg);
-        result *= 10, result += **stringPtr - '0', (*stringPtr)++ ;
+        result *= 10;
+        assert(**stringPtr >= '0');
+        result += (unsigned)(**stringPtr - '0');
+        (*stringPtr)++ ;
    }
    if ((**stringPtr=='K') || (**stringPtr=='M')) {
        unsigned const maxK = ((unsigned)(-1)) >> 10;
@@ -2726,7 +2734,7 @@ int main(int argc, const char** argv)
                PARSE_SUB_ARGS("strict=", "stc=", g_strictness);
                PARSE_SUB_ARGS("maxTries=", "tries=", g_maxTries);
                PARSE_SUB_ARGS("memoLimitLog=", "memLog=", memoTableLog);
-                if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelOpt = readU32FromChar(&argument); g_optmode = 1; if (argument[0]==',') { argument++; continue; } else break; }
+                if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelOpt = (int)readU32FromChar(&argument); g_optmode = 1; if (argument[0]==',') { argument++; continue; } else break; }
                if (longCommandWArg(&argument, "speedForRatio=") || longCommandWArg(&argument, "speedRatio=")) { g_ratioMultiplier = readDoubleFromChar(&argument); if (argument[0]==',') { argument++; continue; } else break; }

                DISPLAY("invalid optimization parameter \n");
@@ -2743,7 +2751,7 @@ int main(int argc, const char** argv)
            g_singleRun = 1;
            for ( ; ;) {
                if(parse_params(&argument, &g_params)) { if(argument[0] == ',') { argument++; continue; } else break; }
-                if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelRun = readU32FromChar(&argument); g_params = emptyParams(); if (argument[0]==',') { argument++; continue; } else break; }
+                if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelRun = (int)readU32FromChar(&argument); g_params = emptyParams(); if (argument[0]==',') { argument++; continue; } else break; }

                DISPLAY("invalid compression parameter \n");
                return 1;
@@ -2855,7 +2863,7 @@ int main(int argc, const char** argv)
                            continue;
                        case 'L':
                            {   argument++;
-                                cLevelRun = readU32FromChar(&argument);
+                                cLevelRun = (int)readU32FromChar(&argument);
                                g_params = emptyParams();
                                continue;
                            }
@@ -2944,7 +2952,8 @@ int main(int argc, const char** argv)
            }
        } else {
            if (g_optimizer) {
-                result = optimizeForSize(argv+filenamesStart, argc-filenamesStart, dictFileName, target, paramTarget, cLevelOpt, cLevelRun, memoTableLog);
+                assert(filenamesStart < argc);
+                result = optimizeForSize(argv+filenamesStart, (size_t)(argc-filenamesStart), dictFileName, target, paramTarget, cLevelOpt, cLevelRun, memoTableLog);
            } else {
                result = benchFiles(argv+filenamesStart, argc-filenamesStart, dictFileName, cLevelRun);
            }
@@ -1,7 +1,9 @@
-#!/bin/sh -e
+#!/bin/sh
+
+set -e

 die() {
-    $ECHO "$@" 1>&2
+    println "$@" 1>&2
    exit 1
 }

@@ -20,7 +22,7 @@ roundTripTest() {
    fi

    rm -f tmp1 tmp2
-    $ECHO "roundTripTest: ./datagen $1 $proba | $ZSTD -v$cLevel | $ZSTD -d$dLevel"
+    println "roundTripTest: ./datagen $1 $proba | $ZSTD -v$cLevel | $ZSTD -d$dLevel"
    ./datagen $1 $proba | $MD5SUM > tmp1
    ./datagen $1 $proba | $ZSTD --ultra -v$cLevel | $ZSTD -d$dLevel  | $MD5SUM > tmp2
    $DIFF -q tmp1 tmp2
@@ -41,7 +43,7 @@ fileRoundTripTest() {
    fi

    rm -f tmp.zstd tmp.md5.1 tmp.md5.2
-    $ECHO "fileRoundTripTest: ./datagen $1 $local_p > tmp && $ZSTD -v$local_c -c tmp | $ZSTD -d$local_d"
+    println "fileRoundTripTest: ./datagen $1 $local_p > tmp && $ZSTD -v$local_c -c tmp | $ZSTD -d$local_d"
    ./datagen $1 $local_p > tmp
    < tmp $MD5SUM > tmp.md5.1
    $ZSTD --ultra -v$local_c -c tmp | $ZSTD -d$local_d | $MD5SUM > tmp.md5.2
@@ -49,9 +51,17 @@ fileRoundTripTest() {
 }

 truncateLastByte() {
-	dd bs=1 count=$(($(wc -c < "$1") - 1)) if="$1" status=none
+    dd bs=1 count=$(($(wc -c < "$1") - 1)) if="$1"
 }

+println() {
+    printf '%b\n' "${*}"
+}
+
+
+SCRIPT_DIR=$(cd "$(dirname "$0")" && pwd)
+PRGDIR="$SCRIPT_DIR/../programs"
+TESTDIR="$SCRIPT_DIR/../tests"
 UNAME=$(uname)

 isTerminal=false
@@ -86,16 +96,11 @@ case "$UNAME" in
  SunOS) DIFF="gdiff" ;;
 esac

-ECHO="echo -e"
-case "$UNAME" in
-  Darwin) ECHO="echo" ;;
-esac
-
-$ECHO "\nStarting playTests.sh isWindows=$isWindows ZSTD='$ZSTD'"
+println "\nStarting playTests.sh isWindows=$isWindows ZSTD='$ZSTD'"

 [ -n "$ZSTD" ] || die "ZSTD variable must be defined!"

-if [ -n "$(echo hello | $ZSTD -v -T2 2>&1 > $INTOVOID | grep 'multi-threading is disabled')" ]
+if echo hello | $ZSTD -v -T2 2>&1 > $INTOVOID | grep -q 'multi-threading is disabled'
 then
    hasMT=""
 else
@@ -104,124 +109,133 @@ fi



-$ECHO "\n===>  simple tests "
+println "\n===>  simple tests "

 ./datagen > tmp
-$ECHO "test : basic compression "
+println "test : basic compression "
 $ZSTD -f tmp                      # trivial compression case, creates tmp.zst
-$ECHO "test : basic decompression"
+println "test : basic decompression"
 $ZSTD -df tmp.zst                 # trivial decompression case (overwrites tmp)
-$ECHO "test : too large compression level => auto-fix"
+println "test : too large compression level => auto-fix"
 $ZSTD -99 -f tmp  # too large compression level, automatic sized down
 $ZSTD -5000000000 -f tmp && die "too large numeric value : must fail"
-$ECHO "test : --fast aka negative compression levels"
+println "test : --fast aka negative compression levels"
 $ZSTD --fast -f tmp  # == -1
 $ZSTD --fast=3 -f tmp  # == -3
 $ZSTD --fast=200000 -f tmp  # too low compression level, automatic fixed
 $ZSTD --fast=5000000000 -f tmp && die "too large numeric value : must fail"
 $ZSTD -c --fast=0 tmp > $INTOVOID && die "--fast must not accept value 0"
-$ECHO "test : too large numeric argument"
+println "test : too large numeric argument"
 $ZSTD --fast=9999999999 -f tmp  && die "should have refused numeric value"
-$ECHO "test : set compression level with environment variable ZSTD_CLEVEL"
+println "test : set compression level with environment variable ZSTD_CLEVEL"
 ZSTD_CLEVEL=12  $ZSTD -f tmp # positive compression level
 ZSTD_CLEVEL=-12 $ZSTD -f tmp # negative compression level
 ZSTD_CLEVEL=+12 $ZSTD -f tmp # valid: verbose '+' sign
-ZSTD_CLEVEL=    $ZSTD -f tmp # empty env var, warn and revert to default setting
+ZSTD_CLEVEL=''  $ZSTD -f tmp # empty env var, warn and revert to default setting
 ZSTD_CLEVEL=-   $ZSTD -f tmp # malformed env var, warn and revert to default setting
 ZSTD_CLEVEL=a   $ZSTD -f tmp # malformed env var, warn and revert to default setting
 ZSTD_CLEVEL=+a  $ZSTD -f tmp # malformed env var, warn and revert to default setting
 ZSTD_CLEVEL=3a7 $ZSTD -f tmp # malformed env var, warn and revert to default setting
 ZSTD_CLEVEL=50000000000  $ZSTD -f tmp # numeric value too large, warn and revert to default setting
-$ECHO "test : override ZSTD_CLEVEL with command line option"
+println "test : override ZSTD_CLEVEL with command line option"
 ZSTD_CLEVEL=12  $ZSTD --fast=3 -f tmp # overridden by command line option
-$ECHO "test : compress to stdout"
+println "test : compress to stdout"
 $ZSTD tmp -c > tmpCompressed
 $ZSTD tmp --stdout > tmpCompressed       # long command format
-$ECHO "test : compress to named file"
+println "test : compress to named file"
 rm tmpCompressed
 $ZSTD tmp -o tmpCompressed
 test -f tmpCompressed   # file must be created
-$ECHO "test : -o must be followed by filename (must fail)"
+println "test : -o must be followed by filename (must fail)"
 $ZSTD tmp -of tmpCompressed && die "-o must be followed by filename "
-$ECHO "test : force write, correct order"
+println "test : force write, correct order"
 $ZSTD tmp -fo tmpCompressed
-$ECHO "test : forgotten argument"
+println "test : forgotten argument"
 cp tmp tmp2
 $ZSTD tmp2 -fo && die "-o must be followed by filename "
-$ECHO "test : implied stdout when input is stdin"
-$ECHO bob | $ZSTD | $ZSTD -d
+println "test : implied stdout when input is stdin"
+println bob | $ZSTD | $ZSTD -d
 if [ "$isTerminal" = true ]; then
-$ECHO "test : compressed data to terminal"
-$ECHO bob | $ZSTD && die "should have refused : compressed data to terminal"
-$ECHO "test : compressed data from terminal (a hang here is a test fail, zstd is wrongly waiting on data from terminal)"
+println "test : compressed data to terminal"
+println bob | $ZSTD && die "should have refused : compressed data to terminal"
+println "test : compressed data from terminal (a hang here is a test fail, zstd is wrongly waiting on data from terminal)"
 $ZSTD -d > $INTOVOID && die "should have refused : compressed data from terminal"
 fi
-$ECHO "test : null-length file roundtrip"
-$ECHO -n '' | $ZSTD - --stdout | $ZSTD -d --stdout
-$ECHO "test : ensure small file doesn't add 3-bytes null block"
+println "test : null-length file roundtrip"
+println -n '' | $ZSTD - --stdout | $ZSTD -d --stdout
+println "test : ensure small file doesn't add 3-bytes null block"
 ./datagen -g1 > tmp1
 $ZSTD tmp1 -c | wc -c | grep "14"
 $ZSTD < tmp1  | wc -c | grep "14"
-$ECHO "test : decompress file with wrong suffix (must fail)"
+println "test : decompress file with wrong suffix (must fail)"
 $ZSTD -d tmpCompressed && die "wrong suffix error not detected!"
 $ZSTD -df tmp && die "should have refused : wrong extension"
-$ECHO "test : decompress into stdout"
+println "test : decompress into stdout"
 $ZSTD -d tmpCompressed -c > tmpResult    # decompression using stdout
 $ZSTD --decompress tmpCompressed -c > tmpResult
 $ZSTD --decompress tmpCompressed --stdout > tmpResult
-$ECHO "test : decompress from stdin into stdout"
+println "test : decompress from stdin into stdout"
 $ZSTD -dc   < tmp.zst > $INTOVOID   # combine decompression, stdin & stdout
 $ZSTD -dc - < tmp.zst > $INTOVOID
 $ZSTD -d    < tmp.zst > $INTOVOID   # implicit stdout when stdin is used
 $ZSTD -d  - < tmp.zst > $INTOVOID
-$ECHO "test : impose memory limitation (must fail)"
+println "test : impose memory limitation (must fail)"
 $ZSTD -d -f tmp.zst -M2K -c > $INTOVOID && die "decompression needs more memory than allowed"
 $ZSTD -d -f tmp.zst --memlimit=2K -c > $INTOVOID && die "decompression needs more memory than allowed"  # long command
 $ZSTD -d -f tmp.zst --memory=2K -c > $INTOVOID && die "decompression needs more memory than allowed"  # long command
 $ZSTD -d -f tmp.zst --memlimit-decompress=2K -c > $INTOVOID && die "decompression needs more memory than allowed"  # long command
-$ECHO "test : overwrite protection"
+println "test : overwrite protection"
 $ZSTD -q tmp && die "overwrite check failed!"
-$ECHO "test : force overwrite"
+println "test : force overwrite"
 $ZSTD -q -f tmp
 $ZSTD -q --force tmp
-$ECHO "test : overwrite readonly file"
+println "test : overwrite readonly file"
 rm -f tmpro tmpro.zst
-$ECHO foo > tmpro.zst
-$ECHO foo > tmpro
+println foo > tmpro.zst
+println foo > tmpro
 chmod 400 tmpro.zst
 $ZSTD -q tmpro && die "should have refused to overwrite read-only file"
 $ZSTD -q -f tmpro
-$ECHO "test: --no-progress flag"
+println "test: --no-progress flag"
 $ZSTD tmpro -c --no-progress | $ZSTD -d -f -o "$INTOVOID" --no-progress
 $ZSTD tmpro -cv --no-progress | $ZSTD -dv -f -o "$INTOVOID" --no-progress
 rm -f tmpro tmpro.zst
-$ECHO "test: overwrite input file (must fail)"
+println "test: overwrite input file (must fail)"
 $ZSTD tmp -fo tmp && die "zstd compression overwrote the input file"
 $ZSTD tmp.zst -dfo tmp.zst && die "zstd decompression overwrote the input file"
-$ECHO "test: detect that input file does not exist"
+println "test: detect that input file does not exist"
 $ZSTD nothere && die "zstd hasn't detected that input file does not exist"
+println "test: --[no-]compress-literals"
+$ZSTD tmp -c --no-compress-literals -1       | $ZSTD -t
+$ZSTD tmp -c --no-compress-literals --fast=1 | $ZSTD -t
+$ZSTD tmp -c --no-compress-literals -19      | $ZSTD -t
+$ZSTD tmp -c --compress-literals    -1       | $ZSTD -t
+$ZSTD tmp -c --compress-literals    --fast=1 | $ZSTD -t
+$ZSTD tmp -c --compress-literals    -19      | $ZSTD -t
+$ZSTD -b --fast=1 -i1e1 tmp --compress-literals
+$ZSTD -b --fast=1 -i1e1 tmp --no-compress-literals

-$ECHO "test : file removal"
+println "test : file removal"
 $ZSTD -f --rm tmp
 test ! -f tmp  # tmp should no longer be present
 $ZSTD -f -d --rm tmp.zst
 test ! -f tmp.zst   # tmp.zst should no longer be present
-$ECHO "test : should quietly not remove non-regular file"
-$ECHO hello > tmp
+println "test : should quietly not remove non-regular file"
+println hello > tmp
 $ZSTD tmp -f -o "$DEVDEVICE" 2>tmplog > "$INTOVOID"
 grep -v "Refusing to remove non-regular file" tmplog
 rm -f tmplog
 $ZSTD tmp -f -o "$INTOVOID" 2>&1 | grep -v "Refusing to remove non-regular file"
-$ECHO "test : --rm on stdin"
-$ECHO a | $ZSTD --rm > $INTOVOID   # --rm should remain silent
+println "test : --rm on stdin"
+println a | $ZSTD --rm > $INTOVOID   # --rm should remain silent
 rm tmp
 $ZSTD -f tmp && die "tmp not present : should have failed"
 test ! -f tmp.zst  # tmp.zst should not be created
-$ECHO "test : -d -f do not delete destination when source is not present"
+println "test : -d -f do not delete destination when source is not present"
 touch tmp    # create destination file
 $ZSTD -d -f tmp.zst && die "attempt to decompress a non existing file"
 test -f tmp  # destination file should still be present
-$ECHO "test : -f do not delete destination when source is not present"
+println "test : -f do not delete destination when source is not present"
 rm tmp         # erase source file
 touch tmp.zst  # create destination file
 $ZSTD -f tmp && die "attempt to compress a non existing file"
@@ -229,9 +243,9 @@ test -f tmp.zst  # destination file should still be present
 rm tmp*


-$ECHO "test : compress multiple files"
-$ECHO hello > tmp1
-$ECHO world > tmp2
+println "test : compress multiple files"
+println hello > tmp1
+println world > tmp2
 $ZSTD tmp1 tmp2 -o "$INTOVOID" -f
 $ZSTD tmp1 tmp2 -c | $ZSTD -t
 $ZSTD tmp1 tmp2 -o tmp.zst
@@ -252,11 +266,11 @@ fi
 rm tmp*


-$ECHO "\n===>  Advanced compression parameters "
-$ECHO "Hello world!" | $ZSTD --zstd=windowLog=21,      - -o tmp.zst && die "wrong parameters not detected!"
-$ECHO "Hello world!" | $ZSTD --zstd=windowLo=21        - -o tmp.zst && die "wrong parameters not detected!"
-$ECHO "Hello world!" | $ZSTD --zstd=windowLog=21,slog  - -o tmp.zst && die "wrong parameters not detected!"
-$ECHO "Hello world!" | $ZSTD --zstd=strategy=10        - -o tmp.zst && die "parameter out of bound not detected!"  # > btultra2 : does not exist
+println "\n===>  Advanced compression parameters "
+println "Hello world!" | $ZSTD --zstd=windowLog=21,      - -o tmp.zst && die "wrong parameters not detected!"
+println "Hello world!" | $ZSTD --zstd=windowLo=21        - -o tmp.zst && die "wrong parameters not detected!"
+println "Hello world!" | $ZSTD --zstd=windowLog=21,slog  - -o tmp.zst && die "wrong parameters not detected!"
+println "Hello world!" | $ZSTD --zstd=strategy=10        - -o tmp.zst && die "parameter out of bound not detected!"  # > btultra2 : does not exist
 test ! -f tmp.zst  # tmp.zst should not be created
 roundTripTest -g512K
 roundTripTest -g512K " --zstd=mml=3,tlen=48,strat=6"
@@ -267,17 +281,17 @@ roundTripTest -g512K " --single-thread --long --zstd=lhlog=20,lmml=64,lblog=1,lh
 roundTripTest -g64K  "19 --zstd=strat=9"   # btultra2


-$ECHO "\n===>  Pass-Through mode "
-$ECHO "Hello world 1!" | $ZSTD -df
-$ECHO "Hello world 2!" | $ZSTD -dcf
-$ECHO "Hello world 3!" > tmp1
+println "\n===>  Pass-Through mode "
+println "Hello world 1!" | $ZSTD -df
+println "Hello world 2!" | $ZSTD -dcf
+println "Hello world 3!" > tmp1
 $ZSTD -dcf tmp1


-$ECHO "\n===>  frame concatenation "
+println "\n===>  frame concatenation "

-$ECHO "hello " > hello.tmp
-$ECHO "world!" > world.tmp
+println "hello " > hello.tmp
+println "world!" > world.tmp
 cat hello.tmp world.tmp > helloworld.tmp
 $ZSTD -c hello.tmp > hello.zstd
 $ZSTD -c world.tmp > world.zstd
@@ -285,52 +299,67 @@ cat hello.zstd world.zstd > helloworld.zstd
 $ZSTD -dc helloworld.zstd > result.tmp
 cat result.tmp
 $DIFF helloworld.tmp result.tmp
-$ECHO "frame concatenation without checksum"
+println "frame concatenation without checksum"
 $ZSTD -c hello.tmp > hello.zstd --no-check
 $ZSTD -c world.tmp > world.zstd --no-check
 cat hello.zstd world.zstd > helloworld.zstd
 $ZSTD -dc helloworld.zstd > result.tmp
 $DIFF helloworld.tmp result.tmp
-$ECHO "testing zstdcat symlink"
+println "testing zstdcat symlink"
 ln -sf $ZSTD zstdcat
 ./zstdcat helloworld.zstd > result.tmp
 $DIFF helloworld.tmp result.tmp
+ln -s helloworld.zstd helloworld.link.zstd
+./zstdcat helloworld.link.zstd > result.tmp
+$DIFF helloworld.tmp result.tmp
 rm zstdcat
 rm result.tmp
-$ECHO "testing zcat symlink"
+println "testing zcat symlink"
 ln -sf $ZSTD zcat
 ./zcat helloworld.zstd > result.tmp
 $DIFF helloworld.tmp result.tmp
+./zcat helloworld.link.zstd > result.tmp
+$DIFF helloworld.tmp result.tmp
 rm zcat
 rm ./*.tmp ./*.zstd
-$ECHO "frame concatenation tests completed"
+println "frame concatenation tests completed"


 if [ "$isWindows" = false ] && [ "$UNAME" != 'SunOS' ] && [ "$UNAME" != "OpenBSD" ] ; then
-$ECHO "\n**** flush write error test **** "
+println "\n**** flush write error test **** "

-$ECHO "$ECHO foo | $ZSTD > /dev/full"
-$ECHO foo | $ZSTD > /dev/full && die "write error not detected!"
-$ECHO "$ECHO foo | $ZSTD | $ZSTD -d > /dev/full"
-$ECHO foo | $ZSTD | $ZSTD -d > /dev/full && die "write error not detected!"
-
-
-$ECHO "\n===>  symbolic link test "
-
-rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst
-$ECHO "hello world" > hello.tmp
-ln -s hello.tmp world.tmp
-$ZSTD world.tmp hello.tmp
-test -f hello.tmp.zst  # regular file should have been compressed!
-test ! -f world.tmp.zst  # symbolic link should not have been compressed!
-$ZSTD world.tmp hello.tmp -f
-test -f world.tmp.zst  # symbolic link should have been compressed with --force
-rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst
+println "println foo | $ZSTD > /dev/full"
+println foo | $ZSTD > /dev/full && die "write error not detected!"
+println "println foo | $ZSTD | $ZSTD -d > /dev/full"
+println foo | $ZSTD | $ZSTD -d > /dev/full && die "write error not detected!"

 fi


-$ECHO "\n===>  test sparse file support "
+if [ "$isWindows" = false ] && [ "$UNAME" != 'SunOS' ] ; then
+
+println "\n===>  symbolic link test "
+
+rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst
+println "hello world" > hello.tmp
+ln -s hello.tmp world.tmp
+ln -s hello.tmp world2.tmp
+$ZSTD world.tmp hello.tmp || true
+test -f hello.tmp.zst  # regular file should have been compressed!
+test ! -f world.tmp.zst  # symbolic link should not have been compressed!
+$ZSTD world.tmp || true
+test ! -f world.tmp.zst  # symbolic link should not have been compressed!
+$ZSTD world.tmp world2.tmp || true
+test ! -f world.tmp.zst  # symbolic link should not have been compressed!
+test ! -f world2.tmp.zst  # symbolic link should not have been compressed!
+$ZSTD world.tmp hello.tmp -f
+test -f world.tmp.zst  # symbolic link should have been compressed with --force
+rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst
+
+fi
+
+
+println "\n===>  test sparse file support "

 ./datagen -g5M  -P100 > tmpSparse
 $ZSTD tmpSparse -c | $ZSTD -dv -o tmpSparseRegen
@@ -343,10 +372,10 @@ ls -ls tmpSparse*  # look at file size and block size on disk
 ./datagen -s1 -g1200007 -P100 | $ZSTD | $ZSTD -dv --sparse -c > tmpSparseOdd   # Odd size file (to not finish on an exact nb of blocks)
 ./datagen -s1 -g1200007 -P100 | $DIFF -s - tmpSparseOdd
 ls -ls tmpSparseOdd  # look at file size and block size on disk
-$ECHO "\n Sparse Compatibility with Console :"
-$ECHO "Hello World 1 !" | $ZSTD | $ZSTD -d -c
-$ECHO "Hello World 2 !" | $ZSTD | $ZSTD -d | cat
-$ECHO "\n Sparse Compatibility with Append :"
+println "\n Sparse Compatibility with Console :"
+println "Hello World 1 !" | $ZSTD | $ZSTD -d -c
+println "Hello World 2 !" | $ZSTD | $ZSTD -d | cat
+println "\n Sparse Compatibility with Append :"
 ./datagen -P100 -g1M > tmpSparse1M
 cat tmpSparse1M tmpSparse1M > tmpSparse2M
 $ZSTD -v -f tmpSparse1M -o tmpSparseCompressed
@@ -357,185 +386,193 @@ $DIFF tmpSparse2M tmpSparseRegenerated
 rm tmpSparse*


-$ECHO "\n===>  multiple files tests "
+println "\n===>  multiple files tests "

 ./datagen -s1        > tmp1 2> $INTOVOID
 ./datagen -s2 -g100K > tmp2 2> $INTOVOID
 ./datagen -s3 -g1M   > tmp3 2> $INTOVOID
-$ECHO "compress tmp* : "
+println "compress tmp* : "
 $ZSTD -f tmp*
 ls -ls tmp*
 rm tmp1 tmp2 tmp3
-$ECHO "decompress tmp* : "
-$ZSTD -df *.zst
+println "decompress tmp* : "
+$ZSTD -df ./*.zst
 ls -ls tmp*
-$ECHO "compress tmp* into stdout > tmpall : "
+println "compress tmp* into stdout > tmpall : "
 $ZSTD -c tmp1 tmp2 tmp3 > tmpall
 ls -ls tmp*  # check size of tmpall (should be tmp1.zst + tmp2.zst + tmp3.zst)
-$ECHO "decompress tmpall* into stdout > tmpdec : "
+println "decompress tmpall* into stdout > tmpdec : "
 cp tmpall tmpall2
 $ZSTD -dc tmpall* > tmpdec
 ls -ls tmp* # check size of tmpdec (should be 2*(tmp1 + tmp2 + tmp3))
-$ECHO "compress multiple files including a missing one (notHere) : "
+println "compress multiple files including a missing one (notHere) : "
 $ZSTD -f tmp1 notHere tmp2 && die "missing file not detected!"


-$ECHO "\n===>  dictionary tests "
+println "\n===>  dictionary tests "

-$ECHO "- test with raw dict (content only) "
+println "- test with raw dict (content only) "
 ./datagen > tmpDict
 ./datagen -g1M | $MD5SUM > tmp1
 ./datagen -g1M | $ZSTD -D tmpDict | $ZSTD -D tmpDict -dvq | $MD5SUM > tmp2
 $DIFF -q tmp1 tmp2
-$ECHO "- Create first dictionary "
-TESTFILE=../programs/zstdcli.c
-$ZSTD --train *.c ../programs/*.c -o tmpDict
-cp $TESTFILE tmp
-$ECHO "- Dictionary compression roundtrip"
+println "- Create first dictionary "
+TESTFILE="$PRGDIR"/zstdcli.c
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict
+cp "$TESTFILE" tmp
+println "- Test dictionary compression with tmpDict as an input file and dictionary"
+$ZSTD -f tmpDict -D tmpDict && die "compression error not detected!"
+println "- Dictionary compression roundtrip"
 $ZSTD -f tmp -D tmpDict
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
-$ECHO "- Dictionary compression with btlazy2 strategy"
+$DIFF "$TESTFILE" result
+println "- Dictionary compression with btlazy2 strategy"
 $ZSTD -f tmp -D tmpDict --zstd=strategy=6
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
+$DIFF "$TESTFILE" result
 if [ -n "$hasMT" ]
 then
-    $ECHO "- Test dictionary compression with multithreading "
+    println "- Test dictionary compression with multithreading "
    ./datagen -g5M | $ZSTD -T2 -D tmpDict | $ZSTD -t -D tmpDict   # fails with v1.3.2
 fi
-$ECHO "- Create second (different) dictionary "
-$ZSTD --train *.c ../programs/*.c ../programs/*.h -o tmpDictC
+println "- Create second (different) dictionary "
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
 $ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
-$ECHO "- Create dictionary with short dictID"
-$ZSTD --train *.c ../programs/*.c --dictID=1 -o tmpDict1
+println "- Create dictionary with short dictID"
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
 cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
-$ECHO "- Create dictionary with wrong dictID parameter order (must fail)"
-$ZSTD --train *.c ../programs/*.c --dictID -o 1 tmpDict1 && die "wrong order : --dictID must be followed by argument "
-$ECHO "- Create dictionary with size limit"
-$ZSTD --train *.c ../programs/*.c -o tmpDict2 --maxdict=4K -v
-$ECHO "- Create dictionary with small size limit"
-$ZSTD --train *.c ../programs/*.c -o tmpDict3 --maxdict=1K -v
-$ECHO "- Create dictionary with wrong parameter order (must fail)"
-$ZSTD --train *.c ../programs/*.c -o tmpDict3 --maxdict -v 4K && die "wrong order : --maxdict must be followed by argument "
-$ECHO "- Compress without dictID"
+println "- Create dictionary with wrong dictID parameter order (must fail)"
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID -o 1 tmpDict1 && die "wrong order : --dictID must be followed by argument "
+println "- Create dictionary with size limit"
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K -v
+println "- Create dictionary with small size limit"
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict3 --maxdict=1K -v
+println "- Create dictionary with wrong parameter order (must fail)"
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict3 --maxdict -v 4K && die "wrong order : --maxdict must be followed by argument "
+println "- Compress without dictID"
 $ZSTD -f tmp -D tmpDict1 --no-dictID
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
-$ECHO "- Compress with wrong argument order (must fail)"
+$DIFF "$TESTFILE" result
+println "- Compress with wrong argument order (must fail)"
 $ZSTD tmp -Df tmpDict1 -c > $INTOVOID && die "-D must be followed by dictionary name "
-$ECHO "- Compress multiple files with dictionary"
+println "- Compress multiple files with dictionary"
 rm -rf dirTestDict
 mkdir dirTestDict
-cp *.c dirTestDict
-cp ../programs/*.c dirTestDict
-cp ../programs/*.h dirTestDict
+cp "$TESTDIR"/*.c dirTestDict
+cp "$PRGDIR"/*.c dirTestDict
+cp "$PRGDIR"/*.h dirTestDict
 $MD5SUM dirTestDict/* > tmph1
 $ZSTD -f --rm dirTestDict/* -D tmpDictC
 $ZSTD -d --rm dirTestDict/*.zst -D tmpDictC  # note : use internal checksum by default
 case "$UNAME" in
-  Darwin) $ECHO "md5sum -c not supported on OS-X : test skipped" ;;  # not compatible with OS-X's md5
+  Darwin) println "md5sum -c not supported on OS-X : test skipped" ;;  # not compatible with OS-X's md5
  *) $MD5SUM -c tmph1 ;;
 esac
 rm -rf dirTestDict
-$ECHO "- dictionary builder on bogus input"
-$ECHO "Hello World" > tmp
+println "- dictionary builder on bogus input"
+println "Hello World" > tmp
 $ZSTD --train-legacy -q tmp && die "Dictionary training should fail : not enough input source"
 ./datagen -P0 -g10M > tmp
 $ZSTD --train-legacy -q tmp && die "Dictionary training should fail : source is pure noise"
-$ECHO "- Test -o before --train"
+println "- Test -o before --train"
 rm -f tmpDict dictionary
-$ZSTD -o tmpDict --train *.c ../programs/*.c
+$ZSTD -o tmpDict --train "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f tmpDict
-$ZSTD --train *.c ../programs/*.c
+$ZSTD --train "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f dictionary
 rm tmp* dictionary


-$ECHO "\n===>  fastCover dictionary builder : advanced options "
-
-TESTFILE=../programs/zstdcli.c
+println "\n===>  fastCover dictionary builder : advanced options "
+TESTFILE="$PRGDIR"/zstdcli.c
 ./datagen > tmpDict
-$ECHO "- Create first dictionary"
-$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 *.c ../programs/*.c -o tmpDict
-cp $TESTFILE tmp
+println "- Create first dictionary"
+$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict
+cp "$TESTFILE" tmp
 $ZSTD -f tmp -D tmpDict
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
-$ECHO "- Create second (different) dictionary"
-$ZSTD --train-fastcover=k=56,d=8 *.c ../programs/*.c ../programs/*.h -o tmpDictC
+$DIFF "$TESTFILE" result
+println "- Create second (different) dictionary"
+$ZSTD --train-fastcover=k=56,d=8 "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
 $ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
-$ECHO "- Create dictionary with short dictID"
-$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 *.c ../programs/*.c --dictID=1 -o tmpDict1
+$ZSTD --train-fastcover=k=56,d=8 && die "Create dictionary without input file"
+println "- Create dictionary with short dictID"
+$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
 cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
-$ECHO "- Create dictionary with size limit"
-$ZSTD --train-fastcover=steps=8 *.c ../programs/*.c -o tmpDict2 --maxdict=4K
-$ECHO "- Compare size of dictionary from 90% training samples with 80% training samples"
-$ZSTD --train-fastcover=split=90 -r *.c ../programs/*.c
-$ZSTD --train-fastcover=split=80 -r *.c ../programs/*.c
-$ECHO "- Create dictionary using all samples for both training and testing"
-$ZSTD --train-fastcover=split=100 -r *.c ../programs/*.c
-$ECHO "- Create dictionary using f=16"
-$ZSTD --train-fastcover=f=16 -r *.c ../programs/*.c
-$ECHO "- Create dictionary using accel=2"
-$ZSTD --train-fastcover=accel=2 -r *.c ../programs/*.c
-$ECHO "- Create dictionary using accel=10"
-$ZSTD --train-fastcover=accel=10 -r *.c ../programs/*.c
-$ECHO "- Create dictionary with multithreading"
-$ZSTD --train-fastcover -T4 -r *.c ../programs/*.c
-$ECHO "- Test -o before --train-fastcover"
+println "- Create dictionaries with shrink-dict flag enabled"
+$ZSTD --train-fastcover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict
+$ZSTD --train-fastcover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict1
+$ZSTD --train-fastcover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict2
+println "- Create dictionary with size limit"
+$ZSTD --train-fastcover=steps=8 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K
+println "- Compare size of dictionary from 90% training samples with 80% training samples"
+$ZSTD --train-fastcover=split=90 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+$ZSTD --train-fastcover=split=80 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Create dictionary using all samples for both training and testing"
+$ZSTD --train-fastcover=split=100 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Create dictionary using f=16"
+$ZSTD --train-fastcover=f=16 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+$ZSTD --train-fastcover=accel=15 -r "$TESTDIR"/*.c "$PRGDIR"/*.c && die "Created dictionary using accel=15"
+println "- Create dictionary using accel=2"
+$ZSTD --train-fastcover=accel=2 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Create dictionary using accel=10"
+$ZSTD --train-fastcover=accel=10 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Create dictionary with multithreading"
+$ZSTD --train-fastcover -T4 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Test -o before --train-fastcover"
 rm -f tmpDict dictionary
-$ZSTD -o tmpDict --train-fastcover *.c ../programs/*.c
+$ZSTD -o tmpDict --train-fastcover "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f tmpDict
-$ZSTD --train-fastcover *.c ../programs/*.c
+$ZSTD --train-fastcover "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f dictionary
 rm tmp* dictionary


-$ECHO "\n===>  legacy dictionary builder "
+println "\n===>  legacy dictionary builder "

-TESTFILE=../programs/zstdcli.c
+TESTFILE="$PRGDIR"/zstdcli.c
 ./datagen > tmpDict
-$ECHO "- Create first dictionary"
-$ZSTD --train-legacy=selectivity=8 *.c ../programs/*.c -o tmpDict
-cp $TESTFILE tmp
+println "- Create first dictionary"
+$ZSTD --train-legacy=selectivity=8 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict
+cp "$TESTFILE" tmp
 $ZSTD -f tmp -D tmpDict
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
-$ECHO "- Create second (different) dictionary"
-$ZSTD --train-legacy=s=5 *.c ../programs/*.c ../programs/*.h -o tmpDictC
+$DIFF "$TESTFILE" result
+$ZSTD --train-legacy=s=8 && die "Create dictionary without input files (should error)"
+println "- Create second (different) dictionary"
+$ZSTD --train-legacy=s=5 "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
 $ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
-$ECHO "- Create dictionary with short dictID"
-$ZSTD --train-legacy -s5 *.c ../programs/*.c --dictID=1 -o tmpDict1
+println "- Create dictionary with short dictID"
+$ZSTD --train-legacy -s5 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
 cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
-$ECHO "- Create dictionary with size limit"
-$ZSTD --train-legacy -s9 *.c ../programs/*.c -o tmpDict2 --maxdict=4K
-$ECHO "- Test -o before --train-legacy"
+println "- Create dictionary with size limit"
+$ZSTD --train-legacy -s9 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K
+println "- Test -o before --train-legacy"
 rm -f tmpDict dictionary
-$ZSTD -o tmpDict --train-legacy *.c ../programs/*.c
+$ZSTD -o tmpDict --train-legacy "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f tmpDict
-$ZSTD --train-legacy *.c ../programs/*.c
+$ZSTD --train-legacy "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f dictionary
 rm tmp* dictionary


-$ECHO "\n===>  integrity tests "
+println "\n===>  integrity tests "

-$ECHO "test one file (tmp1.zst) "
+println "test one file (tmp1.zst) "
 ./datagen > tmp1
 $ZSTD tmp1
 $ZSTD -t tmp1.zst
 $ZSTD --test tmp1.zst
-$ECHO "test multiple files (*.zst) "
-$ZSTD -t *.zst
-$ECHO "test bad files (*) "
-$ZSTD -t * && die "bad files not detected !"
+println "test multiple files (*.zst) "
+$ZSTD -t ./*.zst
+println "test bad files (*) "
+$ZSTD -t ./* && die "bad files not detected !"
 $ZSTD -t tmp1 && die "bad file not detected !"
 cp tmp1 tmp2.zst
 $ZSTD -t tmp2.zst && die "bad file not detected !"
 ./datagen -g0 > tmp3
 $ZSTD -t tmp3 && die "bad file not detected !"   # detects 0-sized files as bad
-$ECHO "test --rm and --test combined "
+println "test --rm and --test combined "
 $ZSTD -t --rm tmp1.zst
 test -f tmp1.zst   # check file is still present
 split -b16384 tmp1.zst tmpSplit.
@@ -544,40 +581,40 @@ $ZSTD -t tmpSplit.* && die "bad file not detected !"



-$ECHO "\n===>  golden files tests "
+println "\n===>  golden files tests "

-$ZSTD -t -r files
-$ZSTD -c -r files | $ZSTD -t
+$ZSTD -t -r "$TESTDIR/files"
+$ZSTD -c -r "$TESTDIR/files" | $ZSTD -t


-$ECHO "\n===>  benchmark mode tests "
+println "\n===>  benchmark mode tests "

-$ECHO "bench one file"
+println "bench one file"
 ./datagen > tmp1
 $ZSTD -bi0 tmp1
-$ECHO "bench multiple levels"
+println "bench multiple levels"
 $ZSTD -i0b0e3 tmp1
-$ECHO "bench negative level"
+println "bench negative level"
 $ZSTD -bi0 --fast tmp1
-$ECHO "with recursive and quiet modes"
+println "with recursive and quiet modes"
 $ZSTD -rqi1b1e2 tmp1
-$ECHO "benchmark decompression only"
+println "benchmark decompression only"
 $ZSTD -f tmp1
 $ZSTD -b -d -i1 tmp1.zst

-$ECHO "\n===>  zstd compatibility tests "
+println "\n===>  zstd compatibility tests "

 ./datagen > tmp
 rm -f tmp.zst
 $ZSTD --format=zstd -f tmp
 test -f tmp.zst

-$ECHO "\n===>  gzip compatibility tests "
+println "\n===>  gzip compatibility tests "

 GZIPMODE=1
 $ZSTD --format=gzip -V || GZIPMODE=0
 if [ $GZIPMODE -eq 1 ]; then
-    $ECHO "gzip support detected"
+    println "gzip support detected"
    GZIPEXE=1
    gzip -V || GZIPEXE=0
    if [ $GZIPEXE -eq 1 ]; then
@@ -588,14 +625,14 @@ if [ $GZIPMODE -eq 1 ]; then
        $ZSTD -d -f -v tmp.gz
        rm tmp*
    else
-        $ECHO "gzip binary not detected"
+        println "gzip binary not detected"
    fi
 else
-    $ECHO "gzip mode not supported"
+    println "gzip mode not supported"
 fi


-$ECHO "\n===>  gzip frame tests "
+println "\n===>  gzip frame tests "

 if [ $GZIPMODE -eq 1 ]; then
    ./datagen > tmp
@@ -605,7 +642,7 @@ if [ $GZIPMODE -eq 1 ]; then
    truncateLastByte tmp.gz | $ZSTD -t > $INTOVOID && die "incomplete frame not detected !"
    rm tmp*
 else
-    $ECHO "gzip mode not supported"
+    println "gzip mode not supported"
 fi

 if [ $GZIPMODE -eq 1 ]; then
@@ -615,16 +652,16 @@ if [ $GZIPMODE -eq 1 ]; then
    test -f tmp.zst
 fi

-$ECHO "\n===>  xz compatibility tests "
+println "\n===>  xz compatibility tests "

 LZMAMODE=1
 $ZSTD --format=xz -V || LZMAMODE=0
 if [ $LZMAMODE -eq 1 ]; then
-    $ECHO "xz support detected"
+    println "xz support detected"
    XZEXE=1
    xz -Q -V && lzma -Q -V || XZEXE=0
    if [ $XZEXE -eq 1 ]; then
-        $ECHO "Testing zstd xz and lzma support"
+        println "Testing zstd xz and lzma support"
        ./datagen > tmp
        $ZSTD --format=lzma -f tmp
        $ZSTD --format=xz -f tmp
@@ -635,18 +672,18 @@ if [ $LZMAMODE -eq 1 ]; then
        $ZSTD -d -f -v tmp.xz
        $ZSTD -d -f -v tmp.lzma
        rm tmp*
-        $ECHO "Creating symlinks"
+        println "Creating symlinks"
        ln -s $ZSTD ./xz
        ln -s $ZSTD ./unxz
        ln -s $ZSTD ./lzma
        ln -s $ZSTD ./unlzma
-        $ECHO "Testing xz and lzma symlinks"
+        println "Testing xz and lzma symlinks"
        ./datagen > tmp
        ./xz tmp
        xz -Q -d tmp.xz
        ./lzma tmp
        lzma -Q -d tmp.lzma
-        $ECHO "Testing unxz and unlzma symlinks"
+        println "Testing unxz and unlzma symlinks"
        xz -Q tmp
        ./xz -d tmp.xz
        lzma -Q tmp
@@ -654,14 +691,14 @@ if [ $LZMAMODE -eq 1 ]; then
        rm xz unxz lzma unlzma
        rm tmp*
    else
-        $ECHO "xz binary not detected"
+        println "xz binary not detected"
    fi
 else
-    $ECHO "xz mode not supported"
+    println "xz mode not supported"
 fi


-$ECHO "\n===>  xz frame tests "
+println "\n===>  xz frame tests "

 if [ $LZMAMODE -eq 1 ]; then
    ./datagen > tmp
@@ -673,15 +710,15 @@ if [ $LZMAMODE -eq 1 ]; then
    truncateLastByte tmp.lzma | $ZSTD -t > $INTOVOID && die "incomplete frame not detected !"
    rm tmp*
 else
-    $ECHO "xz mode not supported"
+    println "xz mode not supported"
 fi

-$ECHO "\n===>  lz4 compatibility tests "
+println "\n===>  lz4 compatibility tests "

 LZ4MODE=1
 $ZSTD --format=lz4 -V || LZ4MODE=0
 if [ $LZ4MODE -eq 1 ]; then
-    $ECHO "lz4 support detected"
+    println "lz4 support detected"
    LZ4EXE=1
    lz4 -V || LZ4EXE=0
    if [ $LZ4EXE -eq 1 ]; then
@@ -692,14 +729,14 @@ if [ $LZ4MODE -eq 1 ]; then
        $ZSTD -d -f -v tmp.lz4
        rm tmp*
    else
-        $ECHO "lz4 binary not detected"
+        println "lz4 binary not detected"
    fi
 else
-    $ECHO "lz4 mode not supported"
+    println "lz4 mode not supported"
 fi


-$ECHO "\n===>  lz4 frame tests "
+println "\n===>  lz4 frame tests "

 if [ $LZ4MODE -eq 1 ]; then
    ./datagen > tmp
@@ -709,10 +746,10 @@ if [ $LZ4MODE -eq 1 ]; then
    truncateLastByte tmp.lz4 | $ZSTD -t > $INTOVOID && die "incomplete frame not detected !"
    rm tmp*
 else
-    $ECHO "lz4 mode not supported"
+    println "lz4 mode not supported"
 fi

-$ECHO "\n===> suffix list test"
+println "\n===> suffix list test"

 ! $ZSTD -d tmp.abc 2> tmplg

@@ -729,7 +766,7 @@ if [ $LZ4MODE -ne 1 ]; then
    grep ".lz4" tmplg > $INTOVOID && die "Unsupported suffix listed"
 fi

-$ECHO "\n===>  zstd round-trip tests "
+println "\n===>  zstd round-trip tests "

 roundTripTest
 roundTripTest -g15K       # TableID==3
@@ -742,7 +779,7 @@ roundTripTest -g516K 19   # btopt

 fileRoundTripTest -g500K

-$ECHO "\n===>  zstd long distance matching round-trip tests "
+println "\n===>  zstd long distance matching round-trip tests "
 roundTripTest -g0 "2 --single-thread --long"
 roundTripTest -g1000K "1 --single-thread --long"
 roundTripTest -g517K "6 --single-thread --long"
@@ -754,62 +791,75 @@ fileRoundTripTest -g5M "3 --single-thread --long"
 roundTripTest -g96K "5 --single-thread"
 if [ -n "$hasMT" ]
 then
-    $ECHO "\n===>  zstdmt round-trip tests "
+    println "\n===>  zstdmt round-trip tests "
    roundTripTest -g4M "1 -T0"
    roundTripTest -g8M "3 -T2"
    roundTripTest -g8000K "2 --threads=2"
    fileRoundTripTest -g4M "19 -T2 -B1M"

-    $ECHO "\n===>  zstdmt long distance matching round-trip tests "
+    println "\n===>  zstdmt long distance matching round-trip tests "
    roundTripTest -g8M "3 --long=24 -T2"

-    $ECHO "\n===>  ovLog tests "
+    println "\n===>  ovLog tests "
    ./datagen -g2MB > tmp
    refSize=$($ZSTD tmp -6 -c --zstd=wlog=18         | wc -c)
    ov9Size=$($ZSTD tmp -6 -c --zstd=wlog=18,ovlog=9 | wc -c)
    ov1Size=$($ZSTD tmp -6 -c --zstd=wlog=18,ovlog=1 | wc -c)
-    if [ $refSize -eq $ov9Size ]; then
+    if [ "$refSize" -eq "$ov9Size" ]; then
        echo ov9Size should be different from refSize
        exit 1
    fi
-    if [ $refSize -eq $ov1Size ]; then
+    if [ "$refSize" -eq "$ov1Size" ]; then
        echo ov1Size should be different from refSize
        exit 1
    fi
-    if [ $ov9Size -ge $ov1Size ]; then
-        echo ov9Size=$ov9Size should be smaller than ov1Size=$ov1Size
+    if [ "$ov9Size" -ge "$ov1Size" ]; then
+        echo ov9Size="$ov9Size" should be smaller than ov1Size="$ov1Size"
        exit 1
    fi

 else
-    $ECHO "\n===>  no multithreading, skipping zstdmt tests "
+    println "\n===>  no multithreading, skipping zstdmt tests "
 fi

 rm tmp*

-$ECHO "\n===>  zstd --list/-l single frame tests "
+println "\n===>  zstd --list/-l single frame tests "
 ./datagen > tmp1
 ./datagen > tmp2
 ./datagen > tmp3
 $ZSTD tmp*
-$ZSTD -l *.zst
-$ZSTD -lv *.zst | grep "Decompressed Size:"  # check that decompressed size is present in header
-$ZSTD --list *.zst
-$ZSTD --list -v *.zst
+$ZSTD -l ./*.zst
+$ZSTD -lv ./*.zst | grep "Decompressed Size:"  # check that decompressed size is present in header
+$ZSTD --list ./*.zst
+$ZSTD --list -v ./*.zst

-$ECHO "\n===>  zstd --list/-l multiple frame tests "
+println "\n===>  zstd --list/-l multiple frame tests "
 cat tmp1.zst tmp2.zst > tmp12.zst
 cat tmp12.zst tmp3.zst > tmp123.zst
-$ZSTD -l *.zst
-$ZSTD -lv *.zst
+$ZSTD -l ./*.zst
+$ZSTD -lv ./*.zst

-$ECHO "\n===>  zstd --list/-l error detection tests "
+println "\n===>  zstd --list/-l error detection tests "
 $ZSTD -l tmp1 tmp1.zst && die "-l must fail on non-zstd file"
 $ZSTD --list tmp* && die "-l must fail on non-zstd file"
 $ZSTD -lv tmp1* && die "-l must fail on non-zstd file"
 $ZSTD --list -v tmp2 tmp12.zst && die "-l must fail on non-zstd file"

-$ECHO "\n===>  zstd --list/-l errors when presented with stdin / no files"
+println "test : detect truncated compressed file "
+TEST_DATA_FILE=truncatable-input.txt
+FULL_COMPRESSED_FILE=${TEST_DATA_FILE}.zst
+TRUNCATED_COMPRESSED_FILE=truncated-input.txt.zst
+./datagen -g50000 > $TEST_DATA_FILE
+$ZSTD -f $TEST_DATA_FILE -o $FULL_COMPRESSED_FILE
+dd bs=1 count=100 if=$FULL_COMPRESSED_FILE of=$TRUNCATED_COMPRESSED_FILE
+$ZSTD --list $TRUNCATED_COMPRESSED_FILE && die "-l must fail on truncated file"
+
+rm $TEST_DATA_FILE
+rm $FULL_COMPRESSED_FILE
+rm $TRUNCATED_COMPRESSED_FILE
+
+println "\n===>  zstd --list/-l errors when presented with stdin / no files"
 $ZSTD -l && die "-l must fail on empty list of files"
 $ZSTD -l - && die "-l does not work on stdin"
 $ZSTD -l < tmp1.zst && die "-l does not work on stdin"
@@ -818,7 +868,7 @@ $ZSTD -l - tmp1.zst && die "-l does not work on stdin"
 $ZSTD -l - tmp1.zst < tmp1.zst && die "-l does not work on stdin"
 $ZSTD -l tmp1.zst < tmp2.zst # this will check tmp1.zst, but not tmp2.zst, which is not an error : zstd simply doesn't read stdin in this case. It must not error just because stdin is not a tty

-$ECHO "\n===>  zstd --list/-l test with null files "
+println "\n===>  zstd --list/-l test with null files "
 ./datagen -g0 > tmp5
 $ZSTD tmp5
 $ZSTD -l tmp5.zst
@@ -826,12 +876,12 @@ $ZSTD -l tmp5* && die "-l must fail on non-zstd file"
 $ZSTD -lv tmp5.zst | grep "Decompressed Size: 0.00 KB (0 B)"  # check that 0 size is present in header
 $ZSTD -lv tmp5* && die "-l must fail on non-zstd file"

-$ECHO "\n===>  zstd --list/-l test with no content size field "
+println "\n===>  zstd --list/-l test with no content size field "
 ./datagen -g513K | $ZSTD > tmp6.zst
 $ZSTD -l tmp6.zst
 $ZSTD -lv tmp6.zst | grep "Decompressed Size:"  && die "Field :Decompressed Size: should not be available in this compressed file"

-$ECHO "\n===>   zstd --list/-l test with no checksum "
+println "\n===>   zstd --list/-l test with no checksum "
 $ZSTD -f --no-check tmp1
 $ZSTD -l tmp1.zst
 $ZSTD -lv tmp1.zst
@@ -839,7 +889,7 @@ $ZSTD -lv tmp1.zst
 rm tmp*


-$ECHO "\n===>   zstd long distance matching tests "
+println "\n===>   zstd long distance matching tests "
 roundTripTest -g0 " --single-thread --long"
 roundTripTest -g9M "2 --single-thread --long"
 # Test parameter parsing
@@ -849,29 +899,32 @@ roundTripTest -g1M -P50 "1 --single-thread --long=29" " --long=28 --memory=512MB
 roundTripTest -g1M -P50 "1 --single-thread --long=29" " --zstd=wlog=28 --memory=512MB"


-$ECHO "\n===>   adaptive mode "
-roundTripTest -g270000000 " --adapt"
-roundTripTest -g27000000 " --adapt=min=1,max=4"
-$ECHO "===>   test: --adapt must fail on incoherent bounds "
-./datagen > tmp
-$ZSTD -f -vv --adapt=min=10,max=9 tmp && die "--adapt must fail on incoherent bounds"
+if [ -n "$hasMT" ]
+then
+    println "\n===>   adaptive mode "
+    roundTripTest -g270000000 " --adapt"
+    roundTripTest -g27000000 " --adapt=min=1,max=4"
+    println "===>   test: --adapt must fail on incoherent bounds "
+    ./datagen > tmp
+    $ZSTD -f -vv --adapt=min=10,max=9 tmp && die "--adapt must fail on incoherent bounds"

-$ECHO "\n===>   rsyncable mode "
-roundTripTest -g10M " --rsyncable"
-roundTripTest -g10M " --rsyncable -B100K"
-$ECHO "===>   test: --rsyncable must fail with --single-thread"
-$ZSTD -f -vv --rsyncable --single-thread tmp && die "--rsyncable must fail with --single-thread"
+    println "\n===>   rsyncable mode "
+    roundTripTest -g10M " --rsyncable"
+    roundTripTest -g10M " --rsyncable -B100K"
+    println "===>   test: --rsyncable must fail with --single-thread"
+    $ZSTD -f -vv --rsyncable --single-thread tmp && die "--rsyncable must fail with --single-thread"
+fi


 if [ "$1" != "--test-large-data" ]; then
-    $ECHO "Skipping large data tests"
+    println "Skipping large data tests"
    exit 0
 fi


 #############################################################################

-$ECHO "\n===>   large files tests "
+println "\n===>   large files tests "

 roundTripTest -g270000000 1
 roundTripTest -g250000000 2
@@ -903,7 +956,7 @@ roundTripTest -g1700000000 -P0 "1 --zstd=strategy=6"   # ensure btlazy2 can surv
 fileRoundTripTest -g4193M -P99 1


-$ECHO "\n===>   zstd long, long distance matching round-trip tests "
+println "\n===>   zstd long, long distance matching round-trip tests "
 roundTripTest -g270000000 "1 --single-thread --long"
 roundTripTest -g130000000 -P60 "5 --single-thread --long"
 roundTripTest -g35000000 -P70 "8 --single-thread --long"
@@ -915,45 +968,54 @@ roundTripTest -g600M -P50 "1 --single-thread --long --zstd=wlog=29,clog=28"

 if [ -n "$hasMT" ]
 then
-    $ECHO "\n===>   zstdmt long round-trip tests "
+    println "\n===>   zstdmt long round-trip tests "
    roundTripTest -g80000000 -P99 "19 -T2" " "
    roundTripTest -g5000000000 -P99 "1 -T2" " "
    roundTripTest -g500000000 -P97 "1 -T999" " "
    fileRoundTripTest -g4103M -P98 " -T0" " "
    roundTripTest -g400000000 -P97 "1 --long=24 -T2" " "
+    # Exposes the bug in https://github.com/facebook/zstd/pull/1678
+    # This test fails on 4 different travis builds at the time of writing
+    # because it needs to allocate 8 GB of memory.
+    # roundTripTest -g10G -P99 "1 -T1 --long=31 --zstd=clog=27 --fast=1000"
 else
-    $ECHO "\n**** no multithreading, skipping zstdmt tests **** "
+    println "\n**** no multithreading, skipping zstdmt tests **** "
 fi


-$ECHO "\n===>  cover dictionary builder : advanced options "
+println "\n===>  cover dictionary builder : advanced options "

-TESTFILE=../programs/zstdcli.c
+TESTFILE="$PRGDIR"/zstdcli.c
 ./datagen > tmpDict
-$ECHO "- Create first dictionary"
-$ZSTD --train-cover=k=46,d=8,split=80 *.c ../programs/*.c -o tmpDict
-cp $TESTFILE tmp
+println "- Create first dictionary"
+$ZSTD --train-cover=k=46,d=8,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict
+cp "$TESTFILE" tmp
 $ZSTD -f tmp -D tmpDict
 $ZSTD -d tmp.zst -D tmpDict -fo result
-$DIFF $TESTFILE result
-$ECHO "- Create second (different) dictionary"
-$ZSTD --train-cover=k=56,d=8 *.c ../programs/*.c ../programs/*.h -o tmpDictC
+$DIFF "$TESTFILE" result
+$ZSTD --train-cover=k=56,d=8 && die "Create dictionary without input file (should error)"
+println "- Create second (different) dictionary"
+$ZSTD --train-cover=k=56,d=8 "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
 $ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
-$ECHO "- Create dictionary with short dictID"
-$ZSTD --train-cover=k=46,d=8,split=80 *.c ../programs/*.c --dictID=1 -o tmpDict1
+println "- Create dictionary using shrink-dict flag"
+$ZSTD --train-cover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict
+$ZSTD --train-cover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict1
+$ZSTD --train-cover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict2
+println "- Create dictionary with short dictID"
+$ZSTD --train-cover=k=46,d=8,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
 cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
-$ECHO "- Create dictionary with size limit"
-$ZSTD --train-cover=steps=8 *.c ../programs/*.c -o tmpDict2 --maxdict=4K
-$ECHO "- Compare size of dictionary from 90% training samples with 80% training samples"
-$ZSTD --train-cover=split=90 -r *.c ../programs/*.c
-$ZSTD --train-cover=split=80 -r *.c ../programs/*.c
-$ECHO "- Create dictionary using all samples for both training and testing"
-$ZSTD --train-cover=split=100 -r *.c ../programs/*.c
-$ECHO "- Test -o before --train-cover"
+println "- Create dictionary with size limit"
+$ZSTD --train-cover=steps=8 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K
+println "- Compare size of dictionary from 90% training samples with 80% training samples"
+$ZSTD --train-cover=split=90 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+$ZSTD --train-cover=split=80 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Create dictionary using all samples for both training and testing"
+$ZSTD --train-cover=split=100 -r "$TESTDIR"/*.c "$PRGDIR"/*.c
+println "- Test -o before --train-cover"
 rm -f tmpDict dictionary
-$ZSTD -o tmpDict --train-cover *.c ../programs/*.c
+$ZSTD -o tmpDict --train-cover "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f tmpDict
-$ZSTD --train-cover *.c ../programs/*.c
+$ZSTD --train-cover "$TESTDIR"/*.c "$PRGDIR"/*.c
 test -f dictionary
 rm -f tmp* dictionary

@@ -12,6 +12,7 @@
 #include "pool.h"
 #include "threading.h"
 #include "util.h"
+#include "timefn.h"
 #include <stddef.h>
 #include <stdio.h>

@@ -25,25 +26,27 @@
 #define ASSERT_EQ(lhs, rhs) ASSERT_TRUE((lhs) == (rhs))

 struct data {
-  pthread_mutex_t mutex;
+  ZSTD_pthread_mutex_t mutex;
  unsigned data[16];
  size_t i;
 };

-static void fn(void *opaque) {
+static void fn(void *opaque)
+{
  struct data *data = (struct data *)opaque;
  ZSTD_pthread_mutex_lock(&data->mutex);
-  data->data[data->i] = data->i;
+  data->data[data->i] = (unsigned)(data->i);
  ++data->i;
  ZSTD_pthread_mutex_unlock(&data->mutex);
 }

-static int testOrder(size_t numThreads, size_t queueSize) {
+static int testOrder(size_t numThreads, size_t queueSize)
+{
  struct data data;
-  POOL_ctx *ctx = POOL_create(numThreads, queueSize);
+  POOL_ctx* const ctx = POOL_create(numThreads, queueSize);
  ASSERT_TRUE(ctx);
  data.i = 0;
-  ZSTD_pthread_mutex_init(&data.mutex, NULL);
+  (void)ZSTD_pthread_mutex_init(&data.mutex, NULL);
  { size_t i;
    for (i = 0; i < 16; ++i) {
      POOL_add(ctx, &fn, &data);
@@ -71,7 +74,7 @@ static void waitFn(void *opaque) {
 /* Tests for deadlock */
 static int testWait(size_t numThreads, size_t queueSize) {
  struct data data;
-  POOL_ctx *ctx = POOL_create(numThreads, queueSize);
+  POOL_ctx* const ctx = POOL_create(numThreads, queueSize);
  ASSERT_TRUE(ctx);
  { size_t i;
    for (i = 0; i < 16; ++i) {
@@ -87,55 +90,64 @@ static int testWait(size_t numThreads, size_t queueSize) {

 typedef struct {
    ZSTD_pthread_mutex_t mut;
+    int countdown;
    int val;
    int max;
    ZSTD_pthread_cond_t cond;
 } poolTest_t;

 static void waitLongFn(void *opaque) {
-  poolTest_t* test = (poolTest_t*) opaque;
-  UTIL_sleepMilli(10);
+  poolTest_t* const test = (poolTest_t*) opaque;
  ZSTD_pthread_mutex_lock(&test->mut);
-  test->val = test->val + 1;
-  if (test->val == test->max)
-    ZSTD_pthread_cond_signal(&test->cond);
+  test->val++;
+  if (test->val > test->max)
+      test->max = test->val;
+  ZSTD_pthread_mutex_unlock(&test->mut);
+
+  UTIL_sleepMilli(10);
+
+  ZSTD_pthread_mutex_lock(&test->mut);
+  test->val--;
+  test->countdown--;
+  if (test->countdown == 0)
+      ZSTD_pthread_cond_signal(&test->cond);
  ZSTD_pthread_mutex_unlock(&test->mut);
 }

 static int testThreadReduction_internal(POOL_ctx* ctx, poolTest_t test)
 {
    int const nbWaits = 16;
-    UTIL_time_t startTime;
-    U64 time4threads, time2threads;

+    test.countdown = nbWaits;
    test.val = 0;
-    test.max = nbWaits;
+    test.max = 0;

-    startTime = UTIL_getTime();
    {   int i;
        for (i=0; i<nbWaits; i++)
            POOL_add(ctx, &waitLongFn, &test);
    }
    ZSTD_pthread_mutex_lock(&test.mut);
-    ZSTD_pthread_cond_wait(&test.cond, &test.mut);
-    ASSERT_EQ(test.val, nbWaits);
+    while (test.countdown > 0)
+        ZSTD_pthread_cond_wait(&test.cond, &test.mut);
+    ASSERT_EQ(test.val, 0);
+    ASSERT_EQ(test.max, 4);
    ZSTD_pthread_mutex_unlock(&test.mut);
-    time4threads = UTIL_clockSpanNano(startTime);

    ASSERT_EQ( POOL_resize(ctx, 2/*nbThreads*/) , 0 );
+    test.countdown = nbWaits;
    test.val = 0;
-    startTime = UTIL_getTime();
+    test.max = 0;
    {   int i;
        for (i=0; i<nbWaits; i++)
            POOL_add(ctx, &waitLongFn, &test);
    }
    ZSTD_pthread_mutex_lock(&test.mut);
-    ZSTD_pthread_cond_wait(&test.cond, &test.mut);
-    ASSERT_EQ(test.val, nbWaits);
+    while (test.countdown > 0)
+        ZSTD_pthread_cond_wait(&test.cond, &test.mut);
+    ASSERT_EQ(test.val, 0);
+    ASSERT_EQ(test.max, 2);
    ZSTD_pthread_mutex_unlock(&test.mut);
-    time2threads = UTIL_clockSpanNano(startTime);

-    if (time4threads >= time2threads) return 1;   /* check 4 threads were effectively faster than 2 */
    return 0;
 }

@@ -243,7 +255,7 @@ int main(int argc, const char **argv) {
      printf("FAIL: thread reduction not effective \n");
      return 1;
  } else {
-      printf("SUCCESS: thread reduction effective (slower execution) \n");
+      printf("SUCCESS: thread reduction effective \n");
  }

  if (testAbruptEnding()) {
@@ -90,6 +90,17 @@ static config_t mt_ldm = {
    .param_values = PARAM_VALUES(mt_ldm_param_values),
 };

+static param_value_t mt_advanced_param_values[] = {
+    {.param = ZSTD_c_nbWorkers, .value = 2},
+    {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
+};
+
+static config_t mt_advanced = {
+    .name = "multithreaded with advanced params",
+    .cli_args = "-T2 --no-compress-literals",
+    .param_values = PARAM_VALUES(mt_advanced_param_values),
+};
+
 static param_value_t const small_wlog_param_values[] = {
    {.param = ZSTD_c_windowLog, .value = 10},
 };
@@ -122,6 +133,39 @@ static config_t small_clog = {
    .param_values = PARAM_VALUES(small_clog_param_values),
 };

+static param_value_t const uncompressed_literals_param_values[] = {
+    {.param = ZSTD_c_compressionLevel, .value = 3},
+    {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
+};
+
+static config_t uncompressed_literals = {
+    .name = "uncompressed literals",
+    .cli_args = "-3 --no-compress-literals",
+    .param_values = PARAM_VALUES(uncompressed_literals_param_values),
+};
+
+static param_value_t const uncompressed_literals_opt_param_values[] = {
+    {.param = ZSTD_c_compressionLevel, .value = 19},
+    {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
+};
+
+static config_t uncompressed_literals_opt = {
+    .name = "uncompressed literals optimal",
+    .cli_args = "-19 --no-compress-literals",
+    .param_values = PARAM_VALUES(uncompressed_literals_opt_param_values),
+};
+
+static param_value_t const huffman_literals_param_values[] = {
+    {.param = ZSTD_c_compressionLevel, .value = -1},
+    {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_huffman},
+};
+
+static config_t huffman_literals = {
+    .name = "huffman literals",
+    .cli_args = "--fast=1 --compress-literals",
+    .param_values = PARAM_VALUES(huffman_literals_param_values),
+};
+
 static param_value_t const explicit_params_param_values[] = {
    {.param = ZSTD_c_checksumFlag, .value = 1},
    {.param = ZSTD_c_contentSizeFlag, .value = 0},
@@ -155,6 +199,10 @@ static config_t const* g_configs[] = {
    &small_hlog,
    &small_clog,
    &explicit_params,
+    &uncompressed_literals,
+    &uncompressed_literals_opt,
+    &huffman_literals,
+    &mt_advanced,
    NULL,
 };

@@ -175,8 +175,8 @@ static result_t compress_cctx_compress(
                state->compressed.capacity,
                input.data,
                input.size,
-                state->dictionary.data,
-                state->dictionary.size,
+                config->use_dictionary ? state->dictionary.data : NULL,
+                config->use_dictionary ? state->dictionary.size : 0,
                params);
        else if (config->use_dictionary)
            state->compressed.size = ZSTD_compress_usingDict(
@@ -432,77 +432,158 @@ out:
    return result;
 }

-static result_t old_streaming_compress(
-    method_state_t* base,
-    config_t const* config) {
-    buffer_state_t* state = container_of(base, buffer_state_t, base);
-
-    if (buffer_state_bad(state, config))
-        return result_error(result_error_system_error);
-
-    int const level = config_get_level(config);
-    if (level == CONFIG_NO_LEVEL)
-        return result_error(result_error_skip);
-
-    ZSTD_CStream* zcs = ZSTD_createCStream();
-    result_t result;
-    if (zcs == NULL) {
-        result = result_error(result_error_compression_error);
-        goto out;
-    }
+static int init_cstream(
+    buffer_state_t* state,
+    ZSTD_CStream* zcs,
+    config_t const* config,
+    int const advanced,
+    ZSTD_CDict** cdict)
+{
    size_t zret;
-    if (config->use_dictionary) {
-        zret = ZSTD_initCStream_usingDict(
-            zcs, state->dictionary.data, state->dictionary.size, level);
+    if (advanced) {
+        ZSTD_parameters const params = config_get_zstd_params(config, 0, 0);
+        ZSTD_CDict* dict = NULL;
+        if (cdict) {
+            *cdict = ZSTD_createCDict_advanced(
+                state->dictionary.data,
+                state->dictionary.size,
+                ZSTD_dlm_byRef,
+                ZSTD_dct_auto,
+                params.cParams,
+                ZSTD_defaultCMem);
+            if (!*cdict) {
+                return 1;
+            }
+            zret = ZSTD_initCStream_usingCDict_advanced(
+                zcs, *cdict, params.fParams, ZSTD_CONTENTSIZE_UNKNOWN);
+        } else {
+            zret = ZSTD_initCStream_advanced(
+                zcs,
+                state->dictionary.data,
+                state->dictionary.size,
+                params,
+                ZSTD_CONTENTSIZE_UNKNOWN);
+        }
    } else {
-        zret = ZSTD_initCStream(zcs, level);
+        int const level = config_get_level(config);
+        if (cdict) {
+            *cdict = ZSTD_createCDict(
+                state->dictionary.data,
+                state->dictionary.size,
+                level);
+            if (!*cdict) {
+                return 1;
+            }
+            zret = ZSTD_initCStream_usingCDict(zcs, *cdict);
+        } else if (config->use_dictionary) {
+            zret = ZSTD_initCStream_usingDict(
+                zcs, state->dictionary.data, state->dictionary.size, level);
+        } else {
+            zret = ZSTD_initCStream(zcs, level);
+        }
    }
    if (ZSTD_isError(zret)) {
-        result = result_error(result_error_compression_error);
-        goto out;
+        return 1;
+    }
+    return 0;
+}
+
+static result_t old_streaming_compress_internal(
+    method_state_t* base,
+    config_t const* config,
+    int const advanced,
+    int const cdict) {
+  buffer_state_t* state = container_of(base, buffer_state_t, base);
+
+  if (buffer_state_bad(state, config))
+    return result_error(result_error_system_error);
+
+
+  ZSTD_CStream* zcs = ZSTD_createCStream();
+  ZSTD_CDict* cd = NULL;
+  result_t result;
+  if (zcs == NULL) {
+    result = result_error(result_error_compression_error);
+    goto out;
+  }
+  if (init_cstream(state, zcs, config, advanced, cdict ? &cd : NULL)) {
+      result = result_error(result_error_compression_error);
+      goto out;
+  }
+
+  result_data_t data = {.total_size = 0};
+  for (size_t i = 0; i < state->inputs.size; ++i) {
+    data_buffer_t input = state->inputs.buffers[i];
+    size_t zret = ZSTD_resetCStream(
+        zcs,
+        config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN : input.size);
+    if (ZSTD_isError(zret)) {
+      result = result_error(result_error_compression_error);
+      goto out;
    }

-    result_data_t data = {.total_size = 0};
-    for (size_t i = 0; i < state->inputs.size; ++i) {
-        data_buffer_t input = state->inputs.buffers[i];
-        zret = ZSTD_resetCStream(
-            zcs,
-            config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN
-                                        : input.size);
+    while (input.size > 0) {
+      ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)};
+      input.data += in.size;
+      input.size -= in.size;
+      ZSTD_EndDirective const op =
+          input.size > 0 ? ZSTD_e_continue : ZSTD_e_end;
+      zret = 0;
+      while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) {
+        ZSTD_outBuffer out = {state->compressed.data,
+                              MIN(state->compressed.capacity, 1024)};
+        if (op == ZSTD_e_continue || in.pos < in.size)
+          zret = ZSTD_compressStream(zcs, &out, &in);
+        else
+          zret = ZSTD_endStream(zcs, &out);
        if (ZSTD_isError(zret)) {
-            result = result_error(result_error_compression_error);
-            goto out;
-        }
-
-        while (input.size > 0) {
-            ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)};
-            input.data += in.size;
-            input.size -= in.size;
-            ZSTD_EndDirective const op =
-                input.size > 0 ? ZSTD_e_continue : ZSTD_e_end;
-            zret = 0;
-            while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) {
-                ZSTD_outBuffer out = {state->compressed.data,
-                                      MIN(state->compressed.capacity, 1024)};
-                if (op == ZSTD_e_continue || in.pos < in.size)
-                    zret = ZSTD_compressStream(zcs, &out, &in);
-                else
-                    zret = ZSTD_endStream(zcs, &out);
-                if (ZSTD_isError(zret)) {
-                    result = result_error(result_error_compression_error);
-                    goto out;
-                }
-                data.total_size += out.pos;
-            }
+          result = result_error(result_error_compression_error);
+          goto out;
        }
+        data.total_size += out.pos;
+      }
    }
+  }

-    result = result_data(data);
+  result = result_data(data);
 out:
    ZSTD_freeCStream(zcs);
+    ZSTD_freeCDict(cd);
    return result;
 }

+static result_t old_streaming_compress(
+    method_state_t* base,
+    config_t const* config)
+{
+    return old_streaming_compress_internal(
+        base, config, /* advanced */ 0, /* cdict */ 0);
+}
+
+static result_t old_streaming_compress_advanced(
+    method_state_t* base,
+    config_t const* config)
+{
+    return old_streaming_compress_internal(
+        base, config, /* advanced */ 1, /* cdict */ 0);
+}
+
+static result_t old_streaming_compress_cdict(
+    method_state_t* base,
+    config_t const* config)
+{
+    return old_streaming_compress_internal(
+        base, config, /* advanced */ 0, /* cdict */ 1);
+}
+
+static result_t old_streaming_compress_cdict_advanced(
+    method_state_t* base,
+    config_t const* config)
+{
+    return old_streaming_compress_internal(
+        base, config, /* advanced */ 1, /* cdict */ 1);
+}
+
 method_t const simple = {
    .name = "compress simple",
    .create = buffer_state_create,
@@ -545,6 +626,27 @@ method_t const old_streaming = {
    .destroy = buffer_state_destroy,
 };

+method_t const old_streaming_advanced = {
+    .name = "old streaming advanced",
+    .create = buffer_state_create,
+    .compress = old_streaming_compress,
+    .destroy = buffer_state_destroy,
+};
+
+method_t const old_streaming_cdict = {
+    .name = "old streaming cdcit",
+    .create = buffer_state_create,
+    .compress = old_streaming_compress,
+    .destroy = buffer_state_destroy,
+};
+
+method_t const old_streaming_advanced_cdict = {
+    .name = "old streaming advanced cdict",
+    .create = buffer_state_create,
+    .compress = old_streaming_compress,
+    .destroy = buffer_state_destroy,
+};
+
 method_t const cli = {
    .name = "zstdcli",
    .create = method_state_create,
@@ -560,6 +662,9 @@ static method_t const* g_methods[] = {
    &advanced_one_pass_small_out,
    &advanced_streaming,
    &old_streaming,
+    &old_streaming_advanced,
+    &old_streaming_cdict,
+    &old_streaming_advanced_cdict,
    NULL,
 };

@@ -1,448 +1,816 @@
-Data,                             Config,                           Method,                           Total compressed size
-silesia.tar,                      level -5,                         compress simple,                  7160438
-silesia.tar,                      level -3,                         compress simple,                  6789024
-silesia.tar,                      level -1,                         compress simple,                  6195462
-silesia.tar,                      level 0,                          compress simple,                  4875008
-silesia.tar,                      level 1,                          compress simple,                  5339697
-silesia.tar,                      level 3,                          compress simple,                  4875008
-silesia.tar,                      level 4,                          compress simple,                  4813507
-silesia.tar,                      level 5,                          compress simple,                  4722235
-silesia.tar,                      level 6,                          compress simple,                  4672194
-silesia.tar,                      level 7,                          compress simple,                  4606658
-silesia.tar,                      level 9,                          compress simple,                  4554098
-silesia.tar,                      level 13,                         compress simple,                  4491702
-silesia.tar,                      level 16,                         compress simple,                  4381277
-silesia.tar,                      level 19,                         compress simple,                  4281514
-silesia,                          level -5,                         compress cctx,                    7152294
-silesia,                          level -3,                         compress cctx,                    6789969
-silesia,                          level -1,                         compress cctx,                    6191548
-silesia,                          level 0,                          compress cctx,                    4862377
-silesia,                          level 1,                          compress cctx,                    5318036
-silesia,                          level 3,                          compress cctx,                    4862377
-silesia,                          level 4,                          compress cctx,                    4800629
-silesia,                          level 5,                          compress cctx,                    4710178
-silesia,                          level 6,                          compress cctx,                    4659996
-silesia,                          level 7,                          compress cctx,                    4596234
-silesia,                          level 9,                          compress cctx,                    4543862
-silesia,                          level 13,                         compress cctx,                    4482073
-silesia,                          level 16,                         compress cctx,                    4377391
-silesia,                          level 19,                         compress cctx,                    4293262
-silesia,                          long distance mode,               compress cctx,                    4862377
-silesia,                          multithreaded,                    compress cctx,                    4862377
-silesia,                          multithreaded long distance mode, compress cctx,                    4862377
-silesia,                          small window log,                 compress cctx,                    7115734
-silesia,                          small hash log,                   compress cctx,                    6554898
-silesia,                          small chain log,                  compress cctx,                    4931093
-silesia,                          explicit params,                  compress cctx,                    4813352
-github,                           level -5,                         compress cctx,                    232744
-github,                           level -5 with dict,               compress cctx,                    47294
-github,                           level -3,                         compress cctx,                    220611
-github,                           level -3 with dict,               compress cctx,                    48047
-github,                           level -1,                         compress cctx,                    176575
-github,                           level -1 with dict,               compress cctx,                    43527
-github,                           level 0,                          compress cctx,                    136397
-github,                           level 0 with dict,                compress cctx,                    41536
-github,                           level 1,                          compress cctx,                    143457
-github,                           level 1 with dict,                compress cctx,                    42157
-github,                           level 3,                          compress cctx,                    136397
-github,                           level 3 with dict,                compress cctx,                    41536
-github,                           level 4,                          compress cctx,                    136144
-github,                           level 4 with dict,                compress cctx,                    41721
-github,                           level 5,                          compress cctx,                    135106
-github,                           level 5 with dict,                compress cctx,                    38934
-github,                           level 6,                          compress cctx,                    135108
-github,                           level 6 with dict,                compress cctx,                    38628
-github,                           level 7,                          compress cctx,                    135108
-github,                           level 7 with dict,                compress cctx,                    38741
-github,                           level 9,                          compress cctx,                    135108
-github,                           level 9 with dict,                compress cctx,                    39335
-github,                           level 13,                         compress cctx,                    133717
-github,                           level 13 with dict,               compress cctx,                    39923
-github,                           level 16,                         compress cctx,                    133717
-github,                           level 16 with dict,               compress cctx,                    37568
-github,                           level 19,                         compress cctx,                    133717
-github,                           level 19 with dict,               compress cctx,                    37567
-github,                           long distance mode,               compress cctx,                    decompression error
-github,                           multithreaded,                    compress cctx,                    decompression error
-github,                           multithreaded long distance mode, compress cctx,                    decompression error
-github,                           small window log,                 compress cctx,                    decompression error
-github,                           small hash log,                   compress cctx,                    decompression error
-github,                           small chain log,                  compress cctx,                    decompression error
-github,                           explicit params,                  compress cctx,                    decompression error
-silesia,                          level -5,                         zstdcli,                          7152342
-silesia,                          level -3,                         zstdcli,                          6790021
-silesia,                          level -1,                         zstdcli,                          6191597
-silesia,                          level 0,                          zstdcli,                          4862425
-silesia,                          level 1,                          zstdcli,                          5318084
-silesia,                          level 3,                          zstdcli,                          4862425
-silesia,                          level 4,                          zstdcli,                          4800677
-silesia,                          level 5,                          zstdcli,                          4710226
-silesia,                          level 6,                          zstdcli,                          4660044
-silesia,                          level 7,                          zstdcli,                          4596282
-silesia,                          level 9,                          zstdcli,                          4543910
-silesia,                          level 13,                         zstdcli,                          4482121
-silesia,                          level 16,                         zstdcli,                          4377439
-silesia,                          level 19,                         zstdcli,                          4293310
-silesia,                          long distance mode,               zstdcli,                          4853437
-silesia,                          multithreaded,                    zstdcli,                          4862425
-silesia,                          multithreaded long distance mode, zstdcli,                          4853437
-silesia,                          small window log,                 zstdcli,                          7126434
-silesia,                          small hash log,                   zstdcli,                          6554946
-silesia,                          small chain log,                  zstdcli,                          4931141
-silesia,                          explicit params,                  zstdcli,                          4815380
-silesia.tar,                      level -5,                         zstdcli,                          7161160
-silesia.tar,                      level -3,                         zstdcli,                          6789865
-silesia.tar,                      level -1,                         zstdcli,                          6196433
-silesia.tar,                      level 0,                          zstdcli,                          4875136
-silesia.tar,                      level 1,                          zstdcli,                          5340573
-silesia.tar,                      level 3,                          zstdcli,                          4875136
-silesia.tar,                      level 4,                          zstdcli,                          4814531
-silesia.tar,                      level 5,                          zstdcli,                          4723284
-silesia.tar,                      level 6,                          zstdcli,                          4673591
-silesia.tar,                      level 7,                          zstdcli,                          4608342
-silesia.tar,                      level 9,                          zstdcli,                          4554700
-silesia.tar,                      level 13,                         zstdcli,                          4491706
-silesia.tar,                      level 16,                         zstdcli,                          4381281
-silesia.tar,                      level 19,                         zstdcli,                          4281518
-silesia.tar,                      no source size,                   zstdcli,                          4875132
-silesia.tar,                      long distance mode,               zstdcli,                          4866975
-silesia.tar,                      multithreaded,                    zstdcli,                          4875136
-silesia.tar,                      multithreaded long distance mode, zstdcli,                          4866975
-silesia.tar,                      small window log,                 zstdcli,                          7130434
-silesia.tar,                      small hash log,                   zstdcli,                          6587841
-silesia.tar,                      small chain log,                  zstdcli,                          4943259
-silesia.tar,                      explicit params,                  zstdcli,                          4839202
-github,                           level -5,                         zstdcli,                          234744
-github,                           level -5 with dict,               zstdcli,                          48718
-github,                           level -3,                         zstdcli,                          222611
-github,                           level -3 with dict,               zstdcli,                          47395
-github,                           level -1,                         zstdcli,                          178575
-github,                           level -1 with dict,               zstdcli,                          45170
-github,                           level 0,                          zstdcli,                          138397
-github,                           level 0 with dict,                zstdcli,                          43170
-github,                           level 1,                          zstdcli,                          145457
-github,                           level 1 with dict,                zstdcli,                          43682
-github,                           level 3,                          zstdcli,                          138397
-github,                           level 3 with dict,                zstdcli,                          43170
-github,                           level 4,                          zstdcli,                          138144
-github,                           level 4 with dict,                zstdcli,                          43306
-github,                           level 5,                          zstdcli,                          137106
-github,                           level 5 with dict,                zstdcli,                          40938
-github,                           level 6,                          zstdcli,                          137108
-github,                           level 6 with dict,                zstdcli,                          40632
-github,                           level 7,                          zstdcli,                          137108
-github,                           level 7 with dict,                zstdcli,                          40766
-github,                           level 9,                          zstdcli,                          137108
-github,                           level 9 with dict,                zstdcli,                          41326
-github,                           level 13,                         zstdcli,                          135717
-github,                           level 13 with dict,               zstdcli,                          41716
-github,                           level 16,                         zstdcli,                          135717
-github,                           level 16 with dict,               zstdcli,                          39577
-github,                           level 19,                         zstdcli,                          135717
-github,                           level 19 with dict,               zstdcli,                          39576
-github,                           long distance mode,               zstdcli,                          138397
-github,                           multithreaded,                    zstdcli,                          138397
-github,                           multithreaded long distance mode, zstdcli,                          138397
-github,                           small window log,                 zstdcli,                          138397
-github,                           small hash log,                   zstdcli,                          137467
-github,                           small chain log,                  zstdcli,                          138314
-github,                           explicit params,                  zstdcli,                          136140
-silesia,                          level -5,                         advanced one pass,                7152294
-silesia,                          level -3,                         advanced one pass,                6789969
-silesia,                          level -1,                         advanced one pass,                6191548
-silesia,                          level 0,                          advanced one pass,                4862377
-silesia,                          level 1,                          advanced one pass,                5318036
-silesia,                          level 3,                          advanced one pass,                4862377
-silesia,                          level 4,                          advanced one pass,                4800629
-silesia,                          level 5,                          advanced one pass,                4710178
-silesia,                          level 6,                          advanced one pass,                4659996
-silesia,                          level 7,                          advanced one pass,                4596234
-silesia,                          level 9,                          advanced one pass,                4543862
-silesia,                          level 13,                         advanced one pass,                4482073
-silesia,                          level 16,                         advanced one pass,                4377391
-silesia,                          level 19,                         advanced one pass,                4293262
-silesia,                          no source size,                   advanced one pass,                4862377
-silesia,                          long distance mode,               advanced one pass,                4853389
-silesia,                          multithreaded,                    advanced one pass,                4862377
-silesia,                          multithreaded long distance mode, advanced one pass,                4853389
-silesia,                          small window log,                 advanced one pass,                7126386
-silesia,                          small hash log,                   advanced one pass,                6554898
-silesia,                          small chain log,                  advanced one pass,                4931093
-silesia,                          explicit params,                  advanced one pass,                4815369
-silesia.tar,                      level -5,                         advanced one pass,                7160438
-silesia.tar,                      level -3,                         advanced one pass,                6789024
-silesia.tar,                      level -1,                         advanced one pass,                6195462
-silesia.tar,                      level 0,                          advanced one pass,                4875008
-silesia.tar,                      level 1,                          advanced one pass,                5339697
-silesia.tar,                      level 3,                          advanced one pass,                4875008
-silesia.tar,                      level 4,                          advanced one pass,                4813507
-silesia.tar,                      level 5,                          advanced one pass,                4722235
-silesia.tar,                      level 6,                          advanced one pass,                4672194
-silesia.tar,                      level 7,                          advanced one pass,                4606658
-silesia.tar,                      level 9,                          advanced one pass,                4554098
-silesia.tar,                      level 13,                         advanced one pass,                4491702
-silesia.tar,                      level 16,                         advanced one pass,                4381277
-silesia.tar,                      level 19,                         advanced one pass,                4281514
-silesia.tar,                      no source size,                   advanced one pass,                4875008
-silesia.tar,                      long distance mode,               advanced one pass,                4861218
-silesia.tar,                      multithreaded,                    advanced one pass,                4874631
-silesia.tar,                      multithreaded long distance mode, advanced one pass,                4860683
-silesia.tar,                      small window log,                 advanced one pass,                7130394
-silesia.tar,                      small hash log,                   advanced one pass,                6587833
-silesia.tar,                      small chain log,                  advanced one pass,                4943255
-silesia.tar,                      explicit params,                  advanced one pass,                4829974
-github,                           level -5,                         advanced one pass,                232744
-github,                           level -5 with dict,               advanced one pass,                46718
-github,                           level -3,                         advanced one pass,                220611
-github,                           level -3 with dict,               advanced one pass,                45395
-github,                           level -1,                         advanced one pass,                176575
-github,                           level -1 with dict,               advanced one pass,                43170
-github,                           level 0,                          advanced one pass,                136397
-github,                           level 0 with dict,                advanced one pass,                41170
-github,                           level 1,                          advanced one pass,                143457
-github,                           level 1 with dict,                advanced one pass,                41682
-github,                           level 3,                          advanced one pass,                136397
-github,                           level 3 with dict,                advanced one pass,                41170
-github,                           level 4,                          advanced one pass,                136144
-github,                           level 4 with dict,                advanced one pass,                41306
-github,                           level 5,                          advanced one pass,                135106
-github,                           level 5 with dict,                advanced one pass,                38938
-github,                           level 6,                          advanced one pass,                135108
-github,                           level 6 with dict,                advanced one pass,                38632
-github,                           level 7,                          advanced one pass,                135108
-github,                           level 7 with dict,                advanced one pass,                38766
-github,                           level 9,                          advanced one pass,                135108
-github,                           level 9 with dict,                advanced one pass,                39326
-github,                           level 13,                         advanced one pass,                133717
-github,                           level 13 with dict,               advanced one pass,                39716
-github,                           level 16,                         advanced one pass,                133717
-github,                           level 16 with dict,               advanced one pass,                37577
-github,                           level 19,                         advanced one pass,                133717
-github,                           level 19 with dict,               advanced one pass,                37576
-github,                           no source size,                   advanced one pass,                136397
-github,                           long distance mode,               advanced one pass,                136397
-github,                           multithreaded,                    advanced one pass,                136397
-github,                           multithreaded long distance mode, advanced one pass,                136397
-github,                           small window log,                 advanced one pass,                136397
-github,                           small hash log,                   advanced one pass,                135467
-github,                           small chain log,                  advanced one pass,                136314
-github,                           explicit params,                  advanced one pass,                137670
-silesia,                          level -5,                         advanced one pass small out,      7152294
-silesia,                          level -3,                         advanced one pass small out,      6789969
-silesia,                          level -1,                         advanced one pass small out,      6191548
-silesia,                          level 0,                          advanced one pass small out,      4862377
-silesia,                          level 1,                          advanced one pass small out,      5318036
-silesia,                          level 3,                          advanced one pass small out,      4862377
-silesia,                          level 4,                          advanced one pass small out,      4800629
-silesia,                          level 5,                          advanced one pass small out,      4710178
-silesia,                          level 6,                          advanced one pass small out,      4659996
-silesia,                          level 7,                          advanced one pass small out,      4596234
-silesia,                          level 9,                          advanced one pass small out,      4543862
-silesia,                          level 13,                         advanced one pass small out,      4482073
-silesia,                          level 16,                         advanced one pass small out,      4377391
-silesia,                          level 19,                         advanced one pass small out,      4293262
-silesia,                          no source size,                   advanced one pass small out,      4862377
-silesia,                          long distance mode,               advanced one pass small out,      4853389
-silesia,                          multithreaded,                    advanced one pass small out,      4862377
-silesia,                          multithreaded long distance mode, advanced one pass small out,      4853389
-silesia,                          small window log,                 advanced one pass small out,      7126386
-silesia,                          small hash log,                   advanced one pass small out,      6554898
-silesia,                          small chain log,                  advanced one pass small out,      4931093
-silesia,                          explicit params,                  advanced one pass small out,      4815369
-silesia.tar,                      level -5,                         advanced one pass small out,      7160438
-silesia.tar,                      level -3,                         advanced one pass small out,      6789024
-silesia.tar,                      level -1,                         advanced one pass small out,      6195462
-silesia.tar,                      level 0,                          advanced one pass small out,      4875008
-silesia.tar,                      level 1,                          advanced one pass small out,      5339697
-silesia.tar,                      level 3,                          advanced one pass small out,      4875008
-silesia.tar,                      level 4,                          advanced one pass small out,      4813507
-silesia.tar,                      level 5,                          advanced one pass small out,      4722235
-silesia.tar,                      level 6,                          advanced one pass small out,      4672194
-silesia.tar,                      level 7,                          advanced one pass small out,      4606658
-silesia.tar,                      level 9,                          advanced one pass small out,      4554098
-silesia.tar,                      level 13,                         advanced one pass small out,      4491702
-silesia.tar,                      level 16,                         advanced one pass small out,      4381277
-silesia.tar,                      level 19,                         advanced one pass small out,      4281514
-silesia.tar,                      no source size,                   advanced one pass small out,      4875008
-silesia.tar,                      long distance mode,               advanced one pass small out,      4861218
-silesia.tar,                      multithreaded,                    advanced one pass small out,      4874631
-silesia.tar,                      multithreaded long distance mode, advanced one pass small out,      4860683
-silesia.tar,                      small window log,                 advanced one pass small out,      7130394
-silesia.tar,                      small hash log,                   advanced one pass small out,      6587833
-silesia.tar,                      small chain log,                  advanced one pass small out,      4943255
-silesia.tar,                      explicit params,                  advanced one pass small out,      4829974
-github,                           level -5,                         advanced one pass small out,      232744
-github,                           level -5 with dict,               advanced one pass small out,      46718
-github,                           level -3,                         advanced one pass small out,      220611
-github,                           level -3 with dict,               advanced one pass small out,      45395
-github,                           level -1,                         advanced one pass small out,      176575
-github,                           level -1 with dict,               advanced one pass small out,      43170
-github,                           level 0,                          advanced one pass small out,      136397
-github,                           level 0 with dict,                advanced one pass small out,      41170
-github,                           level 1,                          advanced one pass small out,      143457
-github,                           level 1 with dict,                advanced one pass small out,      41682
-github,                           level 3,                          advanced one pass small out,      136397
-github,                           level 3 with dict,                advanced one pass small out,      41170
-github,                           level 4,                          advanced one pass small out,      136144
-github,                           level 4 with dict,                advanced one pass small out,      41306
-github,                           level 5,                          advanced one pass small out,      135106
-github,                           level 5 with dict,                advanced one pass small out,      38938
-github,                           level 6,                          advanced one pass small out,      135108
-github,                           level 6 with dict,                advanced one pass small out,      38632
-github,                           level 7,                          advanced one pass small out,      135108
-github,                           level 7 with dict,                advanced one pass small out,      38766
-github,                           level 9,                          advanced one pass small out,      135108
-github,                           level 9 with dict,                advanced one pass small out,      39326
-github,                           level 13,                         advanced one pass small out,      133717
-github,                           level 13 with dict,               advanced one pass small out,      39716
-github,                           level 16,                         advanced one pass small out,      133717
-github,                           level 16 with dict,               advanced one pass small out,      37577
-github,                           level 19,                         advanced one pass small out,      133717
-github,                           level 19 with dict,               advanced one pass small out,      37576
-github,                           no source size,                   advanced one pass small out,      136397
-github,                           long distance mode,               advanced one pass small out,      136397
-github,                           multithreaded,                    advanced one pass small out,      136397
-github,                           multithreaded long distance mode, advanced one pass small out,      136397
-github,                           small window log,                 advanced one pass small out,      136397
-github,                           small hash log,                   advanced one pass small out,      135467
-github,                           small chain log,                  advanced one pass small out,      136314
-github,                           explicit params,                  advanced one pass small out,      137670
-silesia,                          level -5,                         advanced streaming,               7152294
-silesia,                          level -3,                         advanced streaming,               6789973
-silesia,                          level -1,                         advanced streaming,               6191549
-silesia,                          level 0,                          advanced streaming,               4862377
-silesia,                          level 1,                          advanced streaming,               5318036
-silesia,                          level 3,                          advanced streaming,               4862377
-silesia,                          level 4,                          advanced streaming,               4800629
-silesia,                          level 5,                          advanced streaming,               4710178
-silesia,                          level 6,                          advanced streaming,               4659996
-silesia,                          level 7,                          advanced streaming,               4596234
-silesia,                          level 9,                          advanced streaming,               4543862
-silesia,                          level 13,                         advanced streaming,               4482073
-silesia,                          level 16,                         advanced streaming,               4377391
-silesia,                          level 19,                         advanced streaming,               4293262
-silesia,                          no source size,                   advanced streaming,               4862341
-silesia,                          long distance mode,               advanced streaming,               4853389
-silesia,                          multithreaded,                    advanced streaming,               4862377
-silesia,                          multithreaded long distance mode, advanced streaming,               4853389
-silesia,                          small window log,                 advanced streaming,               7126389
-silesia,                          small hash log,                   advanced streaming,               6554898
-silesia,                          small chain log,                  advanced streaming,               4931093
-silesia,                          explicit params,                  advanced streaming,               4815380
-silesia.tar,                      level -5,                         advanced streaming,               7160440
-silesia.tar,                      level -3,                         advanced streaming,               6789026
-silesia.tar,                      level -1,                         advanced streaming,               6195465
-silesia.tar,                      level 0,                          advanced streaming,               4875010
-silesia.tar,                      level 1,                          advanced streaming,               5339701
-silesia.tar,                      level 3,                          advanced streaming,               4875010
-silesia.tar,                      level 4,                          advanced streaming,               4813507
-silesia.tar,                      level 5,                          advanced streaming,               4722240
-silesia.tar,                      level 6,                          advanced streaming,               4672203
-silesia.tar,                      level 7,                          advanced streaming,               4606658
-silesia.tar,                      level 9,                          advanced streaming,               4554105
-silesia.tar,                      level 13,                         advanced streaming,               4491703
-silesia.tar,                      level 16,                         advanced streaming,               4381277
-silesia.tar,                      level 19,                         advanced streaming,               4281514
-silesia.tar,                      no source size,                   advanced streaming,               4875006
-silesia.tar,                      long distance mode,               advanced streaming,               4861218
-silesia.tar,                      multithreaded,                    advanced streaming,               4875132
-silesia.tar,                      multithreaded long distance mode, advanced streaming,               4866971
-silesia.tar,                      small window log,                 advanced streaming,               7130394
-silesia.tar,                      small hash log,                   advanced streaming,               6587834
-silesia.tar,                      small chain log,                  advanced streaming,               4943260
-silesia.tar,                      explicit params,                  advanced streaming,               4830002
-github,                           level -5,                         advanced streaming,               232744
-github,                           level -5 with dict,               advanced streaming,               46718
-github,                           level -3,                         advanced streaming,               220611
-github,                           level -3 with dict,               advanced streaming,               45395
-github,                           level -1,                         advanced streaming,               176575
-github,                           level -1 with dict,               advanced streaming,               43170
-github,                           level 0,                          advanced streaming,               136397
-github,                           level 0 with dict,                advanced streaming,               41170
-github,                           level 1,                          advanced streaming,               143457
-github,                           level 1 with dict,                advanced streaming,               41682
-github,                           level 3,                          advanced streaming,               136397
-github,                           level 3 with dict,                advanced streaming,               41170
-github,                           level 4,                          advanced streaming,               136144
-github,                           level 4 with dict,                advanced streaming,               41306
-github,                           level 5,                          advanced streaming,               135106
-github,                           level 5 with dict,                advanced streaming,               38938
-github,                           level 6,                          advanced streaming,               135108
-github,                           level 6 with dict,                advanced streaming,               38632
-github,                           level 7,                          advanced streaming,               135108
-github,                           level 7 with dict,                advanced streaming,               38766
-github,                           level 9,                          advanced streaming,               135108
-github,                           level 9 with dict,                advanced streaming,               39326
-github,                           level 13,                         advanced streaming,               133717
-github,                           level 13 with dict,               advanced streaming,               39716
-github,                           level 16,                         advanced streaming,               133717
-github,                           level 16 with dict,               advanced streaming,               37577
-github,                           level 19,                         advanced streaming,               133717
-github,                           level 19 with dict,               advanced streaming,               37576
-github,                           no source size,                   advanced streaming,               136397
-github,                           long distance mode,               advanced streaming,               136397
-github,                           multithreaded,                    advanced streaming,               136397
-github,                           multithreaded long distance mode, advanced streaming,               136397
-github,                           small window log,                 advanced streaming,               136397
-github,                           small hash log,                   advanced streaming,               135467
-github,                           small chain log,                  advanced streaming,               136314
-github,                           explicit params,                  advanced streaming,               137670
-silesia,                          level -5,                         old streaming,                    7152294
-silesia,                          level -3,                         old streaming,                    6789973
-silesia,                          level -1,                         old streaming,                    6191549
-silesia,                          level 0,                          old streaming,                    4862377
-silesia,                          level 1,                          old streaming,                    5318036
-silesia,                          level 3,                          old streaming,                    4862377
-silesia,                          level 4,                          old streaming,                    4800629
-silesia,                          level 5,                          old streaming,                    4710178
-silesia,                          level 6,                          old streaming,                    4659996
-silesia,                          level 7,                          old streaming,                    4596234
-silesia,                          level 9,                          old streaming,                    4543862
-silesia,                          level 13,                         old streaming,                    4482073
-silesia,                          level 16,                         old streaming,                    4377391
-silesia,                          level 19,                         old streaming,                    4293262
-silesia,                          no source size,                   old streaming,                    4862341
-silesia.tar,                      level -5,                         old streaming,                    7160440
-silesia.tar,                      level -3,                         old streaming,                    6789026
-silesia.tar,                      level -1,                         old streaming,                    6195465
-silesia.tar,                      level 0,                          old streaming,                    4875010
-silesia.tar,                      level 1,                          old streaming,                    5339701
-silesia.tar,                      level 3,                          old streaming,                    4875010
-silesia.tar,                      level 4,                          old streaming,                    4813507
-silesia.tar,                      level 5,                          old streaming,                    4722240
-silesia.tar,                      level 6,                          old streaming,                    4672203
-silesia.tar,                      level 7,                          old streaming,                    4606658
-silesia.tar,                      level 9,                          old streaming,                    4554105
-silesia.tar,                      level 13,                         old streaming,                    4491703
-silesia.tar,                      level 16,                         old streaming,                    4381277
-silesia.tar,                      level 19,                         old streaming,                    4281514
-silesia.tar,                      no source size,                   old streaming,                    4875006
-github,                           level -5,                         old streaming,                    232744
-github,                           level -5 with dict,               old streaming,                    46718
-github,                           level -3,                         old streaming,                    220611
-github,                           level -3 with dict,               old streaming,                    45395
-github,                           level -1,                         old streaming,                    176575
-github,                           level -1 with dict,               old streaming,                    43170
-github,                           level 0,                          old streaming,                    136397
-github,                           level 0 with dict,                old streaming,                    41170
-github,                           level 1,                          old streaming,                    143457
-github,                           level 1 with dict,                old streaming,                    41682
-github,                           level 3,                          old streaming,                    136397
-github,                           level 3 with dict,                old streaming,                    41170
-github,                           level 4,                          old streaming,                    136144
-github,                           level 4 with dict,                old streaming,                    41306
-github,                           level 5,                          old streaming,                    135106
-github,                           level 5 with dict,                old streaming,                    38938
-github,                           level 6,                          old streaming,                    135108
-github,                           level 6 with dict,                old streaming,                    38632
-github,                           level 7,                          old streaming,                    135108
-github,                           level 7 with dict,                old streaming,                    38766
-github,                           level 9,                          old streaming,                    135108
-github,                           level 9 with dict,                old streaming,                    39326
-github,                           level 13,                         old streaming,                    133717
-github,                           level 13 with dict,               old streaming,                    39716
-github,                           level 16,                         old streaming,                    133717
-github,                           level 16 with dict,               old streaming,                    37577
-github,                           level 19,                         old streaming,                    133717
-github,                           level 19 with dict,               old streaming,                    37576
-github,                           no source size,                   old streaming,                    141003
+Data,                               Config,                             Method,                             Total compressed size
+silesia.tar,                        level -5,                           compress simple,                    6738558
+silesia.tar,                        level -3,                           compress simple,                    6446362
+silesia.tar,                        level -1,                           compress simple,                    6186038
+silesia.tar,                        level 0,                            compress simple,                    4861374
+silesia.tar,                        level 1,                            compress simple,                    5334825
+silesia.tar,                        level 3,                            compress simple,                    4861374
+silesia.tar,                        level 4,                            compress simple,                    4799583
+silesia.tar,                        level 5,                            compress simple,                    4722271
+silesia.tar,                        level 6,                            compress simple,                    4672231
+silesia.tar,                        level 7,                            compress simple,                    4606657
+silesia.tar,                        level 9,                            compress simple,                    4554099
+silesia.tar,                        level 13,                           compress simple,                    4491706
+silesia.tar,                        level 16,                           compress simple,                    4381265
+silesia.tar,                        level 19,                           compress simple,                    4281551
+silesia.tar,                        uncompressed literals,              compress simple,                    4861374
+silesia.tar,                        uncompressed literals optimal,      compress simple,                    4281551
+silesia.tar,                        huffman literals,                   compress simple,                    6186038
+silesia,                            level -5,                           compress cctx,                      6737567
+silesia,                            level -3,                           compress cctx,                      6444663
+silesia,                            level -1,                           compress cctx,                      6178442
+silesia,                            level 0,                            compress cctx,                      4849491
+silesia,                            level 1,                            compress cctx,                      5313144
+silesia,                            level 3,                            compress cctx,                      4849491
+silesia,                            level 4,                            compress cctx,                      4786913
+silesia,                            level 5,                            compress cctx,                      4710178
+silesia,                            level 6,                            compress cctx,                      4659996
+silesia,                            level 7,                            compress cctx,                      4596234
+silesia,                            level 9,                            compress cctx,                      4543862
+silesia,                            level 13,                           compress cctx,                      4482073
+silesia,                            level 16,                           compress cctx,                      4377389
+silesia,                            level 19,                           compress cctx,                      4293262
+silesia,                            long distance mode,                 compress cctx,                      4849491
+silesia,                            multithreaded,                      compress cctx,                      4849491
+silesia,                            multithreaded long distance mode,   compress cctx,                      4849491
+silesia,                            small window log,                   compress cctx,                      7112784
+silesia,                            small hash log,                     compress cctx,                      6554898
+silesia,                            small chain log,                    compress cctx,                      4931093
+silesia,                            explicit params,                    compress cctx,                      4794609
+silesia,                            uncompressed literals,              compress cctx,                      4849491
+silesia,                            uncompressed literals optimal,      compress cctx,                      4293262
+silesia,                            huffman literals,                   compress cctx,                      6178442
+silesia,                            multithreaded with advanced params, compress cctx,                      4849491
+github,                             level -5,                           compress cctx,                      205285
+github,                             level -5 with dict,                 compress cctx,                      47294
+github,                             level -3,                           compress cctx,                      190643
+github,                             level -3 with dict,                 compress cctx,                      48047
+github,                             level -1,                           compress cctx,                      175568
+github,                             level -1 with dict,                 compress cctx,                      43527
+github,                             level 0,                            compress cctx,                      136311
+github,                             level 0 with dict,                  compress cctx,                      41534
+github,                             level 1,                            compress cctx,                      142450
+github,                             level 1 with dict,                  compress cctx,                      42157
+github,                             level 3,                            compress cctx,                      136311
+github,                             level 3 with dict,                  compress cctx,                      41534
+github,                             level 4,                            compress cctx,                      136144
+github,                             level 4 with dict,                  compress cctx,                      41725
+github,                             level 5,                            compress cctx,                      135106
+github,                             level 5 with dict,                  compress cctx,                      38934
+github,                             level 6,                            compress cctx,                      135108
+github,                             level 6 with dict,                  compress cctx,                      38628
+github,                             level 7,                            compress cctx,                      135108
+github,                             level 7 with dict,                  compress cctx,                      38741
+github,                             level 9,                            compress cctx,                      135108
+github,                             level 9 with dict,                  compress cctx,                      39335
+github,                             level 13,                           compress cctx,                      133717
+github,                             level 13 with dict,                 compress cctx,                      39923
+github,                             level 16,                           compress cctx,                      133717
+github,                             level 16 with dict,                 compress cctx,                      37568
+github,                             level 19,                           compress cctx,                      133717
+github,                             level 19 with dict,                 compress cctx,                      37567
+github,                             long distance mode,                 compress cctx,                      141101
+github,                             multithreaded,                      compress cctx,                      141101
+github,                             multithreaded long distance mode,   compress cctx,                      141101
+github,                             small window log,                   compress cctx,                      141101
+github,                             small hash log,                     compress cctx,                      138943
+github,                             small chain log,                    compress cctx,                      139239
+github,                             explicit params,                    compress cctx,                      140924
+github,                             uncompressed literals,              compress cctx,                      136311
+github,                             uncompressed literals optimal,      compress cctx,                      133717
+github,                             huffman literals,                   compress cctx,                      175568
+github,                             multithreaded with advanced params, compress cctx,                      141101
+silesia,                            level -5,                           zstdcli,                            6882514
+silesia,                            level -3,                           zstdcli,                            6568406
+silesia,                            level -1,                           zstdcli,                            6183433
+silesia,                            level 0,                            zstdcli,                            4849539
+silesia,                            level 1,                            zstdcli,                            5314157
+silesia,                            level 3,                            zstdcli,                            4849539
+silesia,                            level 4,                            zstdcli,                            4786961
+silesia,                            level 5,                            zstdcli,                            4710226
+silesia,                            level 6,                            zstdcli,                            4660044
+silesia,                            level 7,                            zstdcli,                            4596282
+silesia,                            level 9,                            zstdcli,                            4543910
+silesia,                            level 13,                           zstdcli,                            4482121
+silesia,                            level 16,                           zstdcli,                            4377437
+silesia,                            level 19,                           zstdcli,                            4293310
+silesia,                            long distance mode,                 zstdcli,                            4839698
+silesia,                            multithreaded,                      zstdcli,                            4849539
+silesia,                            multithreaded long distance mode,   zstdcli,                            4839698
+silesia,                            small window log,                   zstdcli,                            7123892
+silesia,                            small hash log,                     zstdcli,                            6554946
+silesia,                            small chain log,                    zstdcli,                            4931141
+silesia,                            explicit params,                    zstdcli,                            4797048
+silesia,                            uncompressed literals,              zstdcli,                            5128008
+silesia,                            uncompressed literals optimal,      zstdcli,                            4325482
+silesia,                            huffman literals,                   zstdcli,                            5331158
+silesia,                            multithreaded with advanced params, zstdcli,                            5128008
+silesia.tar,                        level -5,                           zstdcli,                            6738906
+silesia.tar,                        level -3,                           zstdcli,                            6448409
+silesia.tar,                        level -1,                           zstdcli,                            6186908
+silesia.tar,                        level 0,                            zstdcli,                            4861462
+silesia.tar,                        level 1,                            zstdcli,                            5336255
+silesia.tar,                        level 3,                            zstdcli,                            4861462
+silesia.tar,                        level 4,                            zstdcli,                            4800482
+silesia.tar,                        level 5,                            zstdcli,                            4723312
+silesia.tar,                        level 6,                            zstdcli,                            4673616
+silesia.tar,                        level 7,                            zstdcli,                            4608346
+silesia.tar,                        level 9,                            zstdcli,                            4554702
+silesia.tar,                        level 13,                           zstdcli,                            4491710
+silesia.tar,                        level 16,                           zstdcli,                            4381269
+silesia.tar,                        level 19,                           zstdcli,                            4281555
+silesia.tar,                        no source size,                     zstdcli,                            4861458
+silesia.tar,                        long distance mode,                 zstdcli,                            4853140
+silesia.tar,                        multithreaded,                      zstdcli,                            4861462
+silesia.tar,                        multithreaded long distance mode,   zstdcli,                            4853140
+silesia.tar,                        small window log,                   zstdcli,                            7127964
+silesia.tar,                        small hash log,                     zstdcli,                            6587841
+silesia.tar,                        small chain log,                    zstdcli,                            4943269
+silesia.tar,                        explicit params,                    zstdcli,                            4822318
+silesia.tar,                        uncompressed literals,              zstdcli,                            5129548
+silesia.tar,                        uncompressed literals optimal,      zstdcli,                            4320914
+silesia.tar,                        huffman literals,                   zstdcli,                            5347560
+silesia.tar,                        multithreaded with advanced params, zstdcli,                            5129548
+github,                             level -5,                           zstdcli,                            207285
+github,                             level -5 with dict,                 zstdcli,                            48718
+github,                             level -3,                           zstdcli,                            192643
+github,                             level -3 with dict,                 zstdcli,                            47395
+github,                             level -1,                           zstdcli,                            177568
+github,                             level -1 with dict,                 zstdcli,                            45170
+github,                             level 0,                            zstdcli,                            138311
+github,                             level 0 with dict,                  zstdcli,                            43148
+github,                             level 1,                            zstdcli,                            144450
+github,                             level 1 with dict,                  zstdcli,                            43682
+github,                             level 3,                            zstdcli,                            138311
+github,                             level 3 with dict,                  zstdcli,                            43148
+github,                             level 4,                            zstdcli,                            138144
+github,                             level 4 with dict,                  zstdcli,                            43251
+github,                             level 5,                            zstdcli,                            137106
+github,                             level 5 with dict,                  zstdcli,                            40938
+github,                             level 6,                            zstdcli,                            137108
+github,                             level 6 with dict,                  zstdcli,                            40632
+github,                             level 7,                            zstdcli,                            137108
+github,                             level 7 with dict,                  zstdcli,                            40766
+github,                             level 9,                            zstdcli,                            137108
+github,                             level 9 with dict,                  zstdcli,                            41326
+github,                             level 13,                           zstdcli,                            135717
+github,                             level 13 with dict,                 zstdcli,                            41716
+github,                             level 16,                           zstdcli,                            135717
+github,                             level 16 with dict,                 zstdcli,                            39577
+github,                             level 19,                           zstdcli,                            135717
+github,                             level 19 with dict,                 zstdcli,                            39576
+github,                             long distance mode,                 zstdcli,                            138311
+github,                             multithreaded,                      zstdcli,                            138311
+github,                             multithreaded long distance mode,   zstdcli,                            138311
+github,                             small window log,                   zstdcli,                            138311
+github,                             small hash log,                     zstdcli,                            137467
+github,                             small chain log,                    zstdcli,                            138314
+github,                             explicit params,                    zstdcli,                            136140
+github,                             uncompressed literals,              zstdcli,                            167915
+github,                             uncompressed literals optimal,      zstdcli,                            158824
+github,                             huffman literals,                   zstdcli,                            144450
+github,                             multithreaded with advanced params, zstdcli,                            167915
+silesia,                            level -5,                           advanced one pass,                  6737567
+silesia,                            level -3,                           advanced one pass,                  6444663
+silesia,                            level -1,                           advanced one pass,                  6178442
+silesia,                            level 0,                            advanced one pass,                  4849491
+silesia,                            level 1,                            advanced one pass,                  5313144
+silesia,                            level 3,                            advanced one pass,                  4849491
+silesia,                            level 4,                            advanced one pass,                  4786913
+silesia,                            level 5,                            advanced one pass,                  4710178
+silesia,                            level 6,                            advanced one pass,                  4659996
+silesia,                            level 7,                            advanced one pass,                  4596234
+silesia,                            level 9,                            advanced one pass,                  4543862
+silesia,                            level 13,                           advanced one pass,                  4482073
+silesia,                            level 16,                           advanced one pass,                  4377389
+silesia,                            level 19,                           advanced one pass,                  4293262
+silesia,                            no source size,                     advanced one pass,                  4849491
+silesia,                            long distance mode,                 advanced one pass,                  4839650
+silesia,                            multithreaded,                      advanced one pass,                  4849491
+silesia,                            multithreaded long distance mode,   advanced one pass,                  4839650
+silesia,                            small window log,                   advanced one pass,                  7123844
+silesia,                            small hash log,                     advanced one pass,                  6554898
+silesia,                            small chain log,                    advanced one pass,                  4931093
+silesia,                            explicit params,                    advanced one pass,                  4797035
+silesia,                            uncompressed literals,              advanced one pass,                  5127960
+silesia,                            uncompressed literals optimal,      advanced one pass,                  4325434
+silesia,                            huffman literals,                   advanced one pass,                  5326210
+silesia,                            multithreaded with advanced params, advanced one pass,                  5127960
+silesia.tar,                        level -5,                           advanced one pass,                  6738558
+silesia.tar,                        level -3,                           advanced one pass,                  6446362
+silesia.tar,                        level -1,                           advanced one pass,                  6186038
+silesia.tar,                        level 0,                            advanced one pass,                  4861374
+silesia.tar,                        level 1,                            advanced one pass,                  5334825
+silesia.tar,                        level 3,                            advanced one pass,                  4861374
+silesia.tar,                        level 4,                            advanced one pass,                  4799583
+silesia.tar,                        level 5,                            advanced one pass,                  4722271
+silesia.tar,                        level 6,                            advanced one pass,                  4672231
+silesia.tar,                        level 7,                            advanced one pass,                  4606657
+silesia.tar,                        level 9,                            advanced one pass,                  4554099
+silesia.tar,                        level 13,                           advanced one pass,                  4491706
+silesia.tar,                        level 16,                           advanced one pass,                  4381265
+silesia.tar,                        level 19,                           advanced one pass,                  4281551
+silesia.tar,                        no source size,                     advanced one pass,                  4861374
+silesia.tar,                        long distance mode,                 advanced one pass,                  4848046
+silesia.tar,                        multithreaded,                      advanced one pass,                  4860726
+silesia.tar,                        multithreaded long distance mode,   advanced one pass,                  4847343
+silesia.tar,                        small window log,                   advanced one pass,                  7127924
+silesia.tar,                        small hash log,                     advanced one pass,                  6587833
+silesia.tar,                        small chain log,                    advanced one pass,                  4943266
+silesia.tar,                        explicit params,                    advanced one pass,                  4808543
+silesia.tar,                        uncompressed literals,              advanced one pass,                  5129447
+silesia.tar,                        uncompressed literals optimal,      advanced one pass,                  4320910
+silesia.tar,                        huffman literals,                   advanced one pass,                  5347283
+silesia.tar,                        multithreaded with advanced params, advanced one pass,                  5129766
+github,                             level -5,                           advanced one pass,                  205285
+github,                             level -5 with dict,                 advanced one pass,                  46718
+github,                             level -3,                           advanced one pass,                  190643
+github,                             level -3 with dict,                 advanced one pass,                  45395
+github,                             level -1,                           advanced one pass,                  175568
+github,                             level -1 with dict,                 advanced one pass,                  43170
+github,                             level 0,                            advanced one pass,                  136311
+github,                             level 0 with dict,                  advanced one pass,                  41148
+github,                             level 1,                            advanced one pass,                  142450
+github,                             level 1 with dict,                  advanced one pass,                  41682
+github,                             level 3,                            advanced one pass,                  136311
+github,                             level 3 with dict,                  advanced one pass,                  41148
+github,                             level 4,                            advanced one pass,                  136144
+github,                             level 4 with dict,                  advanced one pass,                  41251
+github,                             level 5,                            advanced one pass,                  135106
+github,                             level 5 with dict,                  advanced one pass,                  38938
+github,                             level 6,                            advanced one pass,                  135108
+github,                             level 6 with dict,                  advanced one pass,                  38632
+github,                             level 7,                            advanced one pass,                  135108
+github,                             level 7 with dict,                  advanced one pass,                  38766
+github,                             level 9,                            advanced one pass,                  135108
+github,                             level 9 with dict,                  advanced one pass,                  39326
+github,                             level 13,                           advanced one pass,                  133717
+github,                             level 13 with dict,                 advanced one pass,                  39716
+github,                             level 16,                           advanced one pass,                  133717
+github,                             level 16 with dict,                 advanced one pass,                  37577
+github,                             level 19,                           advanced one pass,                  133717
+github,                             level 19 with dict,                 advanced one pass,                  37576
+github,                             no source size,                     advanced one pass,                  136311
+github,                             long distance mode,                 advanced one pass,                  136311
+github,                             multithreaded,                      advanced one pass,                  136311
+github,                             multithreaded long distance mode,   advanced one pass,                  136311
+github,                             small window log,                   advanced one pass,                  136311
+github,                             small hash log,                     advanced one pass,                  135467
+github,                             small chain log,                    advanced one pass,                  136314
+github,                             explicit params,                    advanced one pass,                  137670
+github,                             uncompressed literals,              advanced one pass,                  165915
+github,                             uncompressed literals optimal,      advanced one pass,                  156824
+github,                             huffman literals,                   advanced one pass,                  142450
+github,                             multithreaded with advanced params, advanced one pass,                  165915
+silesia,                            level -5,                           advanced one pass small out,        6737567
+silesia,                            level -3,                           advanced one pass small out,        6444663
+silesia,                            level -1,                           advanced one pass small out,        6178442
+silesia,                            level 0,                            advanced one pass small out,        4849491
+silesia,                            level 1,                            advanced one pass small out,        5313144
+silesia,                            level 3,                            advanced one pass small out,        4849491
+silesia,                            level 4,                            advanced one pass small out,        4786913
+silesia,                            level 5,                            advanced one pass small out,        4710178
+silesia,                            level 6,                            advanced one pass small out,        4659996
+silesia,                            level 7,                            advanced one pass small out,        4596234
+silesia,                            level 9,                            advanced one pass small out,        4543862
+silesia,                            level 13,                           advanced one pass small out,        4482073
+silesia,                            level 16,                           advanced one pass small out,        4377389
+silesia,                            level 19,                           advanced one pass small out,        4293262
+silesia,                            no source size,                     advanced one pass small out,        4849491
+silesia,                            long distance mode,                 advanced one pass small out,        4839650
+silesia,                            multithreaded,                      advanced one pass small out,        4849491
+silesia,                            multithreaded long distance mode,   advanced one pass small out,        4839650
+silesia,                            small window log,                   advanced one pass small out,        7123844
+silesia,                            small hash log,                     advanced one pass small out,        6554898
+silesia,                            small chain log,                    advanced one pass small out,        4931093
+silesia,                            explicit params,                    advanced one pass small out,        4797035
+silesia,                            uncompressed literals,              advanced one pass small out,        5127960
+silesia,                            uncompressed literals optimal,      advanced one pass small out,        4325434
+silesia,                            huffman literals,                   advanced one pass small out,        5326210
+silesia,                            multithreaded with advanced params, advanced one pass small out,        5127960
+silesia.tar,                        level -5,                           advanced one pass small out,        6738558
+silesia.tar,                        level -3,                           advanced one pass small out,        6446362
+silesia.tar,                        level -1,                           advanced one pass small out,        6186038
+silesia.tar,                        level 0,                            advanced one pass small out,        4861374
+silesia.tar,                        level 1,                            advanced one pass small out,        5334825
+silesia.tar,                        level 3,                            advanced one pass small out,        4861374
+silesia.tar,                        level 4,                            advanced one pass small out,        4799583
+silesia.tar,                        level 5,                            advanced one pass small out,        4722271
+silesia.tar,                        level 6,                            advanced one pass small out,        4672231
+silesia.tar,                        level 7,                            advanced one pass small out,        4606657
+silesia.tar,                        level 9,                            advanced one pass small out,        4554099
+silesia.tar,                        level 13,                           advanced one pass small out,        4491706
+silesia.tar,                        level 16,                           advanced one pass small out,        4381265
+silesia.tar,                        level 19,                           advanced one pass small out,        4281551
+silesia.tar,                        no source size,                     advanced one pass small out,        4861374
+silesia.tar,                        long distance mode,                 advanced one pass small out,        4848046
+silesia.tar,                        multithreaded,                      advanced one pass small out,        4860726
+silesia.tar,                        multithreaded long distance mode,   advanced one pass small out,        4847343
+silesia.tar,                        small window log,                   advanced one pass small out,        7127924
+silesia.tar,                        small hash log,                     advanced one pass small out,        6587833
+silesia.tar,                        small chain log,                    advanced one pass small out,        4943266
+silesia.tar,                        explicit params,                    advanced one pass small out,        4808543
+silesia.tar,                        uncompressed literals,              advanced one pass small out,        5129447
+silesia.tar,                        uncompressed literals optimal,      advanced one pass small out,        4320910
+silesia.tar,                        huffman literals,                   advanced one pass small out,        5347283
+silesia.tar,                        multithreaded with advanced params, advanced one pass small out,        5129766
+github,                             level -5,                           advanced one pass small out,        205285
+github,                             level -5 with dict,                 advanced one pass small out,        46718
+github,                             level -3,                           advanced one pass small out,        190643
+github,                             level -3 with dict,                 advanced one pass small out,        45395
+github,                             level -1,                           advanced one pass small out,        175568
+github,                             level -1 with dict,                 advanced one pass small out,        43170
+github,                             level 0,                            advanced one pass small out,        136311
+github,                             level 0 with dict,                  advanced one pass small out,        41148
+github,                             level 1,                            advanced one pass small out,        142450
+github,                             level 1 with dict,                  advanced one pass small out,        41682
+github,                             level 3,                            advanced one pass small out,        136311
+github,                             level 3 with dict,                  advanced one pass small out,        41148
+github,                             level 4,                            advanced one pass small out,        136144
+github,                             level 4 with dict,                  advanced one pass small out,        41251
+github,                             level 5,                            advanced one pass small out,        135106
+github,                             level 5 with dict,                  advanced one pass small out,        38938
+github,                             level 6,                            advanced one pass small out,        135108
+github,                             level 6 with dict,                  advanced one pass small out,        38632
+github,                             level 7,                            advanced one pass small out,        135108
+github,                             level 7 with dict,                  advanced one pass small out,        38766
+github,                             level 9,                            advanced one pass small out,        135108
+github,                             level 9 with dict,                  advanced one pass small out,        39326
+github,                             level 13,                           advanced one pass small out,        133717
+github,                             level 13 with dict,                 advanced one pass small out,        39716
+github,                             level 16,                           advanced one pass small out,        133717
+github,                             level 16 with dict,                 advanced one pass small out,        37577
+github,                             level 19,                           advanced one pass small out,        133717
+github,                             level 19 with dict,                 advanced one pass small out,        37576
+github,                             no source size,                     advanced one pass small out,        136311
+github,                             long distance mode,                 advanced one pass small out,        136311
+github,                             multithreaded,                      advanced one pass small out,        136311
+github,                             multithreaded long distance mode,   advanced one pass small out,        136311
+github,                             small window log,                   advanced one pass small out,        136311
+github,                             small hash log,                     advanced one pass small out,        135467
+github,                             small chain log,                    advanced one pass small out,        136314
+github,                             explicit params,                    advanced one pass small out,        137670
+github,                             uncompressed literals,              advanced one pass small out,        165915
+github,                             uncompressed literals optimal,      advanced one pass small out,        156824
+github,                             huffman literals,                   advanced one pass small out,        142450
+github,                             multithreaded with advanced params, advanced one pass small out,        165915
+silesia,                            level -5,                           advanced streaming,                 6882466
+silesia,                            level -3,                           advanced streaming,                 6568358
+silesia,                            level -1,                           advanced streaming,                 6183385
+silesia,                            level 0,                            advanced streaming,                 4849491
+silesia,                            level 1,                            advanced streaming,                 5314109
+silesia,                            level 3,                            advanced streaming,                 4849491
+silesia,                            level 4,                            advanced streaming,                 4786913
+silesia,                            level 5,                            advanced streaming,                 4710178
+silesia,                            level 6,                            advanced streaming,                 4659996
+silesia,                            level 7,                            advanced streaming,                 4596234
+silesia,                            level 9,                            advanced streaming,                 4543862
+silesia,                            level 13,                           advanced streaming,                 4482073
+silesia,                            level 16,                           advanced streaming,                 4377389
+silesia,                            level 19,                           advanced streaming,                 4293262
+silesia,                            no source size,                     advanced streaming,                 4849455
+silesia,                            long distance mode,                 advanced streaming,                 4839650
+silesia,                            multithreaded,                      advanced streaming,                 4849491
+silesia,                            multithreaded long distance mode,   advanced streaming,                 4839650
+silesia,                            small window log,                   advanced streaming,                 7123846
+silesia,                            small hash log,                     advanced streaming,                 6554898
+silesia,                            small chain log,                    advanced streaming,                 4931093
+silesia,                            explicit params,                    advanced streaming,                 4797048
+silesia,                            uncompressed literals,              advanced streaming,                 5127960
+silesia,                            uncompressed literals optimal,      advanced streaming,                 4325434
+silesia,                            huffman literals,                   advanced streaming,                 5331110
+silesia,                            multithreaded with advanced params, advanced streaming,                 5127960
+silesia.tar,                        level -5,                           advanced streaming,                 6982738
+silesia.tar,                        level -3,                           advanced streaming,                 6641264
+silesia.tar,                        level -1,                           advanced streaming,                 6190789
+silesia.tar,                        level 0,                            advanced streaming,                 4861376
+silesia.tar,                        level 1,                            advanced streaming,                 5336879
+silesia.tar,                        level 3,                            advanced streaming,                 4861376
+silesia.tar,                        level 4,                            advanced streaming,                 4799583
+silesia.tar,                        level 5,                            advanced streaming,                 4722276
+silesia.tar,                        level 6,                            advanced streaming,                 4672240
+silesia.tar,                        level 7,                            advanced streaming,                 4606657
+silesia.tar,                        level 9,                            advanced streaming,                 4554106
+silesia.tar,                        level 13,                           advanced streaming,                 4491707
+silesia.tar,                        level 16,                           advanced streaming,                 4381284
+silesia.tar,                        level 19,                           advanced streaming,                 4281511
+silesia.tar,                        no source size,                     advanced streaming,                 4861372
+silesia.tar,                        long distance mode,                 advanced streaming,                 4848046
+silesia.tar,                        multithreaded,                      advanced streaming,                 4861458
+silesia.tar,                        multithreaded long distance mode,   advanced streaming,                 4853136
+silesia.tar,                        small window log,                   advanced streaming,                 7127924
+silesia.tar,                        small hash log,                     advanced streaming,                 6587834
+silesia.tar,                        small chain log,                    advanced streaming,                 4943271
+silesia.tar,                        explicit params,                    advanced streaming,                 4808570
+silesia.tar,                        uncompressed literals,              advanced streaming,                 5129450
+silesia.tar,                        uncompressed literals optimal,      advanced streaming,                 4320841
+silesia.tar,                        huffman literals,                   advanced streaming,                 5352306
+silesia.tar,                        multithreaded with advanced params, advanced streaming,                 5129544
+github,                             level -5,                           advanced streaming,                 205285
+github,                             level -5 with dict,                 advanced streaming,                 46718
+github,                             level -3,                           advanced streaming,                 190643
+github,                             level -3 with dict,                 advanced streaming,                 45395
+github,                             level -1,                           advanced streaming,                 175568
+github,                             level -1 with dict,                 advanced streaming,                 43170
+github,                             level 0,                            advanced streaming,                 136311
+github,                             level 0 with dict,                  advanced streaming,                 41148
+github,                             level 1,                            advanced streaming,                 142450
+github,                             level 1 with dict,                  advanced streaming,                 41682
+github,                             level 3,                            advanced streaming,                 136311
+github,                             level 3 with dict,                  advanced streaming,                 41148
+github,                             level 4,                            advanced streaming,                 136144
+github,                             level 4 with dict,                  advanced streaming,                 41251
+github,                             level 5,                            advanced streaming,                 135106
+github,                             level 5 with dict,                  advanced streaming,                 38938
+github,                             level 6,                            advanced streaming,                 135108
+github,                             level 6 with dict,                  advanced streaming,                 38632
+github,                             level 7,                            advanced streaming,                 135108
+github,                             level 7 with dict,                  advanced streaming,                 38766
+github,                             level 9,                            advanced streaming,                 135108
+github,                             level 9 with dict,                  advanced streaming,                 39326
+github,                             level 13,                           advanced streaming,                 133717
+github,                             level 13 with dict,                 advanced streaming,                 39716
+github,                             level 16,                           advanced streaming,                 133717
+github,                             level 16 with dict,                 advanced streaming,                 37577
+github,                             level 19,                           advanced streaming,                 133717
+github,                             level 19 with dict,                 advanced streaming,                 37576
+github,                             no source size,                     advanced streaming,                 136311
+github,                             long distance mode,                 advanced streaming,                 136311
+github,                             multithreaded,                      advanced streaming,                 136311
+github,                             multithreaded long distance mode,   advanced streaming,                 136311
+github,                             small window log,                   advanced streaming,                 136311
+github,                             small hash log,                     advanced streaming,                 135467
+github,                             small chain log,                    advanced streaming,                 136314
+github,                             explicit params,                    advanced streaming,                 137670
+github,                             uncompressed literals,              advanced streaming,                 165915
+github,                             uncompressed literals optimal,      advanced streaming,                 156824
+github,                             huffman literals,                   advanced streaming,                 142450
+github,                             multithreaded with advanced params, advanced streaming,                 165915
+silesia,                            level -5,                           old streaming,                      6882466
+silesia,                            level -3,                           old streaming,                      6568358
+silesia,                            level -1,                           old streaming,                      6183385
+silesia,                            level 0,                            old streaming,                      4849491
+silesia,                            level 1,                            old streaming,                      5314109
+silesia,                            level 3,                            old streaming,                      4849491
+silesia,                            level 4,                            old streaming,                      4786913
+silesia,                            level 5,                            old streaming,                      4710178
+silesia,                            level 6,                            old streaming,                      4659996
+silesia,                            level 7,                            old streaming,                      4596234
+silesia,                            level 9,                            old streaming,                      4543862
+silesia,                            level 13,                           old streaming,                      4482073
+silesia,                            level 16,                           old streaming,                      4377389
+silesia,                            level 19,                           old streaming,                      4293262
+silesia,                            no source size,                     old streaming,                      4849455
+silesia,                            long distance mode,                 old streaming,                      12000408
+silesia,                            multithreaded,                      old streaming,                      12000408
+silesia,                            multithreaded long distance mode,   old streaming,                      12000408
+silesia,                            small window log,                   old streaming,                      12000408
+silesia,                            small hash log,                     old streaming,                      12000408
+silesia,                            small chain log,                    old streaming,                      12000408
+silesia,                            explicit params,                    old streaming,                      12000408
+silesia,                            uncompressed literals,              old streaming,                      4849491
+silesia,                            uncompressed literals optimal,      old streaming,                      4293262
+silesia,                            huffman literals,                   old streaming,                      6183385
+silesia,                            multithreaded with advanced params, old streaming,                      12000408
+silesia.tar,                        level -5,                           old streaming,                      6982738
+silesia.tar,                        level -3,                           old streaming,                      6641264
+silesia.tar,                        level -1,                           old streaming,                      6190789
+silesia.tar,                        level 0,                            old streaming,                      4861376
+silesia.tar,                        level 1,                            old streaming,                      5336879
+silesia.tar,                        level 3,                            old streaming,                      4861376
+silesia.tar,                        level 4,                            old streaming,                      4799583
+silesia.tar,                        level 5,                            old streaming,                      4722276
+silesia.tar,                        level 6,                            old streaming,                      4672240
+silesia.tar,                        level 7,                            old streaming,                      4606657
+silesia.tar,                        level 9,                            old streaming,                      4554106
+silesia.tar,                        level 13,                           old streaming,                      4491707
+silesia.tar,                        level 16,                           old streaming,                      4381284
+silesia.tar,                        level 19,                           old streaming,                      4281511
+silesia.tar,                        no source size,                     old streaming,                      4861372
+silesia.tar,                        long distance mode,                 old streaming,                      12022046
+silesia.tar,                        multithreaded,                      old streaming,                      12022046
+silesia.tar,                        multithreaded long distance mode,   old streaming,                      12022046
+silesia.tar,                        small window log,                   old streaming,                      12022046
+silesia.tar,                        small hash log,                     old streaming,                      12022046
+silesia.tar,                        small chain log,                    old streaming,                      12022046
+silesia.tar,                        explicit params,                    old streaming,                      12022046
+silesia.tar,                        uncompressed literals,              old streaming,                      4861376
+silesia.tar,                        uncompressed literals optimal,      old streaming,                      4281511
+silesia.tar,                        huffman literals,                   old streaming,                      6190789
+silesia.tar,                        multithreaded with advanced params, old streaming,                      12022046
+github,                             level -5,                           old streaming,                      205285
+github,                             level -5 with dict,                 old streaming,                      46718
+github,                             level -3,                           old streaming,                      190643
+github,                             level -3 with dict,                 old streaming,                      45395
+github,                             level -1,                           old streaming,                      175568
+github,                             level -1 with dict,                 old streaming,                      43170
+github,                             level 0,                            old streaming,                      136311
+github,                             level 0 with dict,                  old streaming,                      41148
+github,                             level 1,                            old streaming,                      142450
+github,                             level 1 with dict,                  old streaming,                      41682
+github,                             level 3,                            old streaming,                      136311
+github,                             level 3 with dict,                  old streaming,                      41148
+github,                             level 4,                            old streaming,                      136144
+github,                             level 4 with dict,                  old streaming,                      41251
+github,                             level 5,                            old streaming,                      135106
+github,                             level 5 with dict,                  old streaming,                      38938
+github,                             level 6,                            old streaming,                      135108
+github,                             level 6 with dict,                  old streaming,                      38632
+github,                             level 7,                            old streaming,                      135108
+github,                             level 7 with dict,                  old streaming,                      38766
+github,                             level 9,                            old streaming,                      135108
+github,                             level 9 with dict,                  old streaming,                      39326
+github,                             level 13,                           old streaming,                      133717
+github,                             level 13 with dict,                 old streaming,                      39716
+github,                             level 16,                           old streaming,                      133717
+github,                             level 16 with dict,                 old streaming,                      37577
+github,                             level 19,                           old streaming,                      133717
+github,                             level 19 with dict,                 old streaming,                      37576
+github,                             no source size,                     old streaming,                      140631
+github,                             long distance mode,                 old streaming,                      412933
+github,                             multithreaded,                      old streaming,                      412933
+github,                             multithreaded long distance mode,   old streaming,                      412933
+github,                             small window log,                   old streaming,                      412933
+github,                             small hash log,                     old streaming,                      412933
+github,                             small chain log,                    old streaming,                      412933
+github,                             explicit params,                    old streaming,                      412933
+github,                             uncompressed literals,              old streaming,                      136311
+github,                             uncompressed literals optimal,      old streaming,                      133717
+github,                             huffman literals,                   old streaming,                      175568
+github,                             multithreaded with advanced params, old streaming,                      412933
+silesia,                            level -5,                           old streaming advanced,             6882466
+silesia,                            level -3,                           old streaming advanced,             6568358
+silesia,                            level -1,                           old streaming advanced,             6183385
+silesia,                            level 0,                            old streaming advanced,             4849491
+silesia,                            level 1,                            old streaming advanced,             5314109
+silesia,                            level 3,                            old streaming advanced,             4849491
+silesia,                            level 4,                            old streaming advanced,             4786913
+silesia,                            level 5,                            old streaming advanced,             4710178
+silesia,                            level 6,                            old streaming advanced,             4659996
+silesia,                            level 7,                            old streaming advanced,             4596234
+silesia,                            level 9,                            old streaming advanced,             4543862
+silesia,                            level 13,                           old streaming advanced,             4482073
+silesia,                            level 16,                           old streaming advanced,             4377389
+silesia,                            level 19,                           old streaming advanced,             4293262
+silesia,                            no source size,                     old streaming advanced,             4849455
+silesia,                            long distance mode,                 old streaming advanced,             12000408
+silesia,                            multithreaded,                      old streaming advanced,             12000408
+silesia,                            multithreaded long distance mode,   old streaming advanced,             12000408
+silesia,                            small window log,                   old streaming advanced,             12000408
+silesia,                            small hash log,                     old streaming advanced,             12000408
+silesia,                            small chain log,                    old streaming advanced,             12000408
+silesia,                            explicit params,                    old streaming advanced,             12000408
+silesia,                            uncompressed literals,              old streaming advanced,             4849491
+silesia,                            uncompressed literals optimal,      old streaming advanced,             4293262
+silesia,                            huffman literals,                   old streaming advanced,             6183385
+silesia,                            multithreaded with advanced params, old streaming advanced,             12000408
+silesia.tar,                        level -5,                           old streaming advanced,             6982738
+silesia.tar,                        level -3,                           old streaming advanced,             6641264
+silesia.tar,                        level -1,                           old streaming advanced,             6190789
+silesia.tar,                        level 0,                            old streaming advanced,             4861376
+silesia.tar,                        level 1,                            old streaming advanced,             5336879
+silesia.tar,                        level 3,                            old streaming advanced,             4861376
+silesia.tar,                        level 4,                            old streaming advanced,             4799583
+silesia.tar,                        level 5,                            old streaming advanced,             4722276
+silesia.tar,                        level 6,                            old streaming advanced,             4672240
+silesia.tar,                        level 7,                            old streaming advanced,             4606657
+silesia.tar,                        level 9,                            old streaming advanced,             4554106
+silesia.tar,                        level 13,                           old streaming advanced,             4491707
+silesia.tar,                        level 16,                           old streaming advanced,             4381284
+silesia.tar,                        level 19,                           old streaming advanced,             4281511
+silesia.tar,                        no source size,                     old streaming advanced,             4861372
+silesia.tar,                        long distance mode,                 old streaming advanced,             12022046
+silesia.tar,                        multithreaded,                      old streaming advanced,             12022046
+silesia.tar,                        multithreaded long distance mode,   old streaming advanced,             12022046
+silesia.tar,                        small window log,                   old streaming advanced,             12022046
+silesia.tar,                        small hash log,                     old streaming advanced,             12022046
+silesia.tar,                        small chain log,                    old streaming advanced,             12022046
+silesia.tar,                        explicit params,                    old streaming advanced,             12022046
+silesia.tar,                        uncompressed literals,              old streaming advanced,             4861376
+silesia.tar,                        uncompressed literals optimal,      old streaming advanced,             4281511
+silesia.tar,                        huffman literals,                   old streaming advanced,             6190789
+silesia.tar,                        multithreaded with advanced params, old streaming advanced,             12022046
+github,                             level -5,                           old streaming advanced,             205285
+github,                             level -5 with dict,                 old streaming advanced,             46718
+github,                             level -3,                           old streaming advanced,             190643
+github,                             level -3 with dict,                 old streaming advanced,             45395
+github,                             level -1,                           old streaming advanced,             175568
+github,                             level -1 with dict,                 old streaming advanced,             43170
+github,                             level 0,                            old streaming advanced,             136311
+github,                             level 0 with dict,                  old streaming advanced,             41148
+github,                             level 1,                            old streaming advanced,             142450
+github,                             level 1 with dict,                  old streaming advanced,             41682
+github,                             level 3,                            old streaming advanced,             136311
+github,                             level 3 with dict,                  old streaming advanced,             41148
+github,                             level 4,                            old streaming advanced,             136144
+github,                             level 4 with dict,                  old streaming advanced,             41251
+github,                             level 5,                            old streaming advanced,             135106
+github,                             level 5 with dict,                  old streaming advanced,             38938
+github,                             level 6,                            old streaming advanced,             135108
+github,                             level 6 with dict,                  old streaming advanced,             38632
+github,                             level 7,                            old streaming advanced,             135108
+github,                             level 7 with dict,                  old streaming advanced,             38766
+github,                             level 9,                            old streaming advanced,             135108
+github,                             level 9 with dict,                  old streaming advanced,             39326
+github,                             level 13,                           old streaming advanced,             133717
+github,                             level 13 with dict,                 old streaming advanced,             39716
+github,                             level 16,                           old streaming advanced,             133717
+github,                             level 16 with dict,                 old streaming advanced,             37577
+github,                             level 19,                           old streaming advanced,             133717
+github,                             level 19 with dict,                 old streaming advanced,             37576
+github,                             no source size,                     old streaming advanced,             140631
+github,                             long distance mode,                 old streaming advanced,             412933
+github,                             multithreaded,                      old streaming advanced,             412933
+github,                             multithreaded long distance mode,   old streaming advanced,             412933
+github,                             small window log,                   old streaming advanced,             412933
+github,                             small hash log,                     old streaming advanced,             412933
+github,                             small chain log,                    old streaming advanced,             412933
+github,                             explicit params,                    old streaming advanced,             412933
+github,                             uncompressed literals,              old streaming advanced,             136311
+github,                             uncompressed literals optimal,      old streaming advanced,             133717
+github,                             huffman literals,                   old streaming advanced,             175568
+github,                             multithreaded with advanced params, old streaming advanced,             412933
+silesia,                            level -5,                           old streaming cdcit,                6882466
+silesia,                            level -3,                           old streaming cdcit,                6568358
+silesia,                            level -1,                           old streaming cdcit,                6183385
+silesia,                            level 0,                            old streaming cdcit,                4849491
+silesia,                            level 1,                            old streaming cdcit,                5314109
+silesia,                            level 3,                            old streaming cdcit,                4849491
+silesia,                            level 4,                            old streaming cdcit,                4786913
+silesia,                            level 5,                            old streaming cdcit,                4710178
+silesia,                            level 6,                            old streaming cdcit,                4659996
+silesia,                            level 7,                            old streaming cdcit,                4596234
+silesia,                            level 9,                            old streaming cdcit,                4543862
+silesia,                            level 13,                           old streaming cdcit,                4482073
+silesia,                            level 16,                           old streaming cdcit,                4377389
+silesia,                            level 19,                           old streaming cdcit,                4293262
+silesia,                            no source size,                     old streaming cdcit,                4849455
+silesia,                            long distance mode,                 old streaming cdcit,                12000408
+silesia,                            multithreaded,                      old streaming cdcit,                12000408
+silesia,                            multithreaded long distance mode,   old streaming cdcit,                12000408
+silesia,                            small window log,                   old streaming cdcit,                12000408
+silesia,                            small hash log,                     old streaming cdcit,                12000408
+silesia,                            small chain log,                    old streaming cdcit,                12000408
+silesia,                            explicit params,                    old streaming cdcit,                12000408
+silesia,                            uncompressed literals,              old streaming cdcit,                4849491
+silesia,                            uncompressed literals optimal,      old streaming cdcit,                4293262
+silesia,                            huffman literals,                   old streaming cdcit,                6183385
+silesia,                            multithreaded with advanced params, old streaming cdcit,                12000408
+silesia.tar,                        level -5,                           old streaming cdcit,                6982738
+silesia.tar,                        level -3,                           old streaming cdcit,                6641264
+silesia.tar,                        level -1,                           old streaming cdcit,                6190789
+silesia.tar,                        level 0,                            old streaming cdcit,                4861376
+silesia.tar,                        level 1,                            old streaming cdcit,                5336879
+silesia.tar,                        level 3,                            old streaming cdcit,                4861376
+silesia.tar,                        level 4,                            old streaming cdcit,                4799583
+silesia.tar,                        level 5,                            old streaming cdcit,                4722276
+silesia.tar,                        level 6,                            old streaming cdcit,                4672240
+silesia.tar,                        level 7,                            old streaming cdcit,                4606657
+silesia.tar,                        level 9,                            old streaming cdcit,                4554106
+silesia.tar,                        level 13,                           old streaming cdcit,                4491707
+silesia.tar,                        level 16,                           old streaming cdcit,                4381284
+silesia.tar,                        level 19,                           old streaming cdcit,                4281511
+silesia.tar,                        no source size,                     old streaming cdcit,                4861372
+silesia.tar,                        long distance mode,                 old streaming cdcit,                12022046
+silesia.tar,                        multithreaded,                      old streaming cdcit,                12022046
+silesia.tar,                        multithreaded long distance mode,   old streaming cdcit,                12022046
+silesia.tar,                        small window log,                   old streaming cdcit,                12022046
+silesia.tar,                        small hash log,                     old streaming cdcit,                12022046
+silesia.tar,                        small chain log,                    old streaming cdcit,                12022046
+silesia.tar,                        explicit params,                    old streaming cdcit,                12022046
+silesia.tar,                        uncompressed literals,              old streaming cdcit,                4861376
+silesia.tar,                        uncompressed literals optimal,      old streaming cdcit,                4281511
+silesia.tar,                        huffman literals,                   old streaming cdcit,                6190789
+silesia.tar,                        multithreaded with advanced params, old streaming cdcit,                12022046
+github,                             level -5,                           old streaming cdcit,                205285
+github,                             level -5 with dict,                 old streaming cdcit,                46718
+github,                             level -3,                           old streaming cdcit,                190643
+github,                             level -3 with dict,                 old streaming cdcit,                45395
+github,                             level -1,                           old streaming cdcit,                175568
+github,                             level -1 with dict,                 old streaming cdcit,                43170
+github,                             level 0,                            old streaming cdcit,                136311
+github,                             level 0 with dict,                  old streaming cdcit,                41148
+github,                             level 1,                            old streaming cdcit,                142450
+github,                             level 1 with dict,                  old streaming cdcit,                41682
+github,                             level 3,                            old streaming cdcit,                136311
+github,                             level 3 with dict,                  old streaming cdcit,                41148
+github,                             level 4,                            old streaming cdcit,                136144
+github,                             level 4 with dict,                  old streaming cdcit,                41251
+github,                             level 5,                            old streaming cdcit,                135106
+github,                             level 5 with dict,                  old streaming cdcit,                38938
+github,                             level 6,                            old streaming cdcit,                135108
+github,                             level 6 with dict,                  old streaming cdcit,                38632
+github,                             level 7,                            old streaming cdcit,                135108
+github,                             level 7 with dict,                  old streaming cdcit,                38766
+github,                             level 9,                            old streaming cdcit,                135108
+github,                             level 9 with dict,                  old streaming cdcit,                39326
+github,                             level 13,                           old streaming cdcit,                133717
+github,                             level 13 with dict,                 old streaming cdcit,                39716
+github,                             level 16,                           old streaming cdcit,                133717
+github,                             level 16 with dict,                 old streaming cdcit,                37577
+github,                             level 19,                           old streaming cdcit,                133717
+github,                             level 19 with dict,                 old streaming cdcit,                37576
+github,                             no source size,                     old streaming cdcit,                140631
+github,                             long distance mode,                 old streaming cdcit,                412933
+github,                             multithreaded,                      old streaming cdcit,                412933
+github,                             multithreaded long distance mode,   old streaming cdcit,                412933
+github,                             small window log,                   old streaming cdcit,                412933
+github,                             small hash log,                     old streaming cdcit,                412933
+github,                             small chain log,                    old streaming cdcit,                412933
+github,                             explicit params,                    old streaming cdcit,                412933
+github,                             uncompressed literals,              old streaming cdcit,                136311
+github,                             uncompressed literals optimal,      old streaming cdcit,                133717
+github,                             huffman literals,                   old streaming cdcit,                175568
+github,                             multithreaded with advanced params, old streaming cdcit,                412933
+silesia,                            level -5,                           old streaming advanced cdict,       6882466
+silesia,                            level -3,                           old streaming advanced cdict,       6568358
+silesia,                            level -1,                           old streaming advanced cdict,       6183385
+silesia,                            level 0,                            old streaming advanced cdict,       4849491
+silesia,                            level 1,                            old streaming advanced cdict,       5314109
+silesia,                            level 3,                            old streaming advanced cdict,       4849491
+silesia,                            level 4,                            old streaming advanced cdict,       4786913
+silesia,                            level 5,                            old streaming advanced cdict,       4710178
+silesia,                            level 6,                            old streaming advanced cdict,       4659996
+silesia,                            level 7,                            old streaming advanced cdict,       4596234
+silesia,                            level 9,                            old streaming advanced cdict,       4543862
+silesia,                            level 13,                           old streaming advanced cdict,       4482073
+silesia,                            level 16,                           old streaming advanced cdict,       4377389
+silesia,                            level 19,                           old streaming advanced cdict,       4293262
+silesia,                            no source size,                     old streaming advanced cdict,       4849455
+silesia,                            long distance mode,                 old streaming advanced cdict,       12000408
+silesia,                            multithreaded,                      old streaming advanced cdict,       12000408
+silesia,                            multithreaded long distance mode,   old streaming advanced cdict,       12000408
+silesia,                            small window log,                   old streaming advanced cdict,       12000408
+silesia,                            small hash log,                     old streaming advanced cdict,       12000408
+silesia,                            small chain log,                    old streaming advanced cdict,       12000408
+silesia,                            explicit params,                    old streaming advanced cdict,       12000408
+silesia,                            uncompressed literals,              old streaming advanced cdict,       4849491
+silesia,                            uncompressed literals optimal,      old streaming advanced cdict,       4293262
+silesia,                            huffman literals,                   old streaming advanced cdict,       6183385
+silesia,                            multithreaded with advanced params, old streaming advanced cdict,       12000408
+silesia.tar,                        level -5,                           old streaming advanced cdict,       6982738
+silesia.tar,                        level -3,                           old streaming advanced cdict,       6641264
+silesia.tar,                        level -1,                           old streaming advanced cdict,       6190789
+silesia.tar,                        level 0,                            old streaming advanced cdict,       4861376
+silesia.tar,                        level 1,                            old streaming advanced cdict,       5336879
+silesia.tar,                        level 3,                            old streaming advanced cdict,       4861376
+silesia.tar,                        level 4,                            old streaming advanced cdict,       4799583
+silesia.tar,                        level 5,                            old streaming advanced cdict,       4722276
+silesia.tar,                        level 6,                            old streaming advanced cdict,       4672240
+silesia.tar,                        level 7,                            old streaming advanced cdict,       4606657
+silesia.tar,                        level 9,                            old streaming advanced cdict,       4554106
+silesia.tar,                        level 13,                           old streaming advanced cdict,       4491707
+silesia.tar,                        level 16,                           old streaming advanced cdict,       4381284
+silesia.tar,                        level 19,                           old streaming advanced cdict,       4281511
+silesia.tar,                        no source size,                     old streaming advanced cdict,       4861372
+silesia.tar,                        long distance mode,                 old streaming advanced cdict,       12022046
+silesia.tar,                        multithreaded,                      old streaming advanced cdict,       12022046
+silesia.tar,                        multithreaded long distance mode,   old streaming advanced cdict,       12022046
+silesia.tar,                        small window log,                   old streaming advanced cdict,       12022046
+silesia.tar,                        small hash log,                     old streaming advanced cdict,       12022046
+silesia.tar,                        small chain log,                    old streaming advanced cdict,       12022046
+silesia.tar,                        explicit params,                    old streaming advanced cdict,       12022046
+silesia.tar,                        uncompressed literals,              old streaming advanced cdict,       4861376
+silesia.tar,                        uncompressed literals optimal,      old streaming advanced cdict,       4281511
+silesia.tar,                        huffman literals,                   old streaming advanced cdict,       6190789
+silesia.tar,                        multithreaded with advanced params, old streaming advanced cdict,       12022046
+github,                             level -5,                           old streaming advanced cdict,       205285
+github,                             level -5 with dict,                 old streaming advanced cdict,       46718
+github,                             level -3,                           old streaming advanced cdict,       190643
+github,                             level -3 with dict,                 old streaming advanced cdict,       45395
+github,                             level -1,                           old streaming advanced cdict,       175568
+github,                             level -1 with dict,                 old streaming advanced cdict,       43170
+github,                             level 0,                            old streaming advanced cdict,       136311
+github,                             level 0 with dict,                  old streaming advanced cdict,       41148
+github,                             level 1,                            old streaming advanced cdict,       142450
+github,                             level 1 with dict,                  old streaming advanced cdict,       41682
+github,                             level 3,                            old streaming advanced cdict,       136311
+github,                             level 3 with dict,                  old streaming advanced cdict,       41148
+github,                             level 4,                            old streaming advanced cdict,       136144
+github,                             level 4 with dict,                  old streaming advanced cdict,       41251
+github,                             level 5,                            old streaming advanced cdict,       135106
+github,                             level 5 with dict,                  old streaming advanced cdict,       38938
+github,                             level 6,                            old streaming advanced cdict,       135108
+github,                             level 6 with dict,                  old streaming advanced cdict,       38632
+github,                             level 7,                            old streaming advanced cdict,       135108
+github,                             level 7 with dict,                  old streaming advanced cdict,       38766
+github,                             level 9,                            old streaming advanced cdict,       135108
+github,                             level 9 with dict,                  old streaming advanced cdict,       39326
+github,                             level 13,                           old streaming advanced cdict,       133717
+github,                             level 13 with dict,                 old streaming advanced cdict,       39716
+github,                             level 16,                           old streaming advanced cdict,       133717
+github,                             level 16 with dict,                 old streaming advanced cdict,       37577
+github,                             level 19,                           old streaming advanced cdict,       133717
+github,                             level 19 with dict,                 old streaming advanced cdict,       37576
+github,                             no source size,                     old streaming advanced cdict,       140631
+github,                             long distance mode,                 old streaming advanced cdict,       412933
+github,                             multithreaded,                      old streaming advanced cdict,       412933
+github,                             multithreaded long distance mode,   old streaming advanced cdict,       412933
+github,                             small window log,                   old streaming advanced cdict,       412933
+github,                             small hash log,                     old streaming advanced cdict,       412933
+github,                             small chain log,                    old streaming advanced cdict,       412933
+github,                             explicit params,                    old streaming advanced cdict,       412933
+github,                             uncompressed literals,              old streaming advanced cdict,       136311
+github,                             uncompressed literals optimal,      old streaming advanced cdict,       133717
+github,                             huffman literals,                   old streaming advanced cdict,       175568
+github,                             multithreaded with advanced params, old streaming advanced cdict,       412933
@@ -153,7 +153,7 @@ static void print_help(void) {
    }
 }

-/** Parse the arguments. Teturn 0 on success. Print help on failure. */
+/** Parse the arguments. Return 0 on success. Print help on failure. */
 static int parse_args(int argc, char** argv) {
    int option_index = 0;
    int c;
@@ -93,9 +93,9 @@ static size_t cctxParamRoundTripTest(void* resultBuff, size_t resultBuffCapacity
    int const cLevel = h32 % maxClevel;

    /* Set parameters */
-    CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) );
-    CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) );
-    CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_overlapLog, 5) );
+    CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) );
+    CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) );
+    CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_overlapLog, 5) );


    /* Apply parameters */
@@ -31,6 +31,7 @@ static const void *symbols[] = {
  &ZSTD_getFrameContentSize,
  &ZSTD_maxCLevel,
  &ZSTD_compressBound,
+  &ZSTD_decompressBound,
  &ZSTD_isError,
  &ZSTD_getErrorName,
  &ZSTD_createCCtx,
@@ -25,6 +25,7 @@
 #include <stdlib.h>       /* free */
 #include <stdio.h>        /* fgets, sscanf */
 #include <string.h>       /* strcmp */
+#include "timefn.h"       /* UTIL_time_t */
 #include "mem.h"
 #define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_maxCLevel */
 #include "zstd.h"         /* ZSTD_compressBound */
@@ -26,6 +26,7 @@
 #include <stdio.h>        /* fgets, sscanf */
 #include <string.h>       /* strcmp */
 #include <assert.h>       /* assert */
+#include "timefn.h"       /* UTIL_time_t, UTIL_getTime */
 #include "mem.h"
 #define ZSTD_STATIC_LINKING_ONLY  /* ZSTD_maxCLevel, ZSTD_customMem, ZSTD_getDictID_fromFrame */
 #include "zstd.h"         /* ZSTD_compressBound */
@@ -37,6 +38,7 @@
 #include "xxhash.h"       /* XXH64_* */
 #include "seqgen.h"
 #include "util.h"
+#include "timefn.h"       /* UTIL_time_t, UTIL_clockSpanMicro, UTIL_getTime */


 /*-************************************
@@ -344,6 +346,20 @@ static int basicUnitTests(U32 seed, double compressibility)
        DISPLAYLEVEL(3, "OK (%u bytes) \n", (unsigned)(cstreamSize + cdictSize));
    }

+    /* context size functions */
+    DISPLAYLEVEL(3, "test%3i : estimate CStream size using CCtxParams : ", testNb++);
+    {   ZSTD_CCtx_params* const params = ZSTD_createCCtxParams();
+        size_t cstreamSize, cctxSize;
+        CHECK_Z( ZSTD_CCtxParams_setParameter(params, ZSTD_c_compressionLevel, 19) );
+        cstreamSize = ZSTD_estimateCStreamSize_usingCCtxParams(params);
+        CHECK_Z(cstreamSize);
+        cctxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
+        CHECK_Z(cctxSize);
+        if (cstreamSize <= cctxSize + 2 * ZSTD_BLOCKSIZE_MAX) goto _output_error;
+        ZSTD_freeCCtxParams(params);
+        DISPLAYLEVEL(3, "OK \n");
+    }
+
    DISPLAYLEVEL(3, "test%3i : check actual CStream size : ", testNb++);
    {   size_t const s = ZSTD_sizeof_CStream(zc);
        if (ZSTD_isError(s)) goto _output_error;
@@ -495,7 +511,7 @@ static int basicUnitTests(U32 seed, double compressibility)

    /* _srcSize compression test */
    DISPLAYLEVEL(3, "test%3i : compress_srcSize %u bytes : ", testNb++, COMPRESSIBLE_NOISE_LENGTH);
-    ZSTD_initCStream_srcSize(zc, 1, CNBufferSize);
+    CHECK_Z( ZSTD_initCStream_srcSize(zc, 1, CNBufferSize) );
    outBuff.dst = (char*)(compressedBuffer);
    outBuff.size = compressedBufferSize;
    outBuff.pos = 0;
@@ -503,11 +519,14 @@ static int basicUnitTests(U32 seed, double compressibility)
    inBuff.size = CNBufferSize;
    inBuff.pos = 0;
    CHECK_Z( ZSTD_compressStream(zc, &outBuff, &inBuff) );
-    if (inBuff.pos != inBuff.size) goto _output_error;   /* entire input should be consumed */
-    { size_t const r = ZSTD_endStream(zc, &outBuff);
-      if (r != 0) goto _output_error; }  /* error, or some data not flushed */
-    { unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos);
-      if ((size_t)origSize != CNBufferSize) goto _output_error; }  /* exact original size must be present */
+    CHECK(inBuff.pos != inBuff.size, "Entire input should be consumed");
+    {   size_t const r = ZSTD_endStream(zc, &outBuff);
+        CHECK(r != 0, "Error or some data not flushed (ret=%zu)", r);
+    }
+    {   unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos);
+        CHECK(origSize == ZSTD_CONTENTSIZE_UNKNOWN, "Unknown!");
+        CHECK((size_t)origSize != CNBufferSize, "Exact original size must be present (got %llu)", origSize);
+    }
    DISPLAYLEVEL(3, "OK (%u bytes : %.2f%%)\n", (unsigned)cSize, (double)cSize/COMPRESSIBLE_NOISE_LENGTH*100);

    /* wrong _srcSize compression test */
@@ -706,6 +725,156 @@ static int basicUnitTests(U32 seed, double compressibility)
    }
    DISPLAYLEVEL(3, "OK\n");

+    ZSTD_CCtx_reset(zc, ZSTD_reset_session_and_parameters);
+    CHECK_Z( ZSTD_CCtx_loadDictionary(zc, dictionary.start, dictionary.filled) );
+    cSize = ZSTD_compress2(zc, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBufferSize, 100 KB));
+    CHECK_Z(cSize);
+    DISPLAYLEVEL(3, "test%3i : ZSTD_decompressStream() with dictionary : ", testNb++);
+    {
+        ZSTD_DCtx* dctx = ZSTD_createDCtx();
+        /* We should fail to decompress without a dictionary. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            size_t const ret = ZSTD_decompressStream(dctx, &out, &in);
+            if (!ZSTD_isError(ret)) goto _output_error;
+        }
+        /* We should succeed to decompress with the dictionary. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictionary.start, dictionary.filled) );
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The dictionary should presist across calls. */
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The dictionary should not be cleared by ZSTD_reset_session_only. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only);
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* When we reset the context the dictionary is cleared. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            size_t const ret = ZSTD_decompressStream(dctx, &out, &in);
+            if (!ZSTD_isError(ret)) goto _output_error;
+        }
+        ZSTD_freeDCtx(dctx);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : ZSTD_resetDStream() with dictionary : ", testNb++);
+    {
+        ZSTD_DCtx* dctx = ZSTD_createDCtx();
+        /* We should succeed to decompress with the dictionary. */
+        ZSTD_resetDStream(dctx);
+        CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictionary.start, dictionary.filled) );
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The dictionary should not be cleared by ZSTD_resetDStream(). */
+        ZSTD_resetDStream(dctx);
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The dictionary should be cleared by ZSTD_initDStream(). */
+        CHECK_Z( ZSTD_initDStream(dctx) );
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            size_t const ret = ZSTD_decompressStream(dctx, &out, &in);
+            if (!ZSTD_isError(ret)) goto _output_error;
+        }
+        ZSTD_freeDCtx(dctx);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : ZSTD_decompressStream() with ddict : ", testNb++);
+    {
+        ZSTD_DCtx* dctx = ZSTD_createDCtx();
+        ZSTD_DDict* ddict = ZSTD_createDDict(dictionary.start, dictionary.filled);
+        /* We should succeed to decompress with the ddict. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        CHECK_Z( ZSTD_DCtx_refDDict(dctx, ddict) );
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The ddict should presist across calls. */
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* When we reset the context the ddict is cleared. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            size_t const ret = ZSTD_decompressStream(dctx, &out, &in);
+            if (!ZSTD_isError(ret)) goto _output_error;
+        }
+        ZSTD_freeDCtx(dctx);
+        ZSTD_freeDDict(ddict);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with prefix : ", testNb++);
+    {
+        ZSTD_DCtx* dctx = ZSTD_createDCtx();
+        /* We should succeed to decompress with the prefix. */
+        ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
+        CHECK_Z( ZSTD_DCtx_refPrefix_advanced(dctx, dictionary.start, dictionary.filled, ZSTD_dct_auto) );
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error;
+            if (in.pos != in.size) goto _output_error;
+        }
+        /* The prefix should be cleared after the first compression. */
+        {   ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0};
+            ZSTD_inBuffer in = {compressedBuffer, cSize, 0};
+            size_t const ret = ZSTD_decompressStream(dctx, &out, &in);
+            if (!ZSTD_isError(ret)) goto _output_error;
+        }
+        ZSTD_freeDCtx(dctx);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
+    DISPLAYLEVEL(3, "test%3i : ZSTD_initDStream*() with dictionary : ", testNb++);
+    {
+        ZSTD_DCtx* dctx = ZSTD_createDCtx();
+        ZSTD_DDict* ddict = ZSTD_createDDict(dictionary.start, dictionary.filled);
+        size_t ret;
+        /* We should succeed to decompress with the dictionary. */
+        CHECK_Z( ZSTD_initDStream_usingDict(dctx, dictionary.start, dictionary.filled) );
+        CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) );
+        /* The dictionary should presist across calls. */
+        CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) );
+        /* We should succeed to decompress with the ddict. */
+        CHECK_Z( ZSTD_initDStream_usingDDict(dctx, ddict) );
+        CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) );
+        /* The ddict should presist across calls. */
+        CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) );
+        /* When we reset the context the ddict is cleared. */
+        CHECK_Z( ZSTD_initDStream(dctx) );
+        ret = ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize);
+        if (!ZSTD_isError(ret)) goto _output_error;
+        ZSTD_freeDCtx(dctx);
+        ZSTD_freeDDict(ddict);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
    DISPLAYLEVEL(3, "test%3i : ZSTD_initCStream_usingCDict_advanced with masked dictID : ", testNb++);
    {   ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBufferSize, dictionary.filled);
        ZSTD_frameParameters const fParams = { 1 /* contentSize */, 1 /* checksum */, 1 /* noDictID */};
@@ -882,7 +1051,7 @@ static int basicUnitTests(U32 seed, double compressibility)
        inBuff.size = srcSize; assert(srcSize < COMPRESSIBLE_NOISE_LENGTH);
        inBuff.pos = 0;
    }
-    {   ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, 4 KB, dictionary.filled);   /* intentionnally lies on estimatedSrcSize, to push cdict into targeting a small window size */
+    {   ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, 4 KB, dictionary.filled);   /* intentionally lies on estimatedSrcSize, to push cdict into targeting a small window size */
        ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictionary.start, dictionary.filled, ZSTD_dlm_byRef, ZSTD_dct_fullDict, cParams, ZSTD_defaultCMem);
        DISPLAYLEVEL(5, "cParams.windowLog = %u : ", cParams.windowLog);
        CHECK_Z( ZSTD_CCtx_refCDict(zc, cdict) );
@@ -1015,6 +1184,58 @@ static int basicUnitTests(U32 seed, double compressibility)
    }
    DISPLAYLEVEL(3, "OK \n");

+    /* Small Sequence Section bug */
+    DISPLAYLEVEL(3, "test%3i : decompress blocks with small sequences section : ", testNb++);
+    {   /* This test consists of 3 blocks. Each block has one sequence.
+            The sequence has literal length of 10, match length of 10 and offset of 10.
+            The sequence value and compression mode for the blocks are following:
+            The order of values are ll, ml, of.
+              - First block  : (10, 7, 13) (rle, rle, rle)
+                 - size of sequences section: 6 bytes (1 byte for nbSeq, 1 byte for encoding mode, 3 bytes for rle, 1 byte bitstream)
+              - Second block : (10, 7, 1) (repeat, repeat, rle)
+                 - size of sequences section: 4 bytes (1 byte for nbSeq, 1 byte for encoding mode, 1 bytes for rle, 1 byte bitstream)
+              - Third block  : (10, 7, 1) (repeat, repeat, repeat)
+                 - size of sequences section: 3 bytes (1 byte for nbSeq, 1 byte for encoding mode, 1 byte bitstream) */
+
+        unsigned char compressed[] = {
+            0x28, 0xb5, 0x2f, 0xfd, 0x24, 0x3c, 0x35, 0x01, 0x00, 0xf0, 0x85, 0x08,
+            0xc2, 0xc4, 0x70, 0xcf, 0xd7, 0xc0, 0x96, 0x7e, 0x4c, 0x6b, 0xa9, 0x8b,
+            0xbc, 0xc5, 0xb6, 0xd9, 0x7f, 0x4c, 0xf1, 0x05, 0xa6, 0x54, 0xef, 0xac,
+            0x69, 0x94, 0x89, 0x1c, 0x03, 0x44, 0x0a, 0x07, 0x00, 0xb4, 0x04, 0x80,
+            0x40, 0x0a, 0xa4
+        };
+        unsigned int compressedSize = 51;
+        unsigned char decompressed[] = {
+            0x85, 0x08, 0xc2, 0xc4, 0x70, 0xcf, 0xd7, 0xc0, 0x96, 0x7e, 0x85, 0x08,
+            0xc2, 0xc4, 0x70, 0xcf, 0xd7, 0xc0, 0x96, 0x7e, 0x4c, 0x6b, 0xa9, 0x8b,
+            0xbc, 0xc5, 0xb6, 0xd9, 0x7f, 0x4c, 0x4c, 0x6b, 0xa9, 0x8b, 0xbc, 0xc5,
+            0xb6, 0xd9, 0x7f, 0x4c, 0xf1, 0x05, 0xa6, 0x54, 0xef, 0xac, 0x69, 0x94,
+            0x89, 0x1c, 0xf1, 0x05, 0xa6, 0x54, 0xef, 0xac, 0x69, 0x94, 0x89, 0x1c
+        };
+        unsigned int decompressedSize = 60;
+
+        ZSTD_DStream* const zds = ZSTD_createDStream();
+        if (zds==NULL) goto _output_error;
+
+        CHECK_Z( ZSTD_initDStream(zds) );
+        inBuff.src = compressed;
+        inBuff.size = compressedSize;
+        inBuff.pos = 0;
+        outBuff.dst = decodedBuffer;
+        outBuff.size = CNBufferSize;
+        outBuff.pos = 0;
+
+        CHECK(ZSTD_decompressStream(zds, &outBuff, &inBuff) != 0,
+              "Decompress did not reach the end of frame");
+        CHECK(inBuff.pos != inBuff.size, "Decompress did not fully consume input");
+        CHECK(outBuff.pos != decompressedSize, "Decompressed size does not match");
+        CHECK(memcmp(outBuff.dst, decompressed, decompressedSize) != 0,
+              "Decompressed data does not match");
+
+        ZSTD_freeDStream(zds);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
    DISPLAYLEVEL(3, "test%3i : dictionary + uncompressible block + reusing tables checks offset table validity: ", testNb++);
    {   ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(
            dictionary.start, dictionary.filled,
@@ -1703,7 +1924,7 @@ static size_t setCCtxParameter(ZSTD_CCtx* zc, ZSTD_CCtx_params* cctxParams,
                               int useOpaqueAPI)
 {
    if (useOpaqueAPI) {
-        return ZSTD_CCtxParam_setParameter(cctxParams, param, value);
+        return ZSTD_CCtxParams_setParameter(cctxParams, param, value);
    } else {
        return ZSTD_CCtx_setParameter(zc, param, value);
    }
@@ -1900,7 +2121,7 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest,
                    CHECK_Z( ZSTD_CCtx_setPledgedSrcSize(zc, pledgedSrcSize) );
                }

-                /* multi-threading parameters. Only adjust ocassionally for small tests. */
+                /* multi-threading parameters. Only adjust occasionally for small tests. */
                if (bigTests || (FUZ_rand(&lseed) & 0xF) == 0xF) {
                    U32 const nbThreadsCandidate = (FUZ_rand(&lseed) & 4) + 1;
                    U32 const nbThreadsAdjusted = (windowLogMalus < nbThreadsCandidate) ? nbThreadsCandidate - windowLogMalus : 1;
@@ -1930,16 +2151,6 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest,
                    } else {
                        CHECK_Z( ZSTD_CCtx_loadDictionary_byReference(zc, dict, dictSize) );
                    }
-                    if (dict && dictSize) {
-                        /* test that compression parameters are rejected (correctly) after loading a non-NULL dictionary */
-                        if (opaqueAPI) {
-                            size_t const setError = ZSTD_CCtx_setParametersUsingCCtxParams(zc, cctxParams);
-                            CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParametersUsingCCtxParams should have failed");
-                        } else {
-                            size_t const setError = ZSTD_CCtx_setParameter(zc, ZSTD_c_windowLog, cParams.windowLog-1);
-                            CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParameter should have failed");
-                        }
-                    }
                } else {
                    CHECK_Z( ZSTD_CCtx_refPrefix(zc, dict, dictSize) );
                }
@@ -1,11 +1,14 @@
+# object artifacts
+*.o
+
 # Default result files
 _*
-example.*
+example
 example_zstd.*
 example_gz.*
-fitblk.*
+fitblk
 fitblk_zstd.*
-zwrapbench.*
+zwrapbench
 foo.gz

 minigzip
@@ -88,7 +88,7 @@ fitblk: $(EXAMPLE_PATH)/fitblk.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(ZSTDLI
 fitblk_zstd: $(EXAMPLE_PATH)/fitblk.o $(ZLIBWRAPPER_PATH)/zstdTurnedOn_zlibwrapper.o $(ZSTDLIBRARY)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $^ $(ZLIB_LIBRARY) -o $@

-zwrapbench: $(EXAMPLE_PATH)/zwrapbench.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(PROGRAMS_PATH)/util.o $(PROGRAMS_PATH)/datagen.o $(ZSTDLIBRARY)
+zwrapbench: $(EXAMPLE_PATH)/zwrapbench.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(PROGRAMS_PATH)/util.o $(PROGRAMS_PATH)/timefn.o $(PROGRAMS_PATH)/datagen.o $(ZSTDLIBRARY)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $^ $(ZLIB_LIBRARY) -o $@


@@ -71,7 +71,7 @@ inflate with dictionary: hello, hello!
 The script used for compilation can be found at [zlibWrapper/Makefile](Makefile).


-#### The measurement of performace of Zstandard wrapper for zlib
+#### The measurement of performance of Zstandard wrapper for zlib

 The zstd distribution contains a tool called `zwrapbench` which can measure speed and ratio of zlib, zstd, and the wrapper.
 The benchmark is conducted using given filenames or synthetic data if filenames are not provided.
@@ -96,8 +96,8 @@ as this case is automatically detected.
 #### Reusing contexts

 The ordinary zlib compression of two files/streams allocates two contexts:
- for the 1st file calls `deflateInit`, `deflate`, `...`, `deflate`, `defalateEnd`
- for the 2nd file calls `deflateInit`, `deflate`, `...`, `deflate`, `defalateEnd`
+- for the 1st file calls `deflateInit`, `deflate`, `...`, `deflate`, `deflateEnd`
+- for the 2nd file calls `deflateInit`, `deflate`, `...`, `deflate`, `deflateEnd`

 The speed of compression can be improved with reusing a single context with following steps:
 - initialize the context with `deflateInit`
@@ -21,7 +21,7 @@
   data in order to determine how much of that input will compress to
   nearly the requested output block size.  The first pass generates
   enough deflate blocks to produce output to fill the requested
-   output size plus a specfied excess amount (see the EXCESS define
+   output size plus a specified excess amount (see the EXCESS define
   below).  The last deflate block may go quite a bit past that, but
   is discarded.  The second pass decompresses and recompresses just
   the compressed data that fit in the requested plus excess sized
@@ -217,7 +217,7 @@ int main(int argc, char **argv)
    if (ret == Z_MEM_ERROR)
        quit("out of memory");

-    /* set up for next reocmpression */
+    /* set up for next recompression */
    ret = inflateReset(&inf);
    assert(ret != Z_STREAM_ERROR);
    ret = deflateReset(&def);
@@ -17,7 +17,7 @@
   data in order to determine how much of that input will compress to
   nearly the requested output block size.  The first pass generates
   enough deflate blocks to produce output to fill the requested
-   output size plus a specfied excess amount (see the EXCESS define
+   output size plus a specified excess amount (see the EXCESS define
   below).  The last deflate block may go quite a bit past that, but
   is discarded.  The second pass decompresses and recompresses just
   the compressed data that fit in the requested plus excess sized
@@ -198,7 +198,7 @@ int main(int argc, char **argv)
    if (ret == Z_MEM_ERROR)
        quit("out of memory");

-    /* set up for next reocmpression */
+    /* set up for next recompression */
    ret = inflateReset(&inf);
    assert(ret != Z_STREAM_ERROR);
    ret = deflateReset(&def);
@@ -19,6 +19,7 @@
 #include <ctype.h>       /* toupper */
 #include <errno.h>       /* errno */

+#include "timefn.h"      /* UTIL_time_t, UTIL_getTime, UTIL_clockSpanMicro, UTIL_waitForNextTick */
 #include "mem.h"
 #define ZSTD_STATIC_LINKING_ONLY
 #include "zstd.h"
@@ -192,7 +193,7 @@ static int BMK_benchMem(z_const void* srcBuffer, size_t srcSize,
                remaining -= thisBlockSize;
    }   }   }

-    /* warmimg up memory */
+    /* warming up memory */
    RDG_genBuffer(compressedBuffer, maxCompressedSize, 0.10, 0.50, 1);

    /* Bench */
@@ -38,6 +38,8 @@

 #ifdef _WIN32
 #  include <stddef.h>
+#else
+#  include <unistd.h>
 #endif

 #if defined(__TURBOC__) || defined(_MSC_VER) || defined(_WIN32)