Update to zstd 1.5.7

zstd.mod/common.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022-2023 Bruce A Henderson
+' Copyright (c) 2022-2025 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without

zstd.mod/source.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022-2023 Bruce A Henderson
+' Copyright (c) 2022-2025 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without
@@ -53,6 +53,7 @@ Import "zstd/lib/compress/zstd_fast.c"
 Import "zstd/lib/compress/zstd_lazy.c"
 Import "zstd/lib/compress/zstd_ldm.c"
 Import "zstd/lib/compress/zstd_opt.c"
+Import "zstd/lib/compress/zstd_preSplit.c"
 Import "zstd/lib/decompress/huf_decompress.c"
 Import "zstd/lib/decompress/zstd_ddict.c"
 Import "zstd/lib/decompress/zstd_decompress.c"

zstd.mod/zstd.bmx

@@ -1,4 +1,4 @@
-' Copyright (c) 2022-2023 Bruce A Henderson
+' Copyright (c) 2022-2025 Bruce A Henderson
 ' All rights reserved.
 '
 ' Redistribution and use in source and binary forms, with or without
@@ -24,17 +24,19 @@ SuperStrict
 
 Module Archive.Zstd
 
-ModuleInfo "Version: 1.01"
+ModuleInfo "Version: 1.02"
 ModuleInfo "License: BSD"
-ModuleInfo "Copyright: Wrapper - 2022-2023 Bruce A Henderson"
+ModuleInfo "Copyright: Wrapper - 2022-2025 Bruce A Henderson"
 ModuleInfo "Copyright: ZStandard - Meta Platforms, Inc. and affiliates. All rights reserved."
 
+ModuleInfo "History: 1.02"
+ModuleInfo "History: Update to zstd 1.5.7"
 ModuleInfo "History: 1.01"
 ModuleInfo "History: Update to zstd 1.5.5"
 ModuleInfo "History: 1.00"
 ModuleInfo "History: Initial Release. zstd 1.5.2"
 
-ModuleInfo "CC_OPTS: -DHAVE_ZSTD_H -DHAVE_LIBZSTD -DHAVE_LIBZSTD_COMPRESSOR"
+ModuleInfo "CC_OPTS: -DHAVE_ZSTD_H -DHAVE_LIBZSTD -DHAVE_LIBZSTD_COMPRESSOR -DHAVE_ZSTD_compressStream"
 ModuleInfo "CC_OPTS: -DHAVE_CONFIG_H -D_FILE_OFFSET_BITS=64"
 ?win32
 ModuleInfo "CC_OPTS: -DLIBARCHIVE_STATIC"

zstd.mod/zstd/CHANGELOG

@@ -1,3 +1,66 @@
+V1.5.7 (Feb 2025)
+fix: compression bug in 32-bit mode associated with long-lasting sessions
+api: new method `ZSTD_compressSequencesAndLiterals()` (#4217, #4232)
+api: `ZSTD_getFrameHeader()` works on skippable frames (#4228)
+perf: substantial compression speed improvements (up to +30%) on small data, by @TocarIP (#4144) and @cyan4973 (#4165)
+perf: improved compression speed (~+5%) for dictionary compression at low levels (#4170)
+perf: much faster speed for `--patch-from` at high compression levels (#4276)
+perf: higher `--patch-from` compression ratios, notably at high levels (#4288)
+perf: better speed for binaries on Windows (@pps83) and when compiled with Visual Studio (@MessyHack)
+perf: slight compression ratio improvement thanks to better block boundaries (#4136, #4176, #4178)
+perf: slight compression ratio improvement for `dfast`, aka levels 3 and 4 (#4171)
+perf: runtime bmi2 detection enabled on x86 32-bit mode (#4251)
+cli: multi-threading as default CLI setting, by @daniellerozenblit
+cli: new `--max` command (#4290)
+build: improve `msbuild` version autodetection, support VS2022, by @ManuelBlanc
+build: fix `meson` build by @artem and @Victor-C-Zhang, and on Windows by @bgilbert
+build: compatibility with Apple Framework, by @Treata11
+build: improve icc/icx compatibility, by @josepho0918 and @luau-project
+build: improve compatibility with Android NDK, by Adenilson Cavalcanti
+portability: linux kernel branch, with improved support for Sequence producers (@embg, @gcabiddu, @cyan4973)
+portability: improved qnx compatibility, suggested by @rainbowball
+portability: improved install script for FreeBSD, by @sunpoet
+portability: fixed test suite compatibility with gnu hurd, by @diegonc
+doc: clarify specification, by @elasota
+misc: improved tests/decodecorpus validation tool (#4102), by antmicro
+
+V1.5.6 (Mar 2024)
+api: Promote `ZSTD_c_targetCBlockSize` to Stable API by @felixhandte
+api: new `ZSTD_d_maxBlockSize` experimental parameter, to reduce streaming decompression memory, by @terrelln
+perf: improve performance of param `ZSTD_c_targetCBlockSize`, by @Cyan4973
+perf: improved compression of arrays of integers at high compression, by @Cyan4973
+lib: reduce binary size with selective build-time exclusion, by @felixhandte
+lib: improved huffman speed on small data and linux kernel, by @terrelln
+lib: accept dictionaries with partial literal tables, by @terrelln
+lib: fix CCtx size estimation with external sequence producer, by @embg
+lib: fix corner case decoder behaviors, by @Cyan4973 and @aimuz
+lib: fix zdict prototype mismatch in static_only mode, by @ldv-alt
+lib: fix several bugs in magicless-format decoding, by @embg
+cli: add common compressed file types to `--exclude-compressed`` by @daniellerozenblit
+cli: fix mixing `-c` and `-o` commands with `--rm`, by @Cyan4973
+cli: fix erroneous exclusion of hidden files with `--output-dir-mirror` by @felixhandte
+cli: improved time accuracy on BSD, by @felixhandte
+cli: better errors on argument parsing, by @KapJI
+tests: better compatibility with older versions of `grep`, by @Cyan4973
+tests: lorem ipsum generator as default backup content, by @Cyan4973
+build: cmake improvements by @terrelln, @sighingnow, @gjasny, @JohanMabille, @Saverio976, @gruenich, @teo-tsirpanis
+build: bazel support, by @jondo2010
+build: fix cross-compiling for AArch64 with lld by @jcelerier
+build: fix Apple platform compatibility, by @nidhijaju
+build: fix Visual 2012 and lower compatibility, by @Cyan4973
+build: improve win32 support, by @DimitriPapadopoulos
+build: better C90 compliance for zlibWrapper, by @emaste
+port: make: fat binaries on macos, by @mredig
+port: ARM64EC compatibility for Windows, by @dunhor
+port: QNX support by @klausholstjacobsen
+port: MSYS2 and Cygwin makefile installation and test support, by @QBos07
+port: risc-v support validation in CI, by @Cyan4973
+port: sparc64 support validation in CI, by @Cyan4973
+port: AIX compatibility, by @likema
+port: HP-UX compatibility, by @likema
+doc: Improved specification accuracy, by @elasota
+bug: Fix and deprecate ZSTD_generateSequences (#3981)
+
 v1.5.5 (Apr 2023)
 fix: fix rare corruption bug affecting the high compression mode, reported by @danlark1 (#3517, @terrelln)
 perf: improve mid-level compression speed (#3529, #3533, #3543, @yoniko and #3552, @terrelln)
@@ -98,7 +161,7 @@ build: support for m68k (Motorola 68000's), by @cyan4973
 build: improved AIX support, by @Helflym
 build: improved meson unofficial build, by @eli-schwartz
 cli : custom memory limit when training dictionary (#2925), by @embg
-cli : report advanced parameters information when compressing in very verbose mode (``-vv`), by @Svetlitski-FB
+cli : report advanced parameters information when compressing in very verbose mode (`-vv`), by @Svetlitski-FB
 
 v1.5.0  (May 11, 2021)
 api: Various functions promoted from experimental to stable API: (#2579-2581, @senhuang42)
@@ -165,7 +228,7 @@ api: Add Function to Generate Skippable Frame (#2439, @senhuang42)
 perf: New Algorithms for the Long Distance Matcher (#2483, @mpu)
 perf: Performance Improvements for Long Distance Matcher (#2464, @mpu)
 perf: Don't Shrink Window Log when Streaming with a Dictionary (#2451, @terrelln)
-cli: Fix `--output-dir-mirror`'s Rejection of `..`-Containing Paths (#2512, @felixhandte)
+cli: Fix `--output-dir-mirror` rejection of `..` -containing paths (#2512, @felixhandte)
 cli: Allow Input From Console When `-f`/`--force` is Passed (#2466, @felixhandte)
 cli: Improve Help Message (#2500, @senhuang42)
 tests: Remove Flaky Tests (#2455, #2486, #2445, @Cyan4973)
@@ -452,7 +515,7 @@ misc: added /contrib/docker script by @gyscos
 
 v1.3.3  (Dec 21, 2017)
 perf: faster zstd_opt strategy (levels 16-19)
-fix : bug #944 : multithreading with shared ditionary and large data, reported by @gsliepen
+fix : bug #944 : multithreading with shared dictionary and large data, reported by @gsliepen
 cli : fix : content size written in header by default
 cli : fix : improved LZ4 format support, by @felixhandte
 cli : new : hidden command `-S`, to benchmark multiple files while generating one result per file

zstd.mod/zstd/CONTRIBUTING.md

@@ -60,7 +60,7 @@ Our contribution process works in three main stages:
         * Note: run local tests to ensure that your changes didn't break existing functionality
             * Quick check
             ```
-            make shortest
+            make check
             ```
             * Longer check
             ```
@@ -171,8 +171,8 @@ who want earlier signal.
 | Cirrus CI | Used for testing on FreeBSD                                                                                | https://github.com/marketplace/cirrus-ci/                                                                                                              | `.cirrus.yml`          |
 | Circle CI | Historically was used to provide faster signal,<br/> but we may be able to migrate these to Github Actions | https://circleci.com/docs/2.0/getting-started/#setting-up-circleci <br> https://youtu.be/Js3hMUsSZ2c <br> https://circleci.com/docs/2.0/enable-checks/ | `.circleci/config.yml` |
 
-Note: the instructions linked above mostly cover how to set up a repository with CI from scratch. 
-The general idea should be the same for setting up CI on your fork of zstd, but you may have to 
+Note: the instructions linked above mostly cover how to set up a repository with CI from scratch.
+The general idea should be the same for setting up CI on your fork of zstd, but you may have to
 follow slightly different steps. In particular, please ignore any instructions related to setting up
 config files (since zstd already has configs for each of these services).
 
@@ -216,7 +216,7 @@ will typically not be stable enough to obtain reliable benchmark results. If you
 hands on a desktop, this is usually a better scenario.
 
 Of course, benchmarking can be done on non-hyper-stable machines as well. You will just have to
-do a little more work to ensure that you are in fact measuring the changes you've made not and
+do a little more work to ensure that you are in fact measuring the changes you've made and not
 noise. Here are some things you can do to make your benchmarks more stable:
 
 1. The most simple thing you can do to drastically improve the stability of your benchmark is

zstd.mod/zstd/Makefile

@@ -85,14 +85,10 @@ test:
 	$(MAKE) -C $(TESTDIR) $@
 	ZSTD=../../programs/zstd $(MAKE) -C doc/educational_decoder $@
 
-## shortest: same as `make check`
-.PHONY: shortest
-shortest:
-	$(Q)$(MAKE) -C $(TESTDIR) $@
-
 ## check: run basic tests for `zstd` cli
 .PHONY: check
-check: shortest
+check:
+	$(Q)$(MAKE) -C $(TESTDIR) $@
 
 .PHONY: automated_benchmarking
 automated_benchmarking:
@@ -145,13 +141,13 @@ clean:
 	$(Q)$(MAKE) -C contrib/largeNbDicts $@ > $(VOID)
 	$(Q)$(MAKE) -C contrib/externalSequenceProducer $@ > $(VOID)
 	$(Q)$(RM) zstd$(EXT) zstdmt$(EXT) tmp*
-	$(Q)$(RM) -r lz4
+	$(Q)$(RM) -r lz4 cmakebuild mesonbuild install
 	@echo Cleaning completed
 
 #------------------------------------------------------------------------------
 # make install is validated only for Linux, macOS, Hurd and some BSD targets
 #------------------------------------------------------------------------------
-ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD DragonFly NetBSD MSYS_NT Haiku AIX))
+ifneq (,$(filter Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD DragonFly NetBSD MSYS_NT% CYGWIN_NT% Haiku AIX,$(shell sh -c 'MSYSTEM="MSYS" uname') ))
 
 HOST_OS = POSIX
 
@@ -197,6 +193,15 @@ uninstall:
 travis-install:
 	$(MAKE) install PREFIX=~/install_test_dir
 
+.PHONY: clangbuild-darwin-fat
+clangbuild-darwin-fat: clean
+	clang -v
+	CXX=clang++ CC=clang CFLAGS+="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation -arch arm64" $(MAKE) zstd-release
+	mv programs/zstd programs/zstd_arm64
+	CXX=clang++ CC=clang CFLAGS+="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation -arch x86_64" $(MAKE) zstd-release
+	mv programs/zstd programs/zstd_x64
+	lipo -create programs/zstd_x64 programs/zstd_arm64 -output programs/zstd
+
 .PHONY: gcc5build gcc6build gcc7build clangbuild m32build armbuild aarch64build ppcbuild ppc64build
 gcc5build: clean
 	gcc-5 -v
@@ -284,16 +289,16 @@ regressiontest:
 	$(MAKE) -C $(FUZZDIR) regressiontest
 
 uasanregressiontest:
-	$(MAKE) -C $(FUZZDIR) regressiontest CC=clang CXX=clang++ CFLAGS="-O3 -fsanitize=address,undefined" CXXFLAGS="-O3 -fsanitize=address,undefined"
+	$(MAKE) -C $(FUZZDIR) regressiontest CC=clang CXX=clang++ CFLAGS="-O3 -fsanitize=address,undefined -Werror" CXXFLAGS="-O3 -fsanitize=address,undefined -Werror"
 
 msanregressiontest:
-	$(MAKE) -C $(FUZZDIR) regressiontest CC=clang CXX=clang++ CFLAGS="-O3 -fsanitize=memory" CXXFLAGS="-O3 -fsanitize=memory"
+	$(MAKE) -C $(FUZZDIR) regressiontest CC=clang CXX=clang++ CFLAGS="-O3 -fsanitize=memory -Werror" CXXFLAGS="-O3 -fsanitize=memory -Werror"
 
 update_regressionResults : REGRESS_RESULTS_DIR := /tmp/regress_results_dir/
 update_regressionResults:
-	$(MAKE) -C programs zstd
-	$(MAKE) -C tests/regression test
-	$(RM) -rf $(REGRESS_RESULTS_DIR)
+	$(MAKE) -j -C programs zstd
+	$(MAKE) -j -C tests/regression test
+	$(RM) -r $(REGRESS_RESULTS_DIR)
 	$(MKDIR) $(REGRESS_RESULTS_DIR)
 	./tests/regression/test                         \
         --cache  tests/regression/cache             \
@@ -308,7 +313,7 @@ update_regressionResults:
 # run UBsan with -fsanitize-recover=pointer-overflow
 # this only works with recent compilers such as gcc 8+
 usan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=undefined -Werror $(MOREFLAGS)"
+	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=undefined -Werror $(MOREFLAGS)"
 
 asan: clean
 	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=address -Werror $(MOREFLAGS)"
@@ -319,17 +324,18 @@ asan-%: clean
 msan: clean
 	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" HAVE_LZMA=0   # datagen.c fails this test for no obvious reason
 
-msan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) HAVE_LZMA=0 $*
+msan-%:
+	$(MAKE) clean
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -j -C $(TESTDIR) HAVE_LZMA=0 $*
 
 asan32: clean
 	$(MAKE) -C $(TESTDIR) test32 CC=clang MOREFLAGS="-g -fsanitize=address $(MOREFLAGS)"
 
 uasan: clean
-	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror $(MOREFLAGS)"
+	$(MAKE) test CC=clang MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=address,undefined -Werror $(MOREFLAGS)"
 
 uasan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize-recover=pointer-overflow -fsanitize=address,undefined -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $*
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=address,undefined -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $*
 
 tsan-%: clean
 	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=thread -Werror $(MOREFLAGS)" $(MAKE) -C $(TESTDIR) $* FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)"
@@ -380,28 +386,50 @@ lz4install:
 endif
 
 
-CMAKE_PARAMS = -DZSTD_BUILD_CONTRIB:BOOL=ON -DZSTD_BUILD_STATIC:BOOL=ON -DZSTD_BUILD_TESTS:BOOL=ON -DZSTD_ZLIB_SUPPORT:BOOL=ON -DZSTD_LZMA_SUPPORT:BOOL=ON -DCMAKE_BUILD_TYPE=Release
-
-ifneq (,$(filter MSYS%,$(shell uname)))
+ifneq (,$(filter MSYS%,$(shell sh -c 'MSYSTEM="MSYS" uname') ))
 HOST_OS = MSYS
-CMAKE_PARAMS = -G"MSYS Makefiles" -DCMAKE_BUILD_TYPE=Debug -DZSTD_MULTITHREAD_SUPPORT:BOOL=OFF -DZSTD_BUILD_STATIC:BOOL=ON -DZSTD_BUILD_TESTS:BOOL=ON
 endif
 
 #------------------------------------------------------------------------
 # target specific tests
 #------------------------------------------------------------------------
-ifneq (,$(filter $(HOST_OS),MSYS POSIX))
-.PHONY: cmakebuild c89build gnu90build c99build gnu99build c11build bmix64build bmix32build bmi32build staticAnalyze
-cmakebuild:
-	cmake --version
-	$(RM) -r $(BUILDIR)/cmake/build
-	$(MKDIR) $(BUILDIR)/cmake/build
-	cd $(BUILDIR)/cmake/build; cmake -DCMAKE_INSTALL_PREFIX:PATH=~/install_test_dir $(CMAKE_PARAMS) ..
-	$(MAKE) -C $(BUILDIR)/cmake/build -j4;
-	$(MAKE) -C $(BUILDIR)/cmake/build install;
-	$(MAKE) -C $(BUILDIR)/cmake/build uninstall;
-	cd $(BUILDIR)/cmake/build; ctest -V -L Medium
+ifneq (,$(filter MSYS POSIX,$(HOST_OS)))
+
+CMAKE ?= cmake
+CMAKE_PARAMS = -DZSTD_BUILD_CONTRIB:BOOL=ON -DZSTD_BUILD_STATIC:BOOL=ON -DZSTD_BUILD_TESTS:BOOL=ON -DZSTD_ZLIB_SUPPORT:BOOL=ON -DZSTD_LZMA_SUPPORT:BOOL=ON
 
+ifneq (,$(filter MSYS%,$(shell sh -c 'MSYSTEM="MSYS" uname')))
+CMAKE_PARAMS = -G"MSYS Makefiles" -DZSTD_MULTITHREAD_SUPPORT:BOOL=OFF -DZSTD_BUILD_STATIC:BOOL=ON -DZSTD_BUILD_TESTS:BOOL=ON
+endif
+
+.PHONY: cmakebuild
+cmakebuild:
+	$(CMAKE) --version
+	$(RM) -r cmakebuild install
+	$(MKDIR) cmakebuild install
+	cd cmakebuild; $(CMAKE) -Wdev -DCMAKE_BUILD_TYPE=Debug -DCMAKE_C_FLAGS="-Werror -O0" -DCMAKE_INSTALL_PREFIX=install $(CMAKE_PARAMS) ../build/cmake
+	$(CMAKE) --build cmakebuild --target install -- -j V=1
+	cd cmakebuild; ctest -V -L Medium
+
+MESON ?= meson
+NINJA ?= ninja
+
+.PHONY: mesonbuild
+mesonbuild:
+	$(MESON) setup \
+		--buildtype=debugoptimized \
+		-Db_lundef=false \
+		-Dauto_features=enabled \
+		-Dbin_programs=true \
+		-Dbin_tests=true \
+		-Dbin_contrib=true \
+		-Ddefault_library=both \
+		build/meson mesonbuild
+	$(NINJA) -C mesonbuild/
+	$(MESON) test -C mesonbuild/ --print-errorlogs
+	$(MESON) install -C mesonbuild --destdir staging/
+
+.PHONY: c89build gnu90build c99build gnu99build c11build bmix64build bmix32build bmi32build staticAnalyze
 c89build: clean
 	$(CC) -v
 	CFLAGS="-std=c89 -Werror -Wno-attributes -Wpedantic -Wno-long-long -Wno-variadic-macros -O0" $(MAKE) lib zstd

zstd.mod/zstd/README.md

@@ -5,7 +5,7 @@ targeting real-time compression scenarios at zlib-level and better compression r
 It's backed by a very fast entropy stage, provided by [Huff0 and FSE library](https://github.com/Cyan4973/FiniteStateEntropy).
 
 Zstandard's format is stable and documented in [RFC8878](https://datatracker.ietf.org/doc/html/rfc8878). Multiple independent implementations are already available.
-This repository represents the reference implementation, provided as an open-source dual [BSD](LICENSE) and [GPLv2](COPYING) licensed **C** library,
+This repository represents the reference implementation, provided as an open-source dual [BSD](LICENSE) OR [GPLv2](COPYING) licensed **C** library,
 and a command line utility producing and decoding `.zst`, `.gz`, `.xz` and `.lz4` files.
 Should your project require another programming language,
 a list of known ports and bindings is provided on [Zstandard homepage](https://facebook.github.io/zstd/#other-languages).
@@ -29,10 +29,10 @@ a list of known ports and bindings is provided on [Zstandard homepage](https://f
 ## Benchmarks
 
 For reference, several fast compression algorithms were tested and compared
-on a desktop running Ubuntu 20.04 (`Linux 5.11.0-41-generic`),
-with a Core i7-9700K CPU @ 4.9GHz,
+on a desktop featuring a Core i7-9700K CPU @ 4.9GHz
+and running Ubuntu 20.04 (`Linux ubu20 5.15.0-101-generic`),
 using [lzbench], an open-source in-memory benchmark by @inikep
-compiled with [gcc] 9.3.0,
+compiled with [gcc] 9.4.0,
 on the [Silesia compression corpus].
 
 [lzbench]: https://github.com/inikep/lzbench
@@ -41,24 +41,23 @@ on the [Silesia compression corpus].
 
 | Compressor name         | Ratio | Compression| Decompress.|
 | ---------------         | ------| -----------| ---------- |
-| **zstd 1.5.1 -1**       | 2.887 |   530 MB/s |  1700 MB/s |
+| **zstd 1.5.6 -1**       | 2.887 |   510 MB/s |  1580 MB/s |
 | [zlib] 1.2.11 -1        | 2.743 |    95 MB/s |   400 MB/s |
-| brotli 1.0.9 -0         | 2.702 |   395 MB/s |   450 MB/s |
-| **zstd 1.5.1 --fast=1** | 2.437 |   600 MB/s |  2150 MB/s |
-| **zstd 1.5.1 --fast=3** | 2.239 |   670 MB/s |  2250 MB/s |
-| quicklz 1.5.0 -1        | 2.238 |   540 MB/s |   760 MB/s |
-| **zstd 1.5.1 --fast=4** | 2.148 |   710 MB/s |  2300 MB/s |
-| lzo1x 2.10 -1           | 2.106 |   660 MB/s |   845 MB/s |
-| [lz4] 1.9.3             | 2.101 |   740 MB/s |  4500 MB/s |
-| lzf 3.6 -1              | 2.077 |   410 MB/s |   830 MB/s |
-| snappy 1.1.9            | 2.073 |   550 MB/s |  1750 MB/s |
+| brotli 1.0.9 -0         | 2.702 |   395 MB/s |   430 MB/s |
+| **zstd 1.5.6 --fast=1** | 2.437 |   545 MB/s |  1890 MB/s |
+| **zstd 1.5.6 --fast=3** | 2.239 |   650 MB/s |  2000 MB/s |
+| quicklz 1.5.0 -1        | 2.238 |   525 MB/s |   750 MB/s |
+| lzo1x 2.10 -1           | 2.106 |   650 MB/s |   825 MB/s |
+| [lz4] 1.9.4             | 2.101 |   700 MB/s |  4000 MB/s |
+| lzf 3.6 -1              | 2.077 |   420 MB/s |   830 MB/s |
+| snappy 1.1.9            | 2.073 |   530 MB/s |  1660 MB/s |
 
 [zlib]: https://www.zlib.net/
 [lz4]: https://lz4.github.io/lz4/
 
 The negative compression levels, specified with `--fast=#`,
 offer faster compression and decompression speed
-at the cost of compression ratio (compared to level 1).
+at the cost of compression ratio.
 
 Zstd can also offer stronger compression ratios at the cost of compression speed.
 Speed vs Compression trade-off is configurable by small increments.
@@ -185,6 +184,17 @@ You can build and install zstd [vcpkg](https://github.com/Microsoft/vcpkg/) depe
 The zstd port in vcpkg is kept up to date by Microsoft team members and community contributors.
 If the version is out of date, please [create an issue or pull request](https://github.com/Microsoft/vcpkg) on the vcpkg repository.
 
+### Conan
+
+You can install pre-built binaries for zstd or build it from source using [Conan](https://conan.io/). Use the following command:
+
+```bash
+conan install --requires="zstd/[*]" --build=missing
+```
+
+The zstd Conan recipe is kept up to date by Conan maintainers and community contributors.
+If the version is out of date, please [create an issue or pull request](https://github.com/conan-io/conan-center-index) on the ConanCenterIndex repository.
+
 ### Visual Studio (Windows)
 
 Going into `build` directory, you will find additional possibilities:
@@ -198,6 +208,10 @@ Going into `build` directory, you will find additional possibilities:
 You can build the zstd binary via buck by executing: `buck build programs:zstd` from the root of the repo.
 The output binary will be in `buck-out/gen/programs/`.
 
+### Bazel
+
+You easily can integrate zstd into your Bazel project by using the module hosted on the [Bazel Central Repository](https://registry.bazel.build/modules/zstd).
+
 ## Testing
 
 You can run quick local smoke tests by running `make check`.
@@ -213,7 +227,7 @@ Zstandard is considered safe for production environments.
 
 ## License
 
-Zstandard is dual-licensed under [BSD](LICENSE) and [GPLv2](COPYING).
+Zstandard is dual-licensed under [BSD](LICENSE) OR [GPLv2](COPYING).
 
 ## Contributing
 

zstd.mod/zstd/SECURITY.md

@@ -0,0 +1,15 @@
+# Reporting and Fixing Security Issues
+
+Please do not open GitHub issues or pull requests - this makes the problem immediately visible to everyone, including malicious actors. Security issues in this open source project can be safely reported via the Meta Bug Bounty program:
+
+https://www.facebook.com/whitehat
+
+Meta's security team will triage your report and determine whether or not is it eligible for a bounty under our program.
+
+# Receiving Vulnerability Notifications
+
+In the case that a significant security vulnerability is reported to us or discovered by us---without being publicly known---we will, at our discretion, notify high-profile, high-exposure users of Zstandard ahead of our public disclosure of the issue and associated fix.
+
+If you believe your project would benefit from inclusion in this list, please reach out to one of the maintainers.
+
+<!-- Note to maintainers: this list is kept [here](https://fburl.com/wiki/cgc1l62x). -->

zstd.mod/zstd/appveyor.yml

@@ -1,205 +0,0 @@
-# Following tests are run _only_ on `release` branch
-# and on selected feature branch named `appveyorTest` or `visual*`
-
--
-  version: 1.0.{build}
-  branches:
-    only:
-    - release
-    - master
-    - /appveyor*/
-    - /visual*/
-  environment:
-    matrix:
-    - COMPILER: "gcc"
-      HOST:     "mingw"
-      PLATFORM: "x64"
-      SCRIPT:   "make allzstd MOREFLAGS=-static"
-      ARTIFACT: "true"
-      BUILD:    "true"
-    - COMPILER: "gcc"
-      HOST:     "mingw"
-      PLATFORM: "x86"
-      SCRIPT:   "make allzstd MOREFLAGS=-static"
-      ARTIFACT: "true"
-      BUILD:    "true"
-
-    - COMPILER: "clang-cl"
-      HOST:     "cmake-visual"
-      PLATFORM: "x64"
-      CONFIGURATION: "Release"
-      CMAKE_GENERATOR: "Visual Studio 15 2017"
-      CMAKE_GENERATOR_PLATFORM: "x64"
-      CMAKE_GENERATOR_TOOLSET: "LLVM"
-      APPVEYOR_BUILD_WORKER_IMAGE: "Visual Studio 2017"
-
-  install:
-  - ECHO Installing %COMPILER% %PLATFORM% %CONFIGURATION%
-  - SET PATH_ORIGINAL=%PATH%
-  - if [%HOST%]==[mingw] (
-      SET "PATH_MINGW32=C:\mingw-w64\i686-6.3.0-posix-dwarf-rt_v5-rev1\mingw32\bin" &&
-      SET "PATH_MINGW64=C:\mingw-w64\x86_64-6.3.0-posix-seh-rt_v5-rev1\mingw64\bin" &&
-      COPY C:\msys64\usr\bin\make.exe C:\mingw-w64\i686-6.3.0-posix-dwarf-rt_v5-rev1\mingw32\bin\make.exe &&
-      COPY C:\msys64\usr\bin\make.exe C:\mingw-w64\x86_64-6.3.0-posix-seh-rt_v5-rev1\mingw64\bin\make.exe
-    )
-  - IF [%HOST%]==[visual] IF [%PLATFORM%]==[x64] (
-      SET ADDITIONALPARAM=/p:LibraryPath="C:\Program Files\Microsoft SDKs\Windows\v7.1\lib\x64;c:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\lib\amd64;C:\Program Files (x86)\Microsoft Visual Studio 10.0\;C:\Program Files (x86)\Microsoft Visual Studio 10.0\lib\amd64;"
-    )
-
-  build_script:
-  - if [%HOST%]==[mingw] (
-      ( if [%PLATFORM%]==[x64] (
-        SET "PATH=%PATH_MINGW64%;%PATH_ORIGINAL%"
-      ) else if [%PLATFORM%]==[x86] (
-        SET "PATH=%PATH_MINGW32%;%PATH_ORIGINAL%"
-      ) )
-    )
-  - if [%HOST%]==[mingw] if [%BUILD%]==[true] (
-      make -v &&
-      sh -c "%COMPILER% -v" &&
-      ECHO Building zlib to static link &&
-      SET "CC=%COMPILER%" &&
-      sh -c "cd .. && git clone --depth 1 --branch v1.2.11 https://github.com/madler/zlib" &&
-      sh -c "cd ../zlib && make -f win32/Makefile.gcc libz.a"
-      ECHO Building zstd &&
-      SET "CPPFLAGS=-I../../zlib" &&
-      SET "LDFLAGS=../../zlib/libz.a" &&
-      sh -c "%SCRIPT%" &&
-      ( if [%COMPILER%]==[gcc] if [%ARTIFACT%]==[true]
-          ECHO Creating artifacts &&
-          ECHO %cd% &&
-          lib\dll\example\build_package.bat &&
-          make -C programs DEBUGFLAGS= clean zstd &&
-          cd programs\ && 7z a -tzip -mx9 zstd-win-binary-%PLATFORM%.zip zstd.exe &&
-          appveyor PushArtifact zstd-win-binary-%PLATFORM%.zip &&
-          cp zstd.exe ..\bin\zstd.exe &&
-          git clone --depth 1 --branch release https://github.com/facebook/zstd &&
-          cd zstd &&
-          git archive --format=tar release -o zstd-src.tar &&
-          ..\zstd -19 zstd-src.tar &&
-          appveyor PushArtifact zstd-src.tar.zst &&
-          certUtil -hashfile zstd-src.tar.zst SHA256 > zstd-src.tar.zst.sha256.sig &&
-          appveyor PushArtifact zstd-src.tar.zst.sha256.sig &&
-          cd ..\..\bin\ &&
-          7z a -tzip -mx9 zstd-win-release-%PLATFORM%.zip * &&
-          appveyor PushArtifact zstd-win-release-%PLATFORM%.zip
-      )
-    )
-  - if [%HOST%]==[cmake-visual] (
-      ECHO *** &&
-      ECHO *** Building %CMAKE_GENERATOR% ^(%CMAKE_GENERATOR_TOOLSET%^) %PLATFORM%\%CONFIGURATION% &&
-      PUSHD build\cmake &&
-      cmake -DBUILD_TESTING=ON . &&
-      cmake --build . --config %CONFIGURATION% -j4 &&
-      POPD &&
-      ECHO ***
-    )
-
-  test_script:
-  - ECHO Testing %COMPILER% %PLATFORM% %CONFIGURATION%
-  - SET "CC=gcc"
-  - SET "CXX=g++"
-  - if [%TEST%]==[cmake] (
-      mkdir build\cmake\build &&
-      cd build\cmake\build &&
-      SET FUZZERTEST=-T2mn &&
-      SET ZSTREAM_TESTTIME=-T2mn &&
-      cmake -G "Visual Studio 14 2015 Win64" .. &&
-      cd ..\..\.. &&
-      make clean
-    )
-
-
-# The following tests are for regular pushes
-# into `dev` or some feature branch
-# There run less tests, for shorter feedback loop
-
--
-  version: 1.0.{build}
-  environment:
-    matrix:
-    - COMPILER: "visual"
-      HOST:     "visual"
-      PLATFORM: "x64"
-      CONFIGURATION: "Debug"
-    - COMPILER: "visual"
-      HOST:     "visual"
-      PLATFORM: "Win32"
-      CONFIGURATION: "Debug"
-    - COMPILER: "visual"
-      HOST:     "visual"
-      PLATFORM: "x64"
-      CONFIGURATION: "Release"
-    - COMPILER: "visual"
-      HOST:     "visual"
-      PLATFORM: "Win32"
-      CONFIGURATION: "Release"
-
-    - COMPILER: "gcc"
-      HOST:     "cygwin"
-      PLATFORM: "x64"
-
-    - COMPILER: "clang-cl"
-      HOST:     "cmake-visual"
-      PLATFORM: "x64"
-      CONFIGURATION: "Release"
-      CMAKE_GENERATOR: "Visual Studio 15 2017"
-      CMAKE_GENERATOR_PLATFORM: "x64"
-      CMAKE_GENERATOR_TOOLSET: "LLVM"
-      APPVEYOR_BUILD_WORKER_IMAGE: "Visual Studio 2017"
-
-  install:
-  - ECHO Installing %COMPILER% %PLATFORM% %CONFIGURATION%
-  - SET PATH_ORIGINAL=%PATH%
-  - if [%HOST%]==[cygwin] (
-      ECHO Installing Cygwin Packages &&
-      C:\cygwin64\setup-x86_64.exe -qnNdO -R "C:\cygwin64" -g -P ^
-        gcc,^
-        cmake,^
-        make
-    )
-  - IF [%HOST%]==[visual] IF [%PLATFORM%]==[x64] (
-      SET ADDITIONALPARAM=/p:LibraryPath="C:\Program Files\Microsoft SDKs\Windows\v7.1\lib\x64;c:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\lib\amd64;C:\Program Files (x86)\Microsoft Visual Studio 10.0\;C:\Program Files (x86)\Microsoft Visual Studio 10.0\lib\amd64;"
-    )
-
-  build_script:
-  - ECHO Building %COMPILER% %PLATFORM% %CONFIGURATION%
-  - if [%HOST%]==[cygwin] (
-      set CHERE_INVOKING=yes &&
-      set CC=%COMPILER% &&
-      C:\cygwin64\bin\bash --login -c "
-        set -e;
-        cd build/cmake;
-        CFLAGS='-Werror' cmake -G 'Unix Makefiles' -DCMAKE_BUILD_TYPE=Debug -DZSTD_BUILD_TESTS:BOOL=ON -DZSTD_FUZZER_FLAGS=-T20s -DZSTD_ZSTREAM_FLAGS=-T20s -DZSTD_FULLBENCH_FLAGS=-i0 .;
-        make VERBOSE=1 -j;
-        ctest -V -L Medium;
-      "
-    )
-  - if [%HOST%]==[cmake-visual] (
-      ECHO *** &&
-      ECHO *** Building %CMAKE_GENERATOR% ^(%CMAKE_GENERATOR_TOOLSET%^) %PLATFORM%\%CONFIGURATION% &&
-      PUSHD build\cmake &&
-      cmake -DBUILD_TESTING=ON . &&
-      cmake --build . --config %CONFIGURATION% -j4 &&
-      POPD &&
-      ECHO ***
-    )
-  - if [%HOST%]==[visual] (
-      ECHO *** &&
-      ECHO *** Building Visual Studio 2012 %PLATFORM%\%CONFIGURATION% &&
-      ECHO *** &&
-      msbuild "build\VS2010\zstd.sln" /m /verbosity:minimal /property:PlatformToolset=v110 /p:ForceImportBeforeCppTargets=%APPVEYOR_BUILD_FOLDER%\build\VS2010\CompileAsCpp.props /t:Clean,Build /p:Platform=%PLATFORM% /p:Configuration=%CONFIGURATION% /logger:"C:\Program Files\AppVeyor\BuildAgent\Appveyor.MSBuildLogger.dll" &&
-      DIR build\VS2010\bin\%PLATFORM%_%CONFIGURATION%\*.exe &&
-      msbuild "build\VS2010\zstd.sln" /m /verbosity:minimal /property:PlatformToolset=v110 /t:Clean,Build /p:Platform=%PLATFORM% /p:Configuration=%CONFIGURATION% /logger:"C:\Program Files\AppVeyor\BuildAgent\Appveyor.MSBuildLogger.dll" &&
-      DIR build\VS2010\bin\%PLATFORM%_%CONFIGURATION%\*.exe
-    )
-
-
-  test_script:
-  - ECHO Testing %COMPILER% %PLATFORM% %CONFIGURATION%
-  - SET "FUZZERTEST=-T10s"
-  - if [%HOST%]==[mingw] (
-      set "CC=%COMPILER%" &&
-      make clean &&
-      make check
-    )

zstd.mod/zstd/build/VS2008/zstd/zstd.vcproj

@@ -356,6 +356,10 @@
 				RelativePath="..\..\..\programs\dibio.c"
 				>
 			</File>
+			<File
+				RelativePath="..\..\..\programs\lorem.c"
+				>
+			</File>
 			<File
 				RelativePath="..\..\..\lib\dictBuilder\cover.c"
 				>

zstd.mod/zstd/build/VS2010/datagen/datagen.vcxproj

@@ -157,6 +157,8 @@
   <ItemGroup>
     <ClCompile Include="..\..\..\programs\util.c" />
     <ClCompile Include="..\..\..\programs\datagen.c" />
+    <ClCompile Include="..\..\..\programs\lorem.c" />
+    <ClCompile Include="..\..\..\tests\loremOut.c" />
     <ClCompile Include="..\..\..\tests\datagencli.c" />
   </ItemGroup>
   <ItemGroup>

zstd.mod/zstd/build/VS2010/fullbench-dll/fullbench-dll.vcxproj

@@ -1,189 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|Win32">
-      <Configuration>Debug</Configuration>
-      <Platform>Win32</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|Win32">
-      <Configuration>Release</Configuration>
-      <Platform>Win32</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{00000000-1CC8-4FD7-9281-6B8DBB9D3DF8}</ProjectGuid>
-    <Keyword>Win32Proj</Keyword>
-    <RootNamespace>fullbench-dll</RootNamespace>
-    <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>Application</ConfigurationType>
-    <UseDebugLibraries>true</UseDebugLibraries>
-    <CharacterSet>MultiByte</CharacterSet>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
-    <ConfigurationType>Application</ConfigurationType>
-    <UseDebugLibraries>true</UseDebugLibraries>
-    <CharacterSet>MultiByte</CharacterSet>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
-    <ConfigurationType>Application</ConfigurationType>
-    <UseDebugLibraries>false</UseDebugLibraries>
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-    <CharacterSet>MultiByte</CharacterSet>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
-    <ConfigurationType>Application</ConfigurationType>
-    <UseDebugLibraries>false</UseDebugLibraries>
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-    <CharacterSet>MultiByte</CharacterSet>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
-    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
-  </ImportGroup>
-  <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="PropertySheets">
-    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
-    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
-  </ImportGroup>
-  <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="PropertySheets">
-    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
-    <LinkIncremental>true</LinkIncremental>
-    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(UniversalCRT_IncludePath);</IncludePath>
-    <RunCodeAnalysis>false</RunCodeAnalysis>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
-    <LinkIncremental>true</LinkIncremental>
-    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(UniversalCRT_IncludePath);</IncludePath>
-    <RunCodeAnalysis>false</RunCodeAnalysis>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
-    <LinkIncremental>false</LinkIncremental>
-    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(UniversalCRT_IncludePath);</IncludePath>
-    <RunCodeAnalysis>false</RunCodeAnalysis>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
-    <LinkIncremental>false</LinkIncremental>
-    <IncludePath>$(IncludePath);$(SolutionDir)..\..\lib;$(SolutionDir)..\..\programs;$(SolutionDir)..\..\lib\legacy;$(SolutionDir)..\..\lib\common;$(UniversalCRT_IncludePath);</IncludePath>
-    <RunCodeAnalysis>false</RunCodeAnalysis>
-  </PropertyGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
-    <ClCompile>
-      <PrecompiledHeader>
-      </PrecompiledHeader>
-      <WarningLevel>Level4</WarningLevel>
-      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;ZSTD_DLL_IMPORT=1;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <TreatWarningAsError>true</TreatWarningAsError>
-      <EnablePREfast>false</EnablePREfast>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <AdditionalLibraryDirectories>$(SolutionDir)bin\$(Platform)_$(Configuration);%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
-    <ClCompile>
-      <PrecompiledHeader>
-      </PrecompiledHeader>
-      <WarningLevel>Level4</WarningLevel>
-      <Optimization>Disabled</Optimization>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;ZSTD_DLL_IMPORT=1;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <TreatWarningAsError>true</TreatWarningAsError>
-      <EnablePREfast>false</EnablePREfast>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <AdditionalLibraryDirectories>$(SolutionDir)bin\$(Platform)_$(Configuration);%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
-    <ClCompile>
-      <WarningLevel>Level4</WarningLevel>
-      <PrecompiledHeader>
-      </PrecompiledHeader>
-      <Optimization>MaxSpeed</Optimization>
-      <FunctionLevelLinking>true</FunctionLevelLinking>
-      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;ZSTD_DLL_IMPORT=1;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <EnablePREfast>false</EnablePREfast>
-      <TreatWarningAsError>false</TreatWarningAsError>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <EnableCOMDATFolding>true</EnableCOMDATFolding>
-      <OptimizeReferences>true</OptimizeReferences>
-      <AdditionalLibraryDirectories>$(SolutionDir)bin\$(Platform)_$(Configuration);%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
-    <ClCompile>
-      <WarningLevel>Level4</WarningLevel>
-      <PrecompiledHeader>
-      </PrecompiledHeader>
-      <Optimization>MaxSpeed</Optimization>
-      <FunctionLevelLinking>true</FunctionLevelLinking>
-      <IntrinsicFunctions>true</IntrinsicFunctions>
-      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;ZSTD_DLL_IMPORT=1;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <TreatWarningAsError>false</TreatWarningAsError>
-      <EnablePREfast>false</EnablePREfast>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <EnableCOMDATFolding>true</EnableCOMDATFolding>
-      <OptimizeReferences>true</OptimizeReferences>
-      <AdditionalLibraryDirectories>$(SolutionDir)bin\$(Platform)_$(Configuration);%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <ClCompile Include="..\..\..\lib\common\xxhash.c" />
-    <ClCompile Include="..\..\..\programs\util.c" />
-    <ClCompile Include="..\..\..\programs\timefn.c" />
-    <ClCompile Include="..\..\..\programs\datagen.c" />
-    <ClCompile Include="..\..\..\programs\benchfn.c" />
-    <ClCompile Include="..\..\..\tests\fullbench.c" />
-  </ItemGroup>
-  <ItemGroup>
-    <ClInclude Include="..\..\..\lib\zstd.h" />
-    <ClInclude Include="..\..\..\programs\datagen.h" />
-    <ClInclude Include="..\..\..\programs\benchfn.h" />
-    <ClInclude Include="..\..\..\programs\util.h" />
-  </ItemGroup>
-  <ItemGroup>
-    <ProjectReference Include="..\libzstd-dll\libzstd-dll.vcxproj">
-      <Project>{00000000-94d5-4bf9-8a50-7bd9929a0850}</Project>
-    </ProjectReference>
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-  </ImportGroup>
-</Project>

zstd.mod/zstd/build/VS2010/fullbench/fullbench.vcxproj

@@ -170,6 +170,7 @@
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_superblock.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_preSplit.c" />
     <ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
@@ -183,6 +184,7 @@
     <ClCompile Include="..\..\..\programs\util.c" />
     <ClCompile Include="..\..\..\programs\timefn.c" />
     <ClCompile Include="..\..\..\programs\datagen.c" />
+    <ClCompile Include="..\..\..\programs\lorem.c" />
     <ClCompile Include="..\..\..\programs\benchfn.c" />
     <ClCompile Include="..\..\..\tests\fullbench.c" />
   </ItemGroup>

zstd.mod/zstd/build/VS2010/fuzzer/fuzzer.vcxproj

@@ -170,6 +170,7 @@
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_superblock.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_preSplit.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />

zstd.mod/zstd/build/VS2010/libzstd-dll/libzstd-dll.vcxproj

@@ -34,6 +34,7 @@
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_superblock.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_preSplit.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />

zstd.mod/zstd/build/VS2010/libzstd/libzstd.vcxproj

@@ -34,6 +34,7 @@
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_superblock.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_preSplit.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />

zstd.mod/zstd/build/VS2010/zstd.sln

@@ -7,11 +7,6 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "fuzzer", "fuzzer\fuzzer.vcx
 EndProject
 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "fullbench", "fullbench\fullbench.vcxproj", "{61ABD629-1CC8-4FD7-9281-6B8DBB9D3DF8}"
 EndProject
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "fullbench-dll", "fullbench-dll\fullbench-dll.vcxproj", "{00000000-1CC8-4FD7-9281-6B8DBB9D3DF8}"
-	ProjectSection(ProjectDependencies) = postProject
-		{00000000-94D5-4BF9-8A50-7BD9929A0850} = {00000000-94D5-4BF9-8A50-7BD9929A0850}
-	EndProjectSection
-EndProject
 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "datagen", "datagen\datagen.vcxproj", "{037E781E-81A6-494B-B1B3-438AB1200523}"
 EndProject
 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "libzstd", "libzstd\libzstd.vcxproj", "{8BFD8150-94D5-4BF9-8A50-7BD9929A0850}"

zstd.mod/zstd/build/VS2010/zstd/zstd.vcxproj

@@ -35,6 +35,7 @@
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_literals.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_sequences.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_compress_superblock.c" />
+    <ClCompile Include="..\..\..\lib\compress\zstd_preSplit.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_double_fast.c" />
     <ClCompile Include="..\..\..\lib\compress\zstd_lazy.c" />
@@ -63,6 +64,7 @@
     <ClCompile Include="..\..\..\programs\dibio.c" />
     <ClCompile Include="..\..\..\programs\fileio.c" />
     <ClCompile Include="..\..\..\programs\fileio_asyncio.c" />
+    <ClCompile Include="..\..\..\programs\lorem.c" />
     <ClCompile Include="..\..\..\programs\zstdcli.c" />
     <ClCompile Include="..\..\..\programs\zstdcli_trace.c" />
   </ItemGroup>

zstd.mod/zstd/build/VS_scripts/build.VSPreview.cmd

@@ -0,0 +1,7 @@
+@echo off
+
+rem build 32-bit
+call "%~p0%build.generic.cmd" preview Win32 Release v143
+
+rem build 64-bit
+call "%~p0%build.generic.cmd" preview x64 Release v143

zstd.mod/zstd/build/VS_scripts/build.generic.cmd

@@ -2,7 +2,7 @@
 
 IF "%1%" == "" GOTO display_help
 
-SETLOCAL
+SETLOCAL ENABLEDELAYEDEXPANSION
 
 SET msbuild_version=%1
 
@@ -19,39 +19,34 @@ GOTO build
 :display_help
 
 echo Syntax: build.generic.cmd msbuild_version msbuild_platform msbuild_configuration msbuild_toolset
-echo   msbuild_version:          VS installed version (VS2012, VS2013, VS2015, VS2017, VS2019, ...)
+echo   msbuild_version:          VS installed version (latest, VS2012, VS2013, VS2015, VS2017, VS2019, VS2022, ...)
 echo   msbuild_platform:         Platform (x64 or Win32)
 echo   msbuild_configuration:    VS configuration (Release or Debug)
-echo   msbuild_toolset:          Platform Toolset (v100, v110, v120, v140, v141, v142, ...)
+echo   msbuild_toolset:          Platform Toolset (v100, v110, v120, v140, v141, v142, v143, ...)
 
 EXIT /B 1
 
 :build
 
 SET msbuild="%windir%\Microsoft.NET\Framework\v4.0.30319\MSBuild.exe"
-SET msbuild_vs2017community="%programfiles(x86)%\Microsoft Visual Studio\2017\Community\MSBuild\15.0\Bin\MSBuild.exe"
-SET msbuild_vs2017professional="%programfiles(x86)%\Microsoft Visual Studio\2017\Professional\MSBuild\15.0\Bin\MSBuild.exe"
-SET msbuild_vs2017enterprise="%programfiles(x86)%\Microsoft Visual Studio\2017\Enterprise\MSBuild\15.0\Bin\MSBuild.exe"
 IF %msbuild_version% == VS2013 SET msbuild="%programfiles(x86)%\MSBuild\12.0\Bin\MSBuild.exe"
 IF %msbuild_version% == VS2015 SET msbuild="%programfiles(x86)%\MSBuild\14.0\Bin\MSBuild.exe"
-IF %msbuild_version% == VS2017Community SET msbuild=%msbuild_vs2017community%
-IF %msbuild_version% == VS2017Professional SET msbuild=%msbuild_vs2017professional%
-IF %msbuild_version% == VS2017Enterprise SET msbuild=%msbuild_vs2017enterprise%
-IF %msbuild_version% == VS2017 (
-	IF EXIST %msbuild_vs2017community% SET msbuild=%msbuild_vs2017community%
-	IF EXIST %msbuild_vs2017professional% SET msbuild=%msbuild_vs2017professional%
-	IF EXIST %msbuild_vs2017enterprise% SET msbuild=%msbuild_vs2017enterprise%
-)
-
-:: VS2019
-SET msbuild_vs2019community="%programfiles(x86)%\Microsoft Visual Studio\2019\Community\MSBuild\Current\Bin\MSBuild.exe"
-SET msbuild_vs2019professional="%programfiles(x86)%\Microsoft Visual Studio\2019\Professional\MSBuild\Current\Bin\MSBuild.exe"
-SET msbuild_vs2019enterprise="%programfiles(x86)%\Microsoft Visual Studio\2019\Enterprise\MSBuild\Current\Bin\MSBuild.exe"
-IF %msbuild_version% == VS2019 (
-	IF EXIST %msbuild_vs2019community% SET msbuild=%msbuild_vs2019community%
-	IF EXIST %msbuild_vs2019professional% SET msbuild=%msbuild_vs2019professional%
-	IF EXIST %msbuild_vs2019enterprise% SET msbuild=%msbuild_vs2019enterprise%
+IF %msbuild_version% == VS2017 SET vswhere_params=-version [15,16) -products *
+IF %msbuild_version% == VS2017Community SET vswhere_params=-version [15,16) -products Community
+IF %msbuild_version% == VS2017Enterprise SET vswhere_params=-version [15,16) -products Enterprise
+IF %msbuild_version% == VS2017Professional SET vswhere_params=-version [15,16) -products Professional
+IF %msbuild_version% == VS2019 SET vswhere_params=-version [16,17) -products *
+IF %msbuild_version% == VS2022 SET vswhere_params=-version [17,18) -products *
+REM Add the next Visual Studio version here.
+IF %msbuild_version% == latest SET vswhere_params=-latest -products *
+IF %msbuild_version% == preview SET vswhere_params=-prerelease -products *
+
+IF NOT DEFINED vswhere_params GOTO skip_vswhere
+SET vswhere="%ProgramFiles(x86)%\Microsoft Visual Studio\Installer\vswhere.exe"
+FOR /F "USEBACKQ TOKENS=*" %%F IN (`%vswhere% !vswhere_params! -requires Microsoft.Component.MSBuild -find MSBuild\**\Bin\MSBuild.exe`) DO (
+	SET msbuild="%%F"
 )
+:skip_vswhere
 
 SET project="%~p0\..\VS2010\zstd.sln"
 

zstd.mod/zstd/build/cmake/CMakeLists.txt

@@ -7,16 +7,14 @@
 # in the COPYING file in the root directory of this source tree).
 # ################################################################
 
-cmake_minimum_required(VERSION 2.8.12 FATAL_ERROR)
+cmake_minimum_required(VERSION 3.10 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}")
+if("${ZSTD_MAX_VALIDATED_CMAKE_MAJOR_VERSION}" EQUAL "${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")
@@ -32,24 +30,16 @@ set(LIBRARY_DIR ${ZSTD_SOURCE_DIR}/lib)
 include(GetZstdLibraryVersion)
 GetZstdLibraryVersion(${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(ASM) # And ASM
-  enable_language(CXX) # Testing contributed code also utilizes CXX
-else()
-  project(zstd
-    VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}"
-    LANGUAGES C   # Main library is in C
-              ASM # And ASM
-              CXX # Testing contributed code also utilizes CXX
-    )
-endif()
+set(ZSTD_SHORT_VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}")
+set(ZSTD_FULL_VERSION "${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}")
+
+project(zstd
+  VERSION "${ZSTD_FULL_VERSION}"
+  LANGUAGES C   # Main library is in C
+            ASM # And ASM
+            CXX # Testing contributed code also utilizes CXX
+  )
+
 message(STATUS "ZSTD VERSION: ${zstd_VERSION}")
 set(zstd_HOMEPAGE_URL "https://facebook.github.io/zstd")
 set(zstd_DESCRIPTION  "Zstandard is a real-time compression algorithm, providing high compression ratios.")
@@ -95,8 +85,17 @@ else ()
     add_definitions(-DZSTD_LEGACY_SUPPORT=0)
 endif ()
 
+if (APPLE)
+    option(ZSTD_FRAMEWORK "Build as Apple Frameworks" OFF)
+endif ()
+
 if (ANDROID)
     set(ZSTD_MULTITHREAD_SUPPORT_DEFAULT OFF)
+    # Old versions of bionic libc don't have fseeko/ftello
+    if ((NOT ${ANDROID_PLATFORM_LEVEL}) OR ${ANDROID_PLATFORM_LEVEL} VERSION_LESS 24)
+        message(STATUS "Setting compile definitions for old Android API")
+        add_compile_definitions(LIBC_NO_FSEEKO)
+    endif ()
 else()
     set(ZSTD_MULTITHREAD_SUPPORT_DEFAULT ON)
 endif()
@@ -127,10 +126,26 @@ endif ()
 #-----------------------------------------------------------------------------
 # External dependencies
 #-----------------------------------------------------------------------------
+# Define a function to handle special thread settings for HP-UX
+# See https://github.com/facebook/zstd/pull/3862 for details.
+function(setup_hpux_threads)
+    find_package(Threads)
+    if (NOT Threads_FOUND)
+        set(CMAKE_USE_PTHREADS_INIT 1 PARENT_SCOPE)
+        set(CMAKE_THREAD_LIBS_INIT -lpthread PARENT_SCOPE)
+        set(CMAKE_HAVE_THREADS_LIBRARY 1 PARENT_SCOPE)
+        set(Threads_FOUND TRUE PARENT_SCOPE)
+    endif()
+endfunction()
+
 if (ZSTD_MULTITHREAD_SUPPORT AND UNIX)
-    set(THREADS_PREFER_PTHREAD_FLAG ON)
-    find_package(Threads REQUIRED)
-    if(CMAKE_USE_PTHREADS_INIT)
+    if (CMAKE_SYSTEM_NAME MATCHES "HP-UX")
+        setup_hpux_threads()
+    else()
+        set(THREADS_PREFER_PTHREAD_FLAG ON)
+        find_package(Threads REQUIRED)
+    endif()
+    if (CMAKE_USE_PTHREADS_INIT)
         set(THREADS_LIBS "${CMAKE_THREAD_LIBS_INIT}")
     else()
         message(SEND_ERROR "ZSTD currently does not support thread libraries other than pthreads")
@@ -193,10 +208,6 @@ export(EXPORT zstdExports
     FILE "${CMAKE_CURRENT_BINARY_DIR}/zstdTargets.cmake"
     NAMESPACE zstd::
     )
-configure_file(zstdConfig.cmake
-    "${CMAKE_CURRENT_BINARY_DIR}/zstdConfig.cmake"
-    COPYONLY
-    )
 
 # A Package Config file that works from the installation directory
 set(ConfigPackageLocation ${CMAKE_INSTALL_LIBDIR}/cmake/zstd)
@@ -205,8 +216,13 @@ install(EXPORT zstdExports
     NAMESPACE zstd::
     DESTINATION ${ConfigPackageLocation}
     )
+configure_package_config_file(
+    zstdConfig.cmake.in
+    "${CMAKE_CURRENT_BINARY_DIR}/zstdConfig.cmake"
+    INSTALL_DESTINATION ${ConfigPackageLocation}
+)
 install(FILES
-    zstdConfig.cmake
+    "${CMAKE_CURRENT_BINARY_DIR}/zstdConfig.cmake"
     "${CMAKE_CURRENT_BINARY_DIR}/zstdConfigVersion.cmake"
     DESTINATION ${ConfigPackageLocation}
     )

zstd.mod/zstd/build/cmake/CMakeModules/AddZstdCompilationFlags.cmake

@@ -1,11 +1,10 @@
 include(CheckCXXCompilerFlag)
 include(CheckCCompilerFlag)
-# VERSION_GREATER_EQUAL requires CMake 3.7 or later.
-# https://cmake.org/cmake/help/latest/command/if.html#version-greater-equal
-if (CMAKE_VERSION VERSION_LESS 3.18)
-    set(ZSTD_HAVE_CHECK_LINKER_FLAG false)
-else ()
+
+if (CMAKE_VERSION VERSION_GREATER_EQUAL 3.18)
     set(ZSTD_HAVE_CHECK_LINKER_FLAG true)
+else ()
+    set(ZSTD_HAVE_CHECK_LINKER_FLAG false)
 endif ()
 if (ZSTD_HAVE_CHECK_LINKER_FLAG)
     include(CheckLinkerFlag)
@@ -51,13 +50,17 @@ function(EnableCompilerFlag _flag _C _CXX _LD)
 endfunction()
 
 macro(ADD_ZSTD_COMPILATION_FLAGS)
+    # We set ZSTD_HAS_NOEXECSTACK if we are certain we've set all the required
+    # compiler flags to mark the stack as non-executable.
+    set(ZSTD_HAS_NOEXECSTACK false)
+
     if (CMAKE_CXX_COMPILER_ID MATCHES "GNU|Clang" OR MINGW) #Not only UNIX but also WIN32 for MinGW
         # It's possible to select the exact standard used for compilation.
         # It's not necessary, but can be employed for specific purposes.
         # Note that zstd source code is compatible with both C++98 and above
         # and C-gnu90 (c90 + long long + variadic macros ) and above
         # EnableCompilerFlag("-std=c++11" false true) # Set C++ compilation to c++11 standard
-        # EnableCompilerFlag("-std=c99" true false)   # Set C compiation to c99 standard
+        # EnableCompilerFlag("-std=c99" true false)   # Set C compilation to c99 standard
         if (CMAKE_CXX_COMPILER_ID MATCHES "Clang" AND MSVC)
             # clang-cl normally maps -Wall to -Weverything.
             EnableCompilerFlag("/clang:-Wall" true true false)
@@ -76,10 +79,22 @@ macro(ADD_ZSTD_COMPILATION_FLAGS)
         endif ()
         # Add noexecstack flags
         # LDFLAGS
-        EnableCompilerFlag("-z noexecstack" false false true)
+        EnableCompilerFlag("-Wl,-z,noexecstack" false false true)
         # CFLAGS & CXXFLAGS
         EnableCompilerFlag("-Qunused-arguments" true true false)
         EnableCompilerFlag("-Wa,--noexecstack" true true false)
+        # NOTE: Using 3 nested ifs because the variables are sometimes
+        # empty if the condition is false, and sometimes equal to false.
+        # This implicitly converts them to truthy values. There may be
+        # a better way to do this, but this reliably works.
+        if (${LD_FLAG_WL_Z_NOEXECSTACK})
+            if (${C_FLAG_WA_NOEXECSTACK})
+                if (${CXX_FLAG_WA_NOEXECSTACK})
+                    # We've succeeded in marking the stack as non-executable
+                    set(ZSTD_HAS_NOEXECSTACK true)
+                endif()
+            endif()
+        endif()
     elseif (MSVC) # Add specific compilation flags for Windows Visual
 
         set(ACTIVATE_MULTITHREADED_COMPILATION "ON" CACHE BOOL "activate multi-threaded compilation (/MP flag)")

zstd.mod/zstd/build/cmake/README.md

@@ -41,6 +41,48 @@ cmake -DZSTD_BUILD_TESTS=ON -DZSTD_LEGACY_SUPPORT=OFF ..
 make
 ```
 
+**Apple Frameworks**
+It's generally recommended to have CMake with versions higher than 3.14 for [iOS-derived platforms](https://cmake.org/cmake/help/latest/manual/cmake-toolchains.7.html#id27).
+```sh
+cmake -S. -B build-cmake -DZSTD_FRAMEWORK=ON -DCMAKE_SYSTEM_NAME=iOS
+```
+Or you can utilize [iOS-CMake](https://github.com/leetal/ios-cmake) toolchain for CMake versions lower than 3.14
+```sh
+cmake -B build -G Xcode -DCMAKE_TOOLCHAIN_FILE=<Path To ios.toolchain.cmake> -DPLATFORM=OS64 -DZSTD_FRAMEWORK=ON
+```
+
+### how to use it with CMake FetchContent
+
+For all options available, you can see it on <https://github.com/facebook/zstd/blob/dev/build/cmake/lib/CMakeLists.txt>
+```cmake
+include(FetchContent)
+
+set(ZSTD_BUILD_STATIC ON)
+set(ZSTD_BUILD_SHARED OFF)
+
+FetchContent_Declare(
+    zstd
+    URL "https://github.com/facebook/zstd/releases/download/v1.5.5/zstd-1.5.5.tar.gz"
+    DOWNLOAD_EXTRACT_TIMESTAMP TRUE
+    SOURCE_SUBDIR build/cmake
+)
+
+FetchContent_MakeAvailable(zstd)
+
+target_link_libraries(
+    ${PROJECT_NAME}
+    PRIVATE
+    libzstd_static
+)
+
+# On windows and macos this is needed
+target_include_directories(
+    ${PROJECT_NAME}
+    PRIVATE
+    ${zstd_SOURCE_DIR}/lib
+)
+```
+
 ### 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)
 

zstd.mod/zstd/build/cmake/contrib/pzstd/CMakeLists.txt

@@ -18,6 +18,7 @@ set(PZSTD_DIR ${ZSTD_SOURCE_DIR}/contrib/pzstd)
 include_directories(${PROGRAMS_DIR} ${LIBRARY_DIR} ${LIBRARY_DIR}/common ${PZSTD_DIR})
 
 add_executable(pzstd ${PROGRAMS_DIR}/util.c ${PZSTD_DIR}/main.cpp ${PZSTD_DIR}/Options.cpp ${PZSTD_DIR}/Pzstd.cpp ${PZSTD_DIR}/SkippableFrame.cpp)
+target_compile_features(pzstd PRIVATE cxx_std_11)
 set_property(TARGET pzstd APPEND PROPERTY COMPILE_DEFINITIONS "NDEBUG")
 set_property(TARGET pzstd APPEND PROPERTY COMPILE_OPTIONS "-Wno-shadow")
 

zstd.mod/zstd/build/cmake/lib/CMakeLists.txt

@@ -12,45 +12,70 @@ project(libzstd C ASM)
 set(CMAKE_INCLUDE_CURRENT_DIR TRUE)
 option(ZSTD_BUILD_STATIC "BUILD STATIC LIBRARIES" ON)
 option(ZSTD_BUILD_SHARED "BUILD SHARED LIBRARIES" ON)
+option(ZSTD_BUILD_COMPRESSION "BUILD COMPRESSION MODULE" ON)
+option(ZSTD_BUILD_DECOMPRESSION "BUILD DECOMPRESSION MODULE" ON)
+option(ZSTD_BUILD_DICTBUILDER "BUILD DICTBUILDER MODULE" ON)
+option(ZSTD_BUILD_DEPRECATED "BUILD DEPRECATED MODULE" OFF)
+
+set(ZSTDLIB_VISIBLE "" CACHE STRING "Visibility for ZSTDLIB API")
+set(ZSTDERRORLIB_VISIBLE "" CACHE STRING "Visibility for ZSTDERRORLIB_VISIBLE API")
+set(ZDICTLIB_VISIBLE "" CACHE STRING "Visibility for ZDICTLIB_VISIBLE API")
+set(ZSTDLIB_STATIC_API "" CACHE STRING "Visibility for ZSTDLIB_STATIC_API API")
+set(ZDICTLIB_STATIC_API "" CACHE STRING "Visibility for ZDICTLIB_STATIC_API API")
+
+set_property(CACHE ZSTDLIB_VISIBLE PROPERTY STRINGS "" "hidden" "default" "protected" "internal")
+set_property(CACHE ZSTDERRORLIB_VISIBLE PROPERTY STRINGS "" "hidden" "default" "protected" "internal")
+set_property(CACHE ZDICTLIB_VISIBLE PROPERTY STRINGS "" "hidden" "default" "protected" "internal")
+set_property(CACHE ZSTDLIB_STATIC_API PROPERTY STRINGS "" "hidden" "default" "protected" "internal")
+set_property(CACHE ZDICTLIB_STATIC_API PROPERTY STRINGS "" "hidden" "default" "protected" "internal")
 
 if(NOT ZSTD_BUILD_SHARED AND NOT ZSTD_BUILD_STATIC)
     message(SEND_ERROR "You need to build at least one flavor of libzstd")
 endif()
 
-# Define library directory, where sources and header files are located
-include_directories(${LIBRARY_DIR} ${LIBRARY_DIR}/common)
-
 file(GLOB CommonSources ${LIBRARY_DIR}/common/*.c)
 file(GLOB CompressSources ${LIBRARY_DIR}/compress/*.c)
+file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c)
 if (MSVC)
-    file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c)
     add_compile_options(-DZSTD_DISABLE_ASM)
 else ()
-    file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c ${LIBRARY_DIR}/decompress/*.S)
+    if(CMAKE_SYSTEM_PROCESSOR MATCHES "amd64.*|AMD64.*|x86_64.*|X86_64.*" AND ${ZSTD_HAS_NOEXECSTACK})
+        set(DecompressSources ${DecompressSources} ${LIBRARY_DIR}/decompress/huf_decompress_amd64.S)
+    else()
+        add_compile_options(-DZSTD_DISABLE_ASM)
+    endif()
 endif ()
 file(GLOB DictBuilderSources ${LIBRARY_DIR}/dictBuilder/*.c)
+file(GLOB DeprecatedSources ${LIBRARY_DIR}/deprecated/*.c)
 
-set(Sources
-        ${CommonSources}
-        ${CompressSources}
-        ${DecompressSources}
-        ${DictBuilderSources})
-
+file(GLOB PublicHeaders ${LIBRARY_DIR}/*.h)
 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
-        ${CommonHeaders}
-        ${CompressHeaders}
-        ${DecompressHeaders}
-        ${DictBuilderHeaders})
+set(Sources ${CommonSources})
+set(Headers ${PublicHeaders} ${CommonHeaders})
+if (ZSTD_BUILD_COMPRESSION)
+    set(Sources ${Sources} ${CompressSources})
+    set(Headers ${Headers} ${CompressHeaders})
+endif()
+if (ZSTD_BUILD_DECOMPRESSION)
+    set(Sources ${Sources} ${DecompressSources})
+    set(Headers ${Headers} ${DecompressHeaders})
+endif()
+if (ZSTD_BUILD_DICTBUILDER)
+    set(Sources ${Sources} ${DictBuilderSources})
+    set(Headers ${Headers} ${DictBuilderHeaders})
+endif()
+if (ZSTD_BUILD_DEPRECATED)
+    set(Sources ${Sources} ${DeprecatedSources})
+    set(Headers ${Headers} ${DeprecatedHeaders})
+endif()
 
 if (ZSTD_LEGACY_SUPPORT)
     set(LIBRARY_LEGACY_DIR ${LIBRARY_DIR}/legacy)
-    include_directories(${LIBRARY_LEGACY_DIR})
 
     set(Sources ${Sources}
             ${LIBRARY_LEGACY_DIR}/zstd_v01.c
@@ -81,22 +106,38 @@ endif ()
 # Our assembly expects to be compiled by a C compiler, and is only enabled for
 # __GNUC__ compatible compilers. Otherwise all the ASM code is disabled by
 # macros.
-set_source_files_properties(${Sources} PROPERTIES LANGUAGE C)
+if(NOT CMAKE_ASM_COMPILER STREQUAL CMAKE_C_COMPILER)
+    set_source_files_properties(${Sources} PROPERTIES LANGUAGE C)
+endif()
+
+macro (add_definition target var)
+    if (NOT ("${${var}}" STREQUAL ""))
+        set_property(TARGET ${target} APPEND PROPERTY COMPILE_DEFINITIONS "${var}=__attribute__((visibility(\"${${var}}\")))")
+    endif ()
+endmacro ()
 
+# Define directories containing the library's public headers
+set(PUBLIC_INCLUDE_DIRS ${LIBRARY_DIR})
+set(CMAKE_RC_FLAGS "${CMAKE_RC_FLAGS} /I \"${LIBRARY_DIR}\"")
 # Split project to static and shared libraries build
 set(library_targets)
 if (ZSTD_BUILD_SHARED)
     add_library(libzstd_shared SHARED ${Sources} ${Headers} ${PlatformDependResources})
+    target_include_directories(libzstd_shared INTERFACE $<BUILD_INTERFACE:${PUBLIC_INCLUDE_DIRS}>)
     list(APPEND library_targets libzstd_shared)
     if (ZSTD_MULTITHREAD_SUPPORT)
         set_property(TARGET libzstd_shared APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_MULTITHREAD")
         if (UNIX)
             target_link_libraries(libzstd_shared ${THREADS_LIBS})
         endif ()
-    endif()
+    endif ()
+    add_definition(libzstd_shared ZSTDLIB_VISIBLE)
+    add_definition(libzstd_shared ZSTDERRORLIB_VISIBLE)
+    add_definition(libzstd_shared ZDICTLIB_VISIBLE)
 endif ()
 if (ZSTD_BUILD_STATIC)
     add_library(libzstd_static STATIC ${Sources} ${Headers})
+    target_include_directories(libzstd_static INTERFACE $<BUILD_INTERFACE:${PUBLIC_INCLUDE_DIRS}>)
     list(APPEND library_targets libzstd_static)
     if (ZSTD_MULTITHREAD_SUPPORT)
         set_property(TARGET libzstd_static APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_MULTITHREAD")
@@ -104,6 +145,41 @@ if (ZSTD_BUILD_STATIC)
             target_link_libraries(libzstd_static ${THREADS_LIBS})
         endif ()
     endif ()
+    add_definition(libzstd_static ZSTDLIB_VISIBLE)
+    add_definition(libzstd_static ZSTDERRORLIB_VISIBLE)
+    add_definition(libzstd_static ZDICTLIB_VISIBLE)
+    add_definition(libzstd_static ZSTDLIB_STATIC_API)
+    add_definition(libzstd_static ZDICTLIB_STATIC_API)
+endif ()
+if (ZSTD_BUILD_SHARED AND NOT ZSTD_BUILD_STATIC)
+    if (NOT BUILD_SHARED_LIBS)
+        message(WARNING "BUILD_SHARED_LIBS is OFF, but ZSTD_BUILD_SHARED is ON and ZSTD_BUILD_STATIC is OFF, which takes precedence, so libzstd is a shared library")
+    endif ()
+    add_library(libzstd INTERFACE)
+    target_link_libraries(libzstd INTERFACE libzstd_shared)
+    list(APPEND library_targets libzstd)
+endif ()
+if (ZSTD_BUILD_STATIC AND NOT ZSTD_BUILD_SHARED)
+    if (BUILD_SHARED_LIBS)
+        message(WARNING "BUILD_SHARED_LIBS is ON, but ZSTD_BUILD_SHARED is OFF and ZSTD_BUILD_STATIC is ON, which takes precedence, is set so libzstd is a static library")
+    endif ()
+    add_library(libzstd INTERFACE)
+    target_link_libraries(libzstd INTERFACE libzstd_static)
+    list(APPEND library_targets libzstd)
+endif ()
+if (ZSTD_BUILD_SHARED AND ZSTD_BUILD_STATIC)
+    # If both ZSTD_BUILD_SHARED and ZSTD_BUILD_STATIC are set, which is the
+    # default, fallback to using BUILD_SHARED_LIBS to determine whether to
+    # set libzstd to static or shared.
+    if (BUILD_SHARED_LIBS)
+        add_library(libzstd INTERFACE)
+        target_link_libraries(libzstd INTERFACE libzstd_shared)
+        list(APPEND library_targets libzstd)
+    else ()
+        add_library(libzstd INTERFACE)
+        target_link_libraries(libzstd INTERFACE libzstd_static)
+        list(APPEND library_targets libzstd)
+    endif ()
 endif ()
 
 # Add specific compile definitions for MSVC project
@@ -129,8 +205,28 @@ if (ZSTD_BUILD_SHARED)
             libzstd_shared
             PROPERTIES
             OUTPUT_NAME zstd
-            VERSION ${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}
+            VERSION ${ZSTD_FULL_VERSION}
             SOVERSION ${zstd_VERSION_MAJOR})
+            
+    if (ZSTD_FRAMEWORK)
+        set_target_properties(
+                libzstd_shared
+                PROPERTIES
+                FRAMEWORK TRUE
+                FRAMEWORK_VERSION "${ZSTD_FULL_VERSION}"
+                PRODUCT_BUNDLE_IDENTIFIER "github.com/facebook/zstd"
+                XCODE_ATTRIBUTE_INSTALL_PATH "@rpath"
+                PUBLIC_HEADER "${PublicHeaders}"
+                OUTPUT_NAME "zstd"
+                XCODE_ATTRIBUTE_CODE_SIGN_IDENTITY ""
+                XCODE_ATTRIBUTE_CODE_SIGNING_ALLOWED "NO"
+                XCODE_ATTRIBUTE_CODE_SIGNING_REQUIRED "NO"
+                MACOSX_FRAMEWORK_IDENTIFIER "github.com/facebook/zstd"
+                MACOSX_FRAMEWORK_BUNDLE_VERSION "${ZSTD_FULL_VERSION}"
+                MACOSX_FRAMEWORK_SHORT_VERSION_STRING "${ZSTD_SHORT_VERSION}"
+                MACOSX_RPATH TRUE
+                RESOURCE ${PublicHeaders})
+    endif ()
 endif ()
 
 if (ZSTD_BUILD_STATIC)
@@ -139,6 +235,26 @@ if (ZSTD_BUILD_STATIC)
             PROPERTIES
             POSITION_INDEPENDENT_CODE On
             OUTPUT_NAME ${STATIC_LIBRARY_BASE_NAME})
+
+    if (ZSTD_FRAMEWORK)
+        set_target_properties(
+                libzstd_static
+                PROPERTIES
+                FRAMEWORK TRUE
+                FRAMEWORK_VERSION "${ZSTD_FULL_VERSION}"
+                PRODUCT_BUNDLE_IDENTIFIER "github.com/facebook/zstd/${STATIC_LIBRARY_BASE_NAME}"
+                XCODE_ATTRIBUTE_INSTALL_PATH "@rpath"
+                PUBLIC_HEADER "${PublicHeaders}"
+                OUTPUT_NAME "${STATIC_LIBRARY_BASE_NAME}"
+                XCODE_ATTRIBUTE_CODE_SIGN_IDENTITY ""
+                XCODE_ATTRIBUTE_CODE_SIGNING_ALLOWED "NO"
+                XCODE_ATTRIBUTE_CODE_SIGNING_REQUIRED "NO"
+                MACOSX_FRAMEWORK_IDENTIFIER "github.com/facebook/zstd/${STATIC_LIBRARY_BASE_NAME}"
+                MACOSX_FRAMEWORK_BUNDLE_VERSION "${ZSTD_FULL_VERSION}"
+                MACOSX_FRAMEWORK_SHORT_VERSION_STRING "${ZSTD_SHORT_VERSION}"
+                MACOSX_RPATH TRUE
+                RESOURCE ${PublicHeaders})
+    endif ()
 endif ()
 
 # pkg-config
@@ -154,11 +270,7 @@ configure_file("${LIBRARY_DIR}/libzstd.pc.in" "${CMAKE_CURRENT_BINARY_DIR}/libzs
 install(FILES "${CMAKE_CURRENT_BINARY_DIR}/libzstd.pc" DESTINATION "${CMAKE_INSTALL_LIBDIR}/pkgconfig")
 
 # install target
-install(FILES
-    "${LIBRARY_DIR}/zstd.h"
-    "${LIBRARY_DIR}/zdict.h"
-    "${LIBRARY_DIR}/zstd_errors.h"
-    DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")
+install(FILES ${PublicHeaders} DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")
 
 install(TARGETS ${library_targets}
     EXPORT zstdExports
@@ -167,6 +279,8 @@ install(TARGETS ${library_targets}
     LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
     RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
     BUNDLE DESTINATION "${CMAKE_INSTALL_BINDIR}"
+    FRAMEWORK DESTINATION "${CMAKE_INSTALL_LIBDIR}" COMPONENT runtime OPTIONAL
+    PUBLIC_HEADER DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
     )
 
 # uninstall target

zstd.mod/zstd/build/cmake/programs/CMakeLists.txt

@@ -32,7 +32,12 @@ if (MSVC)
     set(PlatformDependResources ${MSVC_RESOURCE_DIR}/zstd.rc)
 endif ()
 
-add_executable(zstd ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/fileio_asyncio.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/dibio.c ${PROGRAMS_DIR}/zstdcli_trace.c ${PlatformDependResources})
+file(GLOB ZSTD_PROGRAM_SRCS "${PROGRAMS_DIR}/*.c")
+if (MSVC AND ZSTD_PROGRAMS_LINK_SHARED)
+    list(APPEND ZSTD_PROGRAM_SRCS ${LIBRARY_DIR}/common/pool.c ${LIBRARY_DIR}/common/threading.c)
+endif ()
+
+add_executable(zstd ${ZSTD_PROGRAM_SRCS})
 target_link_libraries(zstd ${PROGRAMS_ZSTD_LINK_TARGET})
 if (CMAKE_SYSTEM_NAME MATCHES "(Solaris|SunOS)")
     target_link_libraries(zstd rt)
@@ -75,7 +80,9 @@ if (UNIX)
         ${CMAKE_CURRENT_BINARY_DIR}/zstdless.1
         DESTINATION "${MAN_INSTALL_DIR}")
 
-    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/fileio_asyncio.c)
+    add_executable(zstd-frugal ${PROGRAMS_DIR}/zstdcli.c
+        ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c
+        ${PROGRAMS_DIR}/fileio.c ${PROGRAMS_DIR}/fileio_asyncio.c)
     target_link_libraries(zstd-frugal ${PROGRAMS_ZSTD_LINK_TARGET})
     set_property(TARGET zstd-frugal APPEND PROPERTY COMPILE_DEFINITIONS "ZSTD_NOBENCH;ZSTD_NODICT;ZSTD_NOTRACE")
 endif ()

zstd.mod/zstd/build/cmake/tests/CMakeLists.txt

@@ -50,18 +50,18 @@ set(PROGRAMS_DIR ${ZSTD_SOURCE_DIR}/programs)
 set(TESTS_DIR ${ZSTD_SOURCE_DIR}/tests)
 include_directories(${TESTS_DIR} ${PROGRAMS_DIR} ${LIBRARY_DIR} ${LIBRARY_DIR}/common ${LIBRARY_DIR}/compress ${LIBRARY_DIR}/dictBuilder)
 
-add_executable(datagen ${PROGRAMS_DIR}/datagen.c ${TESTS_DIR}/datagencli.c)
+add_executable(datagen ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/lorem.c ${TESTS_DIR}/loremOut.c ${TESTS_DIR}/datagencli.c)
 target_link_libraries(datagen libzstd_static)
 
 #
 # fullbench
 #
-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)
+add_executable(fullbench ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/lorem.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${TESTS_DIR}/fullbench.c)
 if (NOT MSVC)
     target_compile_options(fullbench PRIVATE "-Wno-deprecated-declarations")
 endif()
 target_link_libraries(fullbench libzstd_static)
-add_test(NAME fullbench COMMAND fullbench ${ZSTD_FULLBENCH_FLAGS})
+add_test(NAME fullbench COMMAND "$<TARGET_FILE:fullbench>" ${ZSTD_FULLBENCH_FLAGS})
 
 #
 # fuzzer
@@ -73,7 +73,7 @@ endif()
 target_link_libraries(fuzzer libzstd_static)
 AddTestFlagsOption(ZSTD_FUZZER_FLAGS "$ENV{FUZZERTEST} $ENV{FUZZER_FLAGS}"
     "Semicolon-separated list of flags to pass to the fuzzer test (see `fuzzer -h` for usage)")
-add_test(NAME fuzzer COMMAND fuzzer ${ZSTD_FUZZER_FLAGS})
+add_test(NAME fuzzer COMMAND "$<TARGET_FILE:fuzzer>" ${ZSTD_FUZZER_FLAGS})
 # Disable the timeout since the run time is too long for the default timeout of
 # 1500 seconds and varies considerably between low-end and high-end CPUs.
 # set_tests_properties(fuzzer PROPERTIES TIMEOUT 0)
@@ -88,7 +88,7 @@ endif()
 target_link_libraries(zstreamtest libzstd_static)
 AddTestFlagsOption(ZSTD_ZSTREAM_FLAGS "$ENV{ZSTREAM_TESTTIME} $ENV{FUZZER_FLAGS}"
     "Semicolon-separated list of flags to pass to the zstreamtest test (see `zstreamtest -h` for usage)")
-add_test(NAME zstreamtest COMMAND zstreamtest ${ZSTD_ZSTREAM_FLAGS})
+add_test(NAME zstreamtest COMMAND "$<TARGET_FILE:zstreamtest>" ${ZSTD_ZSTREAM_FLAGS})
 
 #
 # playTests.sh
@@ -110,7 +110,7 @@ endif()
 # Label the "Medium" set of tests (see TESTING.md)
 set_property(TEST fuzzer zstreamtest playTests APPEND PROPERTY LABELS Medium)
 
-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)
+add_executable(paramgrill ${PROGRAMS_DIR}/benchfn.c ${PROGRAMS_DIR}/benchzstd.c ${PROGRAMS_DIR}/datagen.c ${PROGRAMS_DIR}/lorem.c ${PROGRAMS_DIR}/util.c ${PROGRAMS_DIR}/timefn.c ${TESTS_DIR}/paramgrill.c)
 if (UNIX)
     target_link_libraries(paramgrill libzstd_static m) #m is math library
 else()

zstd.mod/zstd/build/cmake/zstdConfig.cmake

@@ -1 +0,0 @@
-include("${CMAKE_CURRENT_LIST_DIR}/zstdTargets.cmake")

zstd.mod/zstd/build/cmake/zstdConfig.cmake.in

@@ -0,0 +1,10 @@
+@PACKAGE_INIT@
+
+include(CMakeFindDependencyMacro)
+if(@ZSTD_MULTITHREAD_SUPPORT@ AND "@UNIX@")
+  find_dependency(Threads)
+endif()
+
+include("${CMAKE_CURRENT_LIST_DIR}/zstdTargets.cmake")
+
+check_required_components("zstd")

zstd.mod/zstd/build/meson/contrib/pzstd/meson.build

@@ -20,6 +20,6 @@ pzstd = executable('pzstd',
   pzstd_sources,
   cpp_args: pzstd_warning_flags,
   include_directories: pzstd_includes,
-  dependencies: [ libzstd_dep, thread_dep ],
+  dependencies: [ libzstd_internal_dep, thread_dep ],
   override_options: ['b_ndebug=true'],
   install: true)

zstd.mod/zstd/build/meson/lib/meson.build

@@ -30,6 +30,7 @@ libzstd_sources = [join_paths(zstd_rootdir, 'lib/common/entropy_common.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/zstd_compress_superblock.c'),
+  join_paths(zstd_rootdir, 'lib/compress/zstd_preSplit.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'),
@@ -124,7 +125,7 @@ libzstd = library('zstd',
   version: zstd_libversion)
 
 libzstd_dep = declare_dependency(link_with: libzstd,
-  include_directories: libzstd_includes)
+  include_directories: join_paths(zstd_rootdir,'lib')) # Do not expose private headers
 
 # we link to both:
 # - the shared library (for public symbols)
@@ -134,7 +135,8 @@ libzstd_dep = declare_dependency(link_with: libzstd,
 # -fvisibility=hidden means those cannot be found
 if get_option('default_library') == 'static'
   libzstd_static = libzstd
-  libzstd_internal_dep = libzstd_dep
+  libzstd_internal_dep = declare_dependency(link_with: libzstd,
+      include_directories: libzstd_includes)
 else
   if get_option('default_library') == 'shared'
     libzstd_static = static_library('zstd_objlib',
@@ -147,11 +149,13 @@ else
   if cc_id == compiler_msvc
     # msvc does not actually support linking to both, but errors out with:
     #   error LNK2005: ZSTD_<foo> already defined in zstd.lib(zstd-1.dll)
-    libzstd_internal_dep = declare_dependency(link_with: libzstd_static)
+    libzstd_internal_dep = declare_dependency(link_with: libzstd_static,
+      include_directories: libzstd_includes)
   else
     libzstd_internal_dep = declare_dependency(link_with: libzstd,
       # the static library must be linked after the shared one
-      dependencies: declare_dependency(link_with: libzstd_static))
+      dependencies: declare_dependency(link_with: libzstd_static),
+      include_directories: libzstd_includes)
   endif
 endif
 

zstd.mod/zstd/build/meson/meson.build

@@ -88,8 +88,13 @@ feature_lz4 = get_option('lz4')
 # =============================================================================
 
 libm_dep = cc.find_library('m', required: false)
-thread_dep = dependency('threads', required: feature_multi_thread)
-use_multi_thread = thread_dep.found()
+if host_machine_os == os_windows
+  thread_dep = dependency('', required: false)
+  use_multi_thread = not feature_multi_thread.disabled()
+else
+  thread_dep = dependency('threads', required: feature_multi_thread)
+  use_multi_thread = thread_dep.found()
+endif
 # Arguments in dependency should be equivalent to those passed to pkg-config
 zlib_dep = dependency('zlib', required: feature_zlib)
 use_zlib = zlib_dep.found()
@@ -111,10 +116,16 @@ if [compiler_gcc, compiler_clang].contains(cc_id)
   if cc_id == compiler_clang
     common_warning_flags += ['-Wconversion', '-Wno-sign-conversion', '-Wdocumentation']
   endif
-  cc_compile_flags = cc.get_supported_arguments(common_warning_flags + ['-Wstrict-prototypes'])
-  cxx_compile_flags = cxx.get_supported_arguments(common_warning_flags)
+  noexecstack_flags = ['-Wa,--noexecstack' ]
+  noexecstack_link_flags = ['-Wl,-z,noexecstack']
+  cc_compile_flags = cc.get_supported_arguments(common_warning_flags + noexecstack_flags + ['-Wstrict-prototypes'])
+  cxx_compile_flags = cxx.get_supported_arguments(common_warning_flags + noexecstack_flags)
   add_project_arguments(cc_compile_flags, language : 'c')
   add_project_arguments(cxx_compile_flags, language : 'cpp')
+  cc_link_flags = cc.get_supported_link_arguments(noexecstack_link_flags)
+  cxx_link_flags = cxx.get_supported_link_arguments(noexecstack_link_flags)
+  add_project_link_arguments(cc_link_flags, language: 'c')
+  add_project_link_arguments(cxx_link_flags, language: 'cpp')
 elif cc_id == compiler_msvc
   msvc_compile_flags = [ '/D_UNICODE', '/DUNICODE' ]
   if use_multi_thread

zstd.mod/zstd/build/meson/meson_options.txt

@@ -27,7 +27,7 @@ option('bin_contrib', type: 'boolean', value: false,
   description: 'Enable contrib build')
 
 option('multi_thread', type: 'feature', value: 'enabled',
-  description: 'Enable multi-threading when pthread is detected')
+  description: 'Enable multi-threading when pthread or Windows is detected')
 option('zlib', type: 'feature', value: 'auto',
   description: 'Enable zlib support')
 option('lzma', type: 'feature', value: 'auto',

zstd.mod/zstd/build/meson/programs/meson.build

@@ -18,6 +18,7 @@ zstd_programs_sources = [join_paths(zstd_rootdir, 'programs/zstdcli.c'),
   join_paths(zstd_rootdir, 'programs/benchfn.c'),
   join_paths(zstd_rootdir, 'programs/benchzstd.c'),
   join_paths(zstd_rootdir, 'programs/datagen.c'),
+  join_paths(zstd_rootdir, 'programs/lorem.c'),
   join_paths(zstd_rootdir, 'programs/dibio.c'),
   join_paths(zstd_rootdir, 'programs/zstdcli_trace.c')]
 

zstd.mod/zstd/build/meson/tests/meson.build

@@ -29,6 +29,7 @@ DECODECORPUS_TESTTIME = '-T30'
 test_includes = [ include_directories(join_paths(zstd_rootdir, 'programs')) ]
 
 testcommon_sources = [join_paths(zstd_rootdir, 'programs/datagen.c'),
+  join_paths(zstd_rootdir, 'programs/lorem.c'),
   join_paths(zstd_rootdir, 'programs/util.c'),
   join_paths(zstd_rootdir, 'programs/timefn.c'),
   join_paths(zstd_rootdir, 'programs/benchfn.c'),
@@ -43,7 +44,8 @@ testcommon_dep = declare_dependency(link_with: testcommon,
   dependencies: libzstd_deps,
   include_directories: libzstd_includes)
 
-datagen_sources = [join_paths(zstd_rootdir, 'tests/datagencli.c')]
+datagen_sources = [join_paths(zstd_rootdir, 'tests/datagencli.c'),
+  join_paths(zstd_rootdir, 'tests/loremOut.c')]
 datagen = executable('datagen',
   datagen_sources,
   c_args: [ '-DNDEBUG' ],
@@ -91,7 +93,7 @@ roundTripCrash = executable('roundTripCrash',
 longmatch_sources = [join_paths(zstd_rootdir, 'tests/longmatch.c')]
 longmatch = executable('longmatch',
   longmatch_sources,
-  dependencies: [ libzstd_dep ],
+  dependencies: [ libzstd_internal_dep ],
   install: false)
 
 invalidDictionaries_sources = [join_paths(zstd_rootdir, 'tests/invalidDictionaries.c')]

zstd.mod/zstd/build/single_file_libs/.gitignore

@@ -4,6 +4,7 @@ zstddeclib.c
 zstdenclib.c
 zstd.c
 zstd.h
+zstd_errors.h
 
 # test artifacts
 temp*

zstd.mod/zstd/build/single_file_libs/build_library_test.sh

@@ -70,6 +70,7 @@ echo "Single file library creation script: PASSED"
 
 # Copy the header to here (for the tests)
 cp "$ZSTD_SRC_ROOT/zstd.h" examples/zstd.h
+cp "$ZSTD_SRC_ROOT/zstd_errors.h" examples/zstd_errors.h
 
 # Compile the generated output
 cc -Wall -Wextra -Werror -Wshadow -pthread -I. -Os -g0 -o $OUT_FILE zstd.c examples/roundtrip.c

zstd.mod/zstd/build/single_file_libs/zstd-in.c

@@ -69,6 +69,7 @@
 #include "compress/zstd_compress_literals.c"
 #include "compress/zstd_compress_sequences.c"
 #include "compress/zstd_compress_superblock.c"
+#include "compress/zstd_preSplit.c"
 #include "compress/zstd_compress.c"
 #include "compress/zstd_double_fast.c"
 #include "compress/zstd_fast.c"

zstd.mod/zstd/contrib/gen_html/Makefile

@@ -40,7 +40,7 @@ gen_html: gen_html.cpp
 
 $(ZSTDMANUAL): gen_html $(ZSTDAPI)
 	echo "Update zstd manual in /doc"
-	./gen_html $(LIBVER) $(ZSTDAPI) $(ZSTDMANUAL)
+	./gen_html$(EXT) $(LIBVER) $(ZSTDAPI) $(ZSTDMANUAL)
 
 .PHONY: manual
 manual: gen_html $(ZSTDMANUAL)

zstd.mod/zstd/contrib/gen_html/gen_html.cpp

@@ -211,6 +211,7 @@ int main(int argc, char *argv[]) {
 
     ostream << "<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=ISO-8859-1\">\n<title>" << version << "</title>\n</head>\n<body>" << endl;
     ostream << "<h1>" << version << "</h1>\n";
+    ostream << "Note: the content of this file has been automatically generated by parsing \"zstd.h\" \n";
 
     ostream << "<hr>\n<a name=\"Contents\"></a><h2>Contents</h2>\n<ol>\n";
     for (size_t i=0; i<chapters.size(); i++)

zstd.mod/zstd/contrib/largeNbDicts/largeNbDicts.c

@@ -1025,7 +1025,7 @@ int main (int argc, const char** argv)
     unsigned nbBlocks = 0; /* determine nbBlocks automatically, from source and blockSize */
     ZSTD_dictContentType_e dictContentType = ZSTD_dct_auto;
     ZSTD_dictAttachPref_e dictAttachPref = ZSTD_dictDefaultAttach;
-    ZSTD_paramSwitch_e prefetchCDictTables = ZSTD_ps_auto;
+    ZSTD_ParamSwitch_e prefetchCDictTables = ZSTD_ps_auto;
     metricAggregatePref_e metricAggregatePref = fastest;
 
     for (int argNb = 1; argNb < argc ; argNb++) {

zstd.mod/zstd/contrib/linux-kernel/linux.mk

@@ -26,6 +26,7 @@ zstd_compress-y := \
 		compress/zstd_lazy.o \
 		compress/zstd_ldm.o \
 		compress/zstd_opt.o \
+		compress/zstd_preSplit.o \
 
 zstd_decompress-y := \
 		zstd_decompress_module.o \

zstd.mod/zstd/contrib/linux-kernel/linux_zstd.h

@@ -136,9 +136,20 @@ typedef ZSTD_parameters zstd_parameters;
 zstd_parameters zstd_get_params(int level,
 	unsigned long long estimated_src_size);
 
-/* ======   Single-pass Compression   ====== */
-
 typedef ZSTD_CCtx zstd_cctx;
+typedef ZSTD_cParameter zstd_cparameter;
+
+/**
+ * zstd_cctx_set_param() - sets a compression parameter
+ * @cctx:         The context. Must have been initialized with zstd_init_cctx().
+ * @param:        The parameter to set.
+ * @value:        The value to set the parameter to.
+ *
+ * Return:        Zero or an error, which can be checked using zstd_is_error().
+ */
+size_t zstd_cctx_set_param(zstd_cctx *cctx, zstd_cparameter param, int value);
+
+/* ======   Single-pass Compression   ====== */
 
 /**
  * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx
@@ -153,6 +164,20 @@ typedef ZSTD_CCtx zstd_cctx;
  */
 size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters);
 
+/**
+ * zstd_cctx_workspace_bound_with_ext_seq_prod() - max memory needed to
+ * initialize a zstd_cctx when using the block-level external sequence
+ * producer API.
+ * @parameters: The compression parameters to be used.
+ *
+ * If multiple compression parameters might be used, the caller must call
+ * this function for each set of parameters and use the maximum size.
+ *
+ * Return:      A lower bound on the size of the workspace that is passed to
+ *              zstd_init_cctx().
+ */
+size_t zstd_cctx_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *parameters);
+
 /**
  * zstd_init_cctx() - initialize a zstd compression context
  * @workspace:      The workspace to emplace the context into. It must outlive
@@ -257,6 +282,16 @@ typedef ZSTD_CStream zstd_cstream;
  */
 size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams);
 
+/**
+ * zstd_cstream_workspace_bound_with_ext_seq_prod() - memory needed to initialize
+ * a zstd_cstream when using the block-level external sequence producer API.
+ * @cparams: The compression parameters to be used for compression.
+ *
+ * Return:   A lower bound on the size of the workspace that is passed to
+ *           zstd_init_cstream().
+ */
+size_t zstd_cstream_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *cparams);
+
 /**
  * zstd_init_cstream() - initialize a zstd streaming compression context
  * @parameters        The zstd parameters to use for compression.
@@ -416,6 +451,18 @@ size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output,
  */
 size_t zstd_find_frame_compressed_size(const void *src, size_t src_size);
 
+/**
+ * zstd_register_sequence_producer() - exposes the zstd library function
+ * ZSTD_registerSequenceProducer(). This is used for the block-level external
+ * sequence producer API. See upstream zstd.h for detailed documentation.
+ */
+typedef ZSTD_sequenceProducer_F zstd_sequence_producer_f;
+void zstd_register_sequence_producer(
+  zstd_cctx *cctx,
+  void* sequence_producer_state,
+  zstd_sequence_producer_f sequence_producer
+);
+
 /**
  * struct zstd_frame_params - zstd frame parameters stored in the frame header
  * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not
@@ -429,7 +476,7 @@ size_t zstd_find_frame_compressed_size(const void *src, size_t src_size);
  *
  * See zstd_lib.h.
  */
-typedef ZSTD_frameHeader zstd_frame_header;
+typedef ZSTD_FrameHeader zstd_frame_header;
 
 /**
  * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame
@@ -444,4 +491,35 @@ typedef ZSTD_frameHeader zstd_frame_header;
 size_t zstd_get_frame_header(zstd_frame_header *params, const void *src,
 	size_t src_size);
 
+/**
+ * struct zstd_sequence - a sequence of literals or a match
+ *
+ * @offset: The offset of the match
+ * @litLength: The literal length of the sequence
+ * @matchLength: The match length of the sequence
+ * @rep: Represents which repeat offset is used
+ */
+typedef ZSTD_Sequence zstd_sequence;
+
+/**
+ * zstd_compress_sequences_and_literals() - compress an array of zstd_sequence and literals
+ *
+ * @cctx: The zstd compression context.
+ * @dst: The buffer to compress the data into.
+ * @dst_capacity: The size of the destination buffer.
+ * @in_seqs: The array of zstd_sequence to compress.
+ * @in_seqs_size: The number of sequences in in_seqs.
+ * @literals: The literals associated to the sequences to be compressed.
+ * @lit_size: The size of the literals in the literals buffer.
+ * @lit_capacity: The size of the literals buffer.
+ * @decompressed_size: The size of the input data
+ *
+ * Return: The compressed size or an error, which can be checked using
+ * 	   zstd_is_error().
+ */
+size_t zstd_compress_sequences_and_literals(zstd_cctx *cctx, void* dst, size_t dst_capacity,
+					    const zstd_sequence *in_seqs, size_t in_seqs_size,
+					    const void* literals, size_t lit_size, size_t lit_capacity,
+					    size_t decompressed_size);
+
 #endif  /* LINUX_ZSTD_H */

zstd.mod/zstd/contrib/linux-kernel/mem.h

@@ -15,7 +15,7 @@
 /*-****************************************
 *  Dependencies
 ******************************************/
-#include <asm/unaligned.h>  /* get_unaligned, put_unaligned* */
+#include <linux/unaligned.h>  /* get_unaligned, put_unaligned* */
 #include <linux/compiler.h>  /* inline */
 #include <linux/swab.h>  /* swab32, swab64 */
 #include <linux/types.h>  /* size_t, ptrdiff_t */
@@ -24,6 +24,7 @@
 /*-****************************************
 *  Compiler specifics
 ******************************************/
+#undef MEM_STATIC /* may be already defined from common/compiler.h */
 #define MEM_STATIC static inline
 
 /*-**************************************************************

zstd.mod/zstd/contrib/linux-kernel/test/include/linux/xxhash.h

@@ -296,7 +296,7 @@ XXH_API void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state
  * - xxHash source repository: https://github.com/Cyan4973/xxHash
  */
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>

zstd.mod/zstd/contrib/linux-kernel/zstd_compress_module.c

@@ -16,6 +16,7 @@
 
 #include "common/zstd_deps.h"
 #include "common/zstd_internal.h"
+#include "compress/zstd_compress_internal.h"
 
 #define ZSTD_FORWARD_IF_ERR(ret)            \
 	do {                                \
@@ -79,12 +80,64 @@ zstd_parameters zstd_get_params(int level,
 }
 EXPORT_SYMBOL(zstd_get_params);
 
+size_t zstd_cctx_set_param(zstd_cctx *cctx, ZSTD_cParameter param, int value)
+{
+	return ZSTD_CCtx_setParameter(cctx, param, value);
+}
+EXPORT_SYMBOL(zstd_cctx_set_param);
+
 size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams)
 {
 	return ZSTD_estimateCCtxSize_usingCParams(*cparams);
 }
 EXPORT_SYMBOL(zstd_cctx_workspace_bound);
 
+// Used by zstd_cctx_workspace_bound_with_ext_seq_prod()
+static size_t dummy_external_sequence_producer(
+	void *sequenceProducerState,
+	ZSTD_Sequence *outSeqs, size_t outSeqsCapacity,
+	const void *src, size_t srcSize,
+	const void *dict, size_t dictSize,
+	int compressionLevel,
+	size_t windowSize)
+{
+	(void)sequenceProducerState;
+	(void)outSeqs; (void)outSeqsCapacity;
+	(void)src; (void)srcSize;
+	(void)dict; (void)dictSize;
+	(void)compressionLevel;
+	(void)windowSize;
+	return ZSTD_SEQUENCE_PRODUCER_ERROR;
+}
+
+static void init_cctx_params_from_compress_params(
+	ZSTD_CCtx_params *cctx_params,
+	const zstd_compression_parameters *compress_params)
+{
+	ZSTD_parameters zstd_params;
+	memset(&zstd_params, 0, sizeof(zstd_params));
+	zstd_params.cParams = *compress_params;
+	ZSTD_CCtxParams_init_advanced(cctx_params, zstd_params);
+}
+
+size_t zstd_cctx_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *compress_params)
+{
+	ZSTD_CCtx_params cctx_params;
+	init_cctx_params_from_compress_params(&cctx_params, compress_params);
+	ZSTD_CCtxParams_registerSequenceProducer(&cctx_params, NULL, dummy_external_sequence_producer);
+	return ZSTD_estimateCCtxSize_usingCCtxParams(&cctx_params);
+}
+EXPORT_SYMBOL(zstd_cctx_workspace_bound_with_ext_seq_prod);
+
+size_t zstd_cstream_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *compress_params)
+{
+	ZSTD_CCtx_params cctx_params;
+	init_cctx_params_from_compress_params(&cctx_params, compress_params);
+	ZSTD_CCtxParams_registerSequenceProducer(&cctx_params, NULL, dummy_external_sequence_producer);
+	return ZSTD_estimateCStreamSize_usingCCtxParams(&cctx_params);
+}
+EXPORT_SYMBOL(zstd_cstream_workspace_bound_with_ext_seq_prod);
+
 zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size)
 {
 	if (workspace == NULL)
@@ -160,5 +213,25 @@ size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output)
 }
 EXPORT_SYMBOL(zstd_end_stream);
 
+void zstd_register_sequence_producer(
+  zstd_cctx *cctx,
+  void* sequence_producer_state,
+  zstd_sequence_producer_f sequence_producer
+) {
+	ZSTD_registerSequenceProducer(cctx, sequence_producer_state, sequence_producer);
+}
+EXPORT_SYMBOL(zstd_register_sequence_producer);
+
+size_t zstd_compress_sequences_and_literals(zstd_cctx *cctx, void* dst, size_t dst_capacity,
+					    const zstd_sequence *in_seqs, size_t in_seqs_size,
+					    const void* literals, size_t lit_size, size_t lit_capacity,
+					    size_t decompressed_size)
+{
+	return ZSTD_compressSequencesAndLiterals(cctx, dst, dst_capacity, in_seqs,
+						 in_seqs_size, literals, lit_size,
+						 lit_capacity, decompressed_size);
+}
+EXPORT_SYMBOL(zstd_compress_sequences_and_literals);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("Zstd Compressor");

zstd.mod/zstd/contrib/linux-kernel/zstd_decompress_module.c

@@ -77,7 +77,7 @@ EXPORT_SYMBOL(zstd_init_dstream);
 
 size_t zstd_reset_dstream(zstd_dstream *dstream)
 {
-	return ZSTD_resetDStream(dstream);
+	return ZSTD_DCtx_reset(dstream, ZSTD_reset_session_only);
 }
 EXPORT_SYMBOL(zstd_reset_dstream);
 

zstd.mod/zstd/contrib/linux-kernel/zstd_deps.h

@@ -115,11 +115,7 @@ static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) {
 #ifndef ZSTD_DEPS_STDINT
 #define ZSTD_DEPS_STDINT
 
-/*
- * The Linux Kernel doesn't provide intptr_t, only uintptr_t, which
- * is an unsigned long.
- */
-typedef long intptr_t;
+/* intptr_t already provided by ZSTD_DEPS_COMMON */
 
 #endif /* ZSTD_DEPS_STDINT */
 #endif /* ZSTD_DEPS_NEED_STDINT */

zstd.mod/zstd/contrib/pzstd/Makefile

@@ -10,7 +10,7 @@
 # Standard variables for installation
 DESTDIR ?=
 PREFIX  ?= /usr/local
-BINDIR  := $(DESTDIR)$(PREFIX)/bin
+BINDIR  := $(PREFIX)/bin
 
 ZSTDDIR = ../../lib
 PROGDIR = ../../programs
@@ -37,11 +37,8 @@ CFLAGS   += -Wno-deprecated-declarations
 PZSTD_INC  = -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(PROGDIR) -I.
 GTEST_INC  = -isystem googletest/googletest/include
 
-# If default C++ version is older than C++11, explicitly set C++11, which is the
-# minimum required by the code.
-ifeq ($(shell echo "\043if __cplusplus < 201103L\n\043error\n\043endif" | $(CXX) -x c++ -Werror -c - -o /dev/null 2>/dev/null && echo 1 || echo 0),0)
-PZSTD_CXX_STD := -std=c++11
-endif
+# Set the minimum required by gtest
+PZSTD_CXX_STD := -std=c++14
 
 PZSTD_CPPFLAGS  = $(PZSTD_INC)
 PZSTD_CCXXFLAGS =
@@ -112,12 +109,12 @@ check:
 .PHONY: install
 install: PZSTD_CPPFLAGS += -DNDEBUG
 install: pzstd$(EXT)
-	install -d -m 755 $(BINDIR)/
-	install -m 755 pzstd$(EXT) $(BINDIR)/pzstd$(EXT)
+	install -d -m 755 $(DESTDIR)$(BINDIR)/
+	install -m 755 pzstd$(EXT) $(DESTDIR)$(BINDIR)/pzstd$(EXT)
 
 .PHONY: uninstall
 uninstall:
-	$(RM) $(BINDIR)/pzstd$(EXT)
+	$(RM) $(DESTDIR)$(BINDIR)/pzstd$(EXT)
 
 # Targets for many different builds
 .PHONY: all

zstd.mod/zstd/contrib/pzstd/Options.cpp

@@ -322,7 +322,7 @@ Options::Status Options::parse(int argc, const char **argv) {
   g_utilDisplayLevel = verbosity;
   // Remove local input files that are symbolic links
   if (!followLinks) {
-      std::remove_if(localInputFiles.begin(), localInputFiles.end(),
+	  localInputFiles.erase(std::remove_if(localInputFiles.begin(), localInputFiles.end(),
                      [&](const char *path) {
                         bool isLink = UTIL_isLink(path);
                         if (isLink && verbosity >= 2) {
@@ -332,7 +332,7 @@ Options::Status Options::parse(int argc, const char **argv) {
                                     path);
                         }
                         return isLink;
-                    });
+					 }), localInputFiles.end());
   }
 
   // Translate input files/directories into files to (de)compress

zstd.mod/zstd/contrib/pzstd/Pzstd.cpp

@@ -269,7 +269,10 @@ static void compress(
     std::shared_ptr<BufferWorkQueue> out,
     size_t maxInputSize) {
   auto& errorHolder = state.errorHolder;
-  auto guard = makeScopeGuard([&] { out->finish(); });
+  auto guard = makeScopeGuard([&] {
+    in->finish();
+    out->finish();
+  });
   // Initialize the CCtx
   auto ctx = state.cStreamPool->get();
   if (!errorHolder.check(ctx != nullptr, "Failed to allocate ZSTD_CStream")) {
@@ -431,7 +434,10 @@ static void decompress(
     std::shared_ptr<BufferWorkQueue> in,
     std::shared_ptr<BufferWorkQueue> out) {
   auto& errorHolder = state.errorHolder;
-  auto guard = makeScopeGuard([&] { out->finish(); });
+  auto guard = makeScopeGuard([&] {
+    in->finish();
+    out->finish();
+  });
   // Initialize the DCtx
   auto ctx = state.dStreamPool->get();
   if (!errorHolder.check(ctx != nullptr, "Failed to allocate ZSTD_DStream")) {
@@ -578,6 +584,7 @@ std::uint64_t writeFile(
     FILE* outputFd,
     bool decompress) {
   auto& errorHolder = state.errorHolder;
+  auto outsFinishGuard = makeScopeGuard([&outs] { outs.finish(); });
   auto lineClearGuard = makeScopeGuard([&state] {
     state.log.clear(kLogInfo);
   });
@@ -585,6 +592,7 @@ std::uint64_t writeFile(
   std::shared_ptr<BufferWorkQueue> out;
   // Grab the output queue for each decompression job (in order).
   while (outs.pop(out)) {
+    auto outFinishGuard = makeScopeGuard([&out] { out->finish(); });
     if (errorHolder.hasError()) {
       continue;
     }

zstd.mod/zstd/contrib/pzstd/test/PzstdTest.cpp

@@ -7,9 +7,7 @@
  * in the COPYING file in the root directory of this source tree).
  */
 #include "Pzstd.h"
-extern "C" {
 #include "datagen.h"
-}
 #include "test/RoundTrip.h"
 #include "utils/ScopeGuard.h"
 

zstd.mod/zstd/contrib/pzstd/test/RoundTripTest.cpp

@@ -6,9 +6,7 @@
  * 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).
  */
-extern "C" {
 #include "datagen.h"
-}
 #include "Options.h"
 #include "test/RoundTrip.h"
 #include "utils/ScopeGuard.h"

zstd.mod/zstd/contrib/pzstd/utils/WorkQueue.h

@@ -115,13 +115,14 @@ class WorkQueue {
   }
 
   /**
-   * Promise that `push()` won't be called again, so once the queue is empty
-   * there will never any more work.
+   * Promise that either the reader side or the writer side is done.
+   * If the writer is done, `push()` won't be called again, so once the queue
+   * is empty there will never be any more work. If the reader is done, `pop()`
+   * won't be called again, so further items pushed will just be ignored.
    */
   void finish() {
     {
       std::lock_guard<std::mutex> lock(mutex_);
-      assert(!done_);
       done_ = true;
     }
     readerCv_.notify_all();

zstd.mod/zstd/contrib/seekable_format/examples/parallel_processing.c

@@ -19,7 +19,7 @@
 #define ZSTD_STATIC_LINKING_ONLY
 #include <zstd.h>      // presumes zstd library is installed
 #include <zstd_errors.h>
-#if defined(WIN32) || defined(_WIN32)
+#if defined(_WIN32)
 #  include <windows.h>
 #  define SLEEP(x) Sleep(x)
 #else

zstd.mod/zstd/contrib/seekable_format/zstd_seekable.h

@@ -1,13 +1,13 @@
 #ifndef SEEKABLE_H
 #define SEEKABLE_H
 
+#include <stdio.h>
+#include "zstd.h"   /* ZSTDLIB_API */
+
 #if defined (__cplusplus)
 extern "C" {
 #endif
 
-#include <stdio.h>
-#include "zstd.h"   /* ZSTDLIB_API */
-
 
 #define ZSTD_seekTableFooterSize 9
 

zstd.mod/zstd/contrib/seekable_format/zstdseek_decompress.c

@@ -77,7 +77,10 @@
 /* ************************************************************
 * Avoid fseek()'s 2GiB barrier with MSVC, macOS, *BSD, MinGW
 ***************************************************************/
-#if defined(_MSC_VER) && _MSC_VER >= 1400
+#if defined(LIBC_NO_FSEEKO)
+/* Some older libc implementations don't include these functions (e.g. Bionic < 24) */
+#   define LONG_SEEK fseek
+#elif defined(_MSC_VER) && _MSC_VER >= 1400
 #   define LONG_SEEK _fseeki64
 #elif !defined(__64BIT__) && (PLATFORM_POSIX_VERSION >= 200112L) /* No point defining Large file for 64 bit */
 #   define LONG_SEEK fseeko
@@ -252,6 +255,8 @@ size_t ZSTD_seekable_free(ZSTD_seekable* zs)
 
 ZSTD_seekTable* ZSTD_seekTable_create_fromSeekable(const ZSTD_seekable* zs)
 {
+    assert(zs != NULL);
+    if (zs->seekTable.entries == NULL) return NULL;
     ZSTD_seekTable* const st = (ZSTD_seekTable*)malloc(sizeof(ZSTD_seekTable));
     if (st==NULL) return NULL;
 

zstd.mod/zstd/doc/decompressor_errata.md

@@ -6,12 +6,53 @@ Each entry will contain:
 1. The last affected decompressor versions.
 2. The decompressor components affected.
 2. Whether the compressed frame could ever be produced by the reference compressor.
-3. An example frame.
+3. An example frame (hexadecimal string when it can be short enough, link to golden file otherwise)
 4. A description of the bug.
 
 The document is in reverse chronological order, with the bugs that affect the most recent zstd decompressor versions listed first.
 
 
+No sequence using the 2-bytes format
+------------------------------------------------
+
+**Last affected version**: v1.5.5
+
+**Affected decompressor component(s)**: Library & CLI
+
+**Produced by the reference compressor**: No
+
+**Example Frame**: see zstd/tests/golden-decompression/zeroSeq_2B.zst
+
+The zstd decoder incorrectly expects FSE tables when there are 0 sequences present in the block
+if the value 0 is encoded using the 2-bytes format.
+Instead, it should immediately end the sequence section, and move on to next block.
+
+This situation was never generated by the reference compressor,
+because representing 0 sequences with the 2-bytes format is inefficient
+(the 1-byte format is always used in this case).
+
+
+Compressed block with a size of exactly 128 KB
+------------------------------------------------
+
+**Last affected version**: v1.5.2
+
+**Affected decompressor component(s)**: Library & CLI
+
+**Produced by the reference compressor**: No
+
+**Example Frame**: see zstd/tests/golden-decompression/block-128k.zst
+
+The zstd decoder incorrectly rejected blocks of type `Compressed_Block` when their size was exactly 128 KB.
+Note that `128 KB - 1` was accepted, and `128 KB + 1` is forbidden by the spec.
+
+This type of block was never generated by the reference compressor.
+
+These blocks used to be disallowed by the spec up until spec version 0.3.2 when the restriction was lifted by [PR#1689](https://github.com/facebook/zstd/pull/1689).
+
+> A Compressed_Block has the extra restriction that Block_Size is always strictly less than the decompressed size. If this condition cannot be respected, the block must be sent uncompressed instead (Raw_Block).
+
+
 Compressed block with 0 literals and 0 sequences
 ------------------------------------------------
 
@@ -31,6 +72,7 @@ Additionally, these blocks were disallowed by the spec up until spec version 0.3
 
 > A Compressed_Block has the extra restriction that Block_Size is always strictly less than the decompressed size. If this condition cannot be respected, the block must be sent uncompressed instead (Raw_Block).
 
+
 First block is RLE block
 ------------------------
 
@@ -52,6 +94,7 @@ block.
 
 https://github.com/facebook/zstd/blob/8814aa5bfa74f05a86e55e9d508da177a893ceeb/lib/compress/zstd_compress.c#L3527-L3535
 
+
 Tiny FSE Table & Block
 ----------------------
 
@@ -82,3 +125,24 @@ The total `Block_Content` is `5` bytes, and `Last_Table_Offset` is `2`.
 See the compressor workaround code:
 
 https://github.com/facebook/zstd/blob/8814aa5bfa74f05a86e55e9d508da177a893ceeb/lib/compress/zstd_compress.c#L2667-L2682
+
+Magicless format
+----------------------
+
+**Last affected version**: v1.5.5
+
+**Affected decompressor component(s)**: Library
+
+**Produced by the reference compressor**: Yes (example: https://gist.github.com/embg/9940726094f4cf2cef162cffe9319232)
+
+**Example Frame**: `27 b5 2f fd 00 03 19 00 00 66 6f 6f 3f ba c4 59`
+
+v1.5.6 fixes several bugs in which the magicless-format decoder rejects valid frames.
+These include but are not limited to:
+* Valid frames that happen to begin with a legacy magic number (little-endian)
+* Valid frames that happen to begin with a skippable magic number (little-endian)
+
+If you are affected by this issue and cannot update to v1.5.6 or later, there is a
+workaround to recover affected data. Simply prepend the ZSTD magic number
+`0xFD2FB528` (little-endian) to your data and decompress using the standard-format
+decoder.

zstd.mod/zstd/doc/decompressor_permissive.md

@@ -0,0 +1,80 @@
+Decompressor Permissiveness to Invalid Data
+===========================================
+
+This document describes the behavior of the reference decompressor in cases
+where it accepts formally invalid data instead of reporting an error.
+
+While the reference decompressor *must* decode any compliant frame following
+the specification, its ability to detect erroneous data is on a best effort
+basis: the decoder may accept input data that would be formally invalid,
+when it causes no risk to the decoder, and which detection would cost too much
+complexity or speed regression.
+
+In practice, the vast majority of invalid data are detected, if only because
+many corruption events are dangerous for the decoder process (such as
+requesting an out-of-bound memory access) and many more are easy to check.
+
+This document lists a few known cases where invalid data was formerly accepted
+by the decoder, and what has changed since.
+
+
+Truncated Huffman states
+------------------------
+
+**Last affected version**: v1.5.6
+
+**Produced by the reference compressor**: No
+
+**Example Frame**: `28b5 2ffd 0000 5500 0072 8001 0420 7e1f 02aa 00`
+
+When using FSE-compressed Huffman weights, the compressed weight bitstream
+could contain fewer bits than necessary to decode the initial states.
+
+The reference decompressor up to v1.5.6 will decode truncated or missing
+initial states as zero, which can result in a valid Huffman tree if only
+the second state is truncated.
+
+In newer versions, truncated initial states are reported as a corruption
+error by the decoder.
+
+
+Offset == 0
+-----------
+
+**Last affected version**: v1.5.5
+
+**Produced by the reference compressor**: No
+
+**Example Frame**: `28b5 2ffd 0000 4500 0008 0002 002f 430b ae`
+
+If a sequence is decoded with `literals_length = 0` and `offset_value = 3`
+while `Repeated_Offset_1 = 1`, the computed offset will be `0`, which is
+invalid.
+
+The reference decompressor up to v1.5.5 processes this case as if the computed
+offset was `1`, including inserting `1` into the repeated offset list.
+This prevents the output buffer from remaining uninitialized, thus denying a
+potential attack vector from an untrusted source.
+However, in the rare case where this scenario would be the outcome of a
+transmission or storage error, the decoder relies on the checksum to detect
+the error.
+
+In newer versions, this case is always detected and reported as a corruption error.
+
+
+Non-zeroes reserved bits
+------------------------
+
+**Last affected version**: v1.5.5
+
+**Produced by the reference compressor**: No
+
+The Sequences section of each block has a header, and one of its elements is a
+byte, which describes the compression mode of each symbol.
+This byte contains 2 reserved bits which must be set to zero.
+
+The reference decompressor up to v1.5.5 just ignores these 2 bits.
+This behavior has no consequence for the rest of the frame decoding process.
+
+In newer versions, the 2 reserved bits are actively checked for value zero,
+and the decoder reports a corruption error if they are not.

zstd.mod/zstd/doc/educational_decoder/Makefile

@@ -10,7 +10,7 @@
 
 ZSTD ?= zstd   # note: requires zstd installation on local system
 
-UNAME?= $(shell uname)
+UNAME?= $(shell sh -c 'MSYSTEM="MSYS" uname') 
 ifeq ($(UNAME), SunOS)
 DIFF ?= gdiff
 else

zstd.mod/zstd/doc/educational_decoder/zstd_decompress.c

@@ -997,7 +997,8 @@ static void decompress_sequences(frame_context_t *const ctx,
                                  const size_t num_sequences);
 static sequence_command_t decode_sequence(sequence_states_t *const state,
                                           const u8 *const src,
-                                          i64 *const offset);
+                                          i64 *const offset,
+                                          int lastSequence);
 static void decode_seq_table(FSE_dtable *const table, istream_t *const in,
                                const seq_part_t type, const seq_mode_t mode);
 
@@ -1017,12 +1018,7 @@ static size_t decode_sequences(frame_context_t *const ctx, istream_t *in,
     // This is a variable size field using between 1 and 3 bytes. Let's call its
     // first byte byte0."
     u8 header = IO_read_bits(in, 8);
-    if (header == 0) {
-        // "There are no sequences. The sequence section stops there.
-        // Regenerated content is defined entirely by literals section."
-        *sequences = NULL;
-        return 0;
-    } else if (header < 128) {
+    if (header < 128) {
         // "Number_of_Sequences = byte0 . Uses 1 byte."
         num_sequences = header;
     } else if (header < 255) {
@@ -1033,6 +1029,12 @@ static size_t decode_sequences(frame_context_t *const ctx, istream_t *in,
         num_sequences = IO_read_bits(in, 16) + 0x7F00;
     }
 
+    if (num_sequences == 0) {
+        // "There are no sequences. The sequence section stops there."
+        *sequences = NULL;
+        return 0;
+    }
+
     *sequences = malloc(num_sequences * sizeof(sequence_command_t));
     if (!*sequences) {
         BAD_ALLOC();
@@ -1114,7 +1116,7 @@ static void decompress_sequences(frame_context_t *const ctx, istream_t *in,
 
     for (size_t i = 0; i < num_sequences; i++) {
         // Decode sequences one by one
-        sequences[i] = decode_sequence(&states, src, &bit_offset);
+        sequences[i] = decode_sequence(&states, src, &bit_offset, i==num_sequences-1);
     }
 
     if (bit_offset != 0) {
@@ -1125,7 +1127,8 @@ static void decompress_sequences(frame_context_t *const ctx, istream_t *in,
 // Decode a single sequence and update the state
 static sequence_command_t decode_sequence(sequence_states_t *const states,
                                           const u8 *const src,
-                                          i64 *const offset) {
+                                          i64 *const offset,
+                                          int lastSequence) {
     // "Each symbol is a code in its own context, which specifies Baseline and
     // Number_of_Bits to add. Codes are FSE compressed, and interleaved with raw
     // additional bits in the same bitstream."
@@ -1160,7 +1163,7 @@ static sequence_command_t decode_sequence(sequence_states_t *const states,
     // Literals_Length_State is updated, followed by Match_Length_State, and
     // then Offset_State."
     // If the stream is complete don't read bits to update state
-    if (*offset != 0) {
+    if (!lastSequence) {
         FSE_update_state(&states->ll_table, &states->ll_state, src, offset);
         FSE_update_state(&states->ml_table, &states->ml_state, src, offset);
         FSE_update_state(&states->of_table, &states->of_state, src, offset);
@@ -1210,7 +1213,7 @@ static void decode_seq_table(FSE_dtable *const table, istream_t *const in,
         break;
     }
     case seq_repeat:
-        // "Repeat_Mode : re-use distribution table from previous compressed
+        // "Repeat_Mode : reuse distribution table from previous compressed
         // block."
         // Nothing to do here, table will be unchanged
         if (!table->symbols) {
@@ -1399,7 +1402,7 @@ size_t ZSTD_get_decompressed_size(const void *src, const size_t src_len) {
 /******* END OUTPUT SIZE COUNTING *********************************************/
 
 /******* DICTIONARY PARSING ***************************************************/
-dictionary_t* create_dictionary() {
+dictionary_t* create_dictionary(void) {
     dictionary_t* const dict = calloc(1, sizeof(dictionary_t));
     if (!dict) {
         BAD_ALLOC();

zstd.mod/zstd/doc/zstd_compression_format.md

@@ -16,7 +16,7 @@ Distribution of this document is unlimited.
 
 ### Version
 
-0.3.9 (2023-03-08)
+0.4.3 (2024-10-07)
 
 
 Introduction
@@ -650,13 +650,15 @@ __`Number_of_Sequences`__
 
 This is a variable size field using between 1 and 3 bytes.
 Let's call its first byte `byte0`.
-- `if (byte0 == 0)` : there are no sequences.
-            The sequence section stops there.
-            Decompressed content is defined entirely as Literals Section content.
-            The FSE tables used in `Repeat_Mode` aren't updated.
 - `if (byte0 < 128)` : `Number_of_Sequences = byte0` . Uses 1 byte.
-- `if (byte0 < 255)` : `Number_of_Sequences = ((byte0-128) << 8) + byte1` . Uses 2 bytes.
-- `if (byte0 == 255)`: `Number_of_Sequences = byte1 + (byte2<<8) + 0x7F00` . Uses 3 bytes.
+- `if (byte0 < 255)` : `Number_of_Sequences = ((byte0 - 0x80) << 8) + byte1`. Uses 2 bytes.
+            Note that the 2 bytes format fully overlaps the 1 byte format.
+- `if (byte0 == 255)`: `Number_of_Sequences = byte1 + (byte2<<8) + 0x7F00`. Uses 3 bytes.
+
+`if (Number_of_Sequences == 0)` : there are no sequences.
+            The sequence section stops immediately,
+            FSE tables used in `Repeat_Mode` aren't updated.
+            Block's decompressed content is defined solely by the Literals Section content.
 
 __Symbol compression modes__
 
@@ -927,7 +929,10 @@ There is an exception though, when current sequence's `literals_length = 0`.
 In this case, repeated offsets are shifted by one,
 so an `offset_value` of 1 means `Repeated_Offset2`,
 an `offset_value` of 2 means `Repeated_Offset3`,
-and an `offset_value` of 3 means `Repeated_Offset1 - 1_byte`.
+and an `offset_value` of 3 means `Repeated_Offset1 - 1`.
+
+In the final case, if `Repeated_Offset1 - 1` evaluates to 0, then the
+data is considered corrupted.
 
 For the first block, the starting offset history is populated with following values :
 `Repeated_Offset1`=1, `Repeated_Offset2`=4, `Repeated_Offset3`=8,
@@ -1033,55 +1038,57 @@ and to compress Huffman headers.
 FSE
 ---
 FSE, short for Finite State Entropy, is an entropy codec based on [ANS].
-FSE encoding/decoding involves a state that is carried over between symbols,
-so decoding must be done in the opposite direction as encoding.
+FSE encoding/decoding involves a state that is carried over between symbols.
+Decoding must be done in the opposite direction as encoding.
 Therefore, all FSE bitstreams are read from end to beginning.
 Note that the order of the bits in the stream is not reversed,
-we just read the elements in the reverse order they are written.
+we just read each multi-bits element in the reverse order they are encoded.
 
 For additional details on FSE, see [Finite State Entropy].
 
 [Finite State Entropy]:https://github.com/Cyan4973/FiniteStateEntropy/
 
-FSE decoding involves a decoding table which has a power of 2 size, and contain three elements:
+FSE decoding is directed by a decoding table with a power of 2 size, each row containing three elements:
 `Symbol`, `Num_Bits`, and `Baseline`.
 The `log2` of the table size is its `Accuracy_Log`.
 An FSE state value represents an index in this table.
 
 To obtain the initial state value, consume `Accuracy_Log` bits from the stream as a __little-endian__ value.
-The next symbol in the stream is the `Symbol` indicated in the table for that state.
+The first symbol in the stream is the `Symbol` indicated in the table for that state.
 To obtain the next state value,
 the decoder should consume `Num_Bits` bits from the stream as a __little-endian__ value and add it to `Baseline`.
 
 [ANS]: https://en.wikipedia.org/wiki/Asymmetric_Numeral_Systems
 
 ### FSE Table Description
-To decode FSE streams, it is necessary to construct the decoding table.
-The Zstandard format encodes FSE table descriptions as follows:
+To decode an FSE bitstream, it is necessary to build its FSE decoding table.
+The decoding table is derived from a distribution of Probabilities.
+The Zstandard format encodes distributions of Probabilities as follows:
 
-An FSE distribution table describes the probabilities of all symbols
-from `0` to the last present one (included)
-on a normalized scale of `1 << Accuracy_Log` .
-Note that there must be two or more symbols with nonzero probability.
-
-It's a bitstream which is read forward, in __little-endian__ fashion.
-It's not necessary to know bitstream exact size,
-it will be discovered and reported by the decoding process.
+The distribution of probabilities is described in a bitstream which is read forward,
+in __little-endian__ fashion.
+The amount of bytes consumed from the bitstream to describe the distribution
+is discovered at the end of the decoding process.
 
-The bitstream starts by reporting on which scale it operates.
+The bitstream starts by reporting on which scale the distribution operates.
 Let's `low4Bits` designate the lowest 4 bits of the first byte :
 `Accuracy_Log = low4bits + 5`.
 
-Then follows each symbol value, from `0` to last present one.
-The number of bits used by each field is variable.
+An FSE distribution table describes the probabilities of all symbols
+from `0` to the last present one (included) in natural order.
+The sum of probabilities is normalized to reach a power of 2 total of `1 << Accuracy_Log` .
+There must be two or more symbols with non-zero probabilities.
+
+The number of bits used to decode each probability is variable.
 It depends on :
 
 - Remaining probabilities + 1 :
   __example__ :
   Presuming an `Accuracy_Log` of 8,
-  and presuming 100 probabilities points have already been distributed,
+  and presuming 100 probability points have already been distributed,
   the decoder may read any value from `0` to `256 - 100 + 1 == 157` (inclusive).
-  Therefore, it must read `log2sup(157) == 8` bits.
+  Therefore, it may read up to `log2sup(157) == 8` bits, where `log2sup(N)`
+  is the smallest integer `T` that satisfies `(1 << T) > N`.
 
 - Value decoded : small values use 1 less bit :
   __example__ :
@@ -1092,111 +1099,133 @@ It depends on :
   values from 98 to 157 use 8 bits.
   This is achieved through this scheme :
 
-  | Value read | Value decoded | Number of bits used |
-  | ---------- | ------------- | ------------------- |
-  |   0 -  97  |   0 -  97     |  7                  |
-  |  98 - 127  |  98 - 127     |  8                  |
-  | 128 - 225  |   0 -  97     |  7                  |
-  | 226 - 255  | 128 - 157     |  8                  |
+  | 8-bit field read | Value decoded | Nb of bits consumed |
+  | ---------------- | ------------- | ------------------- |
+  |         0 -  97  |   0 -  97     |  7                  |
+  |        98 - 127  |  98 - 127     |  8                  |
+  |       128 - 225  |   0 -  97     |  7                  |
+  |       226 - 255  | 128 - 157     |  8                  |
 
-Symbols probabilities are read one by one, in order.
+Probability is derived from Value decoded using the following formula:
+`Probality = Value - 1`
 
-Probability is obtained from Value decoded by following formula :
-`Proba = value - 1`
+Consequently, a Probability of `0` is described by a Value `1`.
 
-It means value `0` becomes negative probability `-1`.
-`-1` is a special probability, which means "less than 1".
-Its effect on distribution table is described in the [next section].
-For the purpose of calculating total allocated probability points, it counts as one.
+A Value `0` is used to signal a special case, named "Probability `-1`".
+It describes a probability which should have been "less than 1".
+Its effect on the decoding table building process is described in the [next section].
+For the purpose of counting total allocated probability points, it counts as one.
 
 [next section]:#from-normalized-distribution-to-decoding-tables
 
-When a symbol has a __probability__ of `zero`,
+Symbols probabilities are read one by one, in order.
+After each probability is decoded, the total nb of probability points is updated.
+This is used to determine how many bits must be read to decode the probability of next symbol.
+
+When a symbol has a __probability__ of `zero` (decoded from reading a Value `1`),
 it is followed by a 2-bits repeat flag.
 This repeat flag tells how many probabilities of zeroes follow the current one.
 It provides a number ranging from 0 to 3.
 If it is a 3, another 2-bits repeat flag follows, and so on.
 
-When last symbol reaches cumulated total of `1 << Accuracy_Log`,
-decoding is complete.
-If the last symbol makes cumulated total go above `1 << Accuracy_Log`,
-distribution is considered corrupted.
+When the Probability for a symbol makes cumulated total reach `1 << Accuracy_Log`,
+then it's the last symbol, and decoding is complete.
 
 Then the decoder can tell how many bytes were used in this process,
 and how many symbols are present.
 The bitstream consumes a round number of bytes.
 Any remaining bit within the last byte is just unused.
 
+If this process results in a non-zero probability for a symbol outside of the
+valid range of symbols that the FSE table is defined for, even if that symbol is
+not used, then the data is considered corrupted.
+For the specific case of offset codes,
+a decoder implementation may reject a frame containing a non-zero probability
+for an offset code larger than the largest offset code supported by the decoder
+implementation.
+
 #### From normalized distribution to decoding tables
 
-The distribution of normalized probabilities is enough
+The normalized distribution of probabilities is enough
 to create a unique decoding table.
-
-It follows the following build rule :
+It is generated using the following build rule :
 
 The table has a size of `Table_Size = 1 << Accuracy_Log`.
-Each cell describes the symbol decoded,
-and instructions to get the next state (`Number_of_Bits` and `Baseline`).
+Each row specifies the decoded symbol,
+and instructions to reach the next state (`Number_of_Bits` and `Baseline`).
 
-Symbols are scanned in their natural order for "less than 1" probabilities.
-Symbols with this probability are being attributed a single cell,
+Symbols are first scanned in their natural order for "less than 1" probabilities
+(previously decoded from a Value of `0`).
+Symbols with this special probability are being attributed a single row,
 starting from the end of the table and retreating.
 These symbols define a full state reset, reading `Accuracy_Log` bits.
 
-Then, all remaining symbols, sorted in natural order, are allocated cells.
-Starting from symbol `0` (if it exists), and table position `0`,
-each symbol gets allocated as many cells as its probability.
-Cell allocation is spread, not linear :
-each successor position follows this rule :
+Then, all remaining symbols, sorted in natural order, are allocated rows.
+Starting from smallest present symbol, and table position `0`,
+each symbol gets allocated as many rows as its probability.
 
+Row allocation is not linear, it follows this order, in modular arithmetic:
 ```
 position += (tableSize>>1) + (tableSize>>3) + 3;
 position &= tableSize-1;
 ```
 
-A position is skipped if already occupied by a "less than 1" probability symbol.
-`position` does not reset between symbols, it simply iterates through
-each position in the table, switching to the next symbol when enough
-states have been allocated to the current one.
+Using above ordering rule, each symbol gets allocated as many rows as its probability.
+If a position is already occupied by a "less than 1" probability symbol,
+it is simply skipped, and the next position is allocated instead.
+Once enough rows have been allocated for the current symbol,
+the allocation process continues, using the next symbol, in natural order.
+This process guarantees that the table is entirely and exactly filled.
 
-The process guarantees that the table is entirely filled.
-Each cell corresponds to a state value, which contains the symbol being decoded.
+Each row specifies a decoded symbol, and is accessed by current state value.
+It also specifies `Number_of_Bits` and `Baseline`, which are required to determine next state value.
 
-To add the `Number_of_Bits` and `Baseline` required to retrieve next state,
-it's first necessary to sort all occurrences of each symbol in state order.
-Lower states will need 1 more bit than higher ones.
-The process is repeated for each symbol.
+To correctly set these fields, it's necessary to sort all occurrences of each symbol in state value order,
+and then attribute N+1 bits to lower rows, and N bits to higher rows,
+following the process described below (using an example):
 
 __Example__ :
-Presuming a symbol has a probability of 5,
-it receives 5 cells, corresponding to 5 state values.
-These state values are then sorted in natural order.
+Presuming an `Accuracy_Log` of 7,
+let's imagine a symbol with a Probability of 5:
+it receives 5 rows, corresponding to 5 state values between `0` and `127`.
+
+In this example, the first state value happens to be `1` (after unspecified previous symbols).
+The next 4 states are then determined using above modular arithmetic rule,
+which specifies to add `64+16+3 = 83` modulo `128` to jump to next position,
+producing the following series: `1`, `84`, `39`, `122`, `77` (modular arithmetic).
+(note: the next symbol will then start at `32`).
+
+These state values are then sorted in natural order,
+resulting in the following series: `1`, `39`, `77`, `84`, `122`.
 
-Next power of 2 after 5 is 8.
-Space of probabilities must be divided into 8 equal parts.
-Presuming the `Accuracy_Log` is 7, it defines a space of 128 states.
-Divided by 8, each share is 16 large.
+The next power of 2 after 5 is 8.
+Therefore, the probability space will be divided into 8 equal parts.
+Since the probability space is `1<<7 = 128` large, each share is `128/8 = 16` large.
 
-In order to reach 8 shares, 8-5=3 lowest states will count "double",
+In order to reach 8 shares, the `8-5 = 3` lowest states will count "double",
 doubling their shares (32 in width), hence requiring one more bit.
 
-Baseline is assigned starting from the higher states using fewer bits,
-increasing at each state, then resuming at the first state,
-each state takes its allocated width from Baseline.
+Baseline is assigned starting from the lowest state using fewer bits,
+continuing in natural state order, looping back at the beginning.
+Each state takes its allocated range from Baseline, sized by its `Number_of_Bits`.
 
-| state value      |   1   |  39   |   77   |  84  |  122   |
 | state order      |   0   |   1   |    2   |   3  |    4   |
 | ---------------- | ----- | ----- | ------ | ---- | ------ |
+| state value      |   1   |  39   |   77   |  84  |  122   |
 | width            |  32   |  32   |   32   |  16  |   16   |
 | `Number_of_Bits` |   5   |   5   |    5   |   4  |    4   |
-| range number     |   2   |   4   |    6   |   0  |    1   |
+| allocation order |   3   |   4   |    5   |   1  |    2   |
 | `Baseline`       |  32   |  64   |   96   |   0  |   16   |
 | range            | 32-63 | 64-95 | 96-127 | 0-15 | 16-31  |
 
-During decoding, the next state value is determined from current state value,
-by reading the required `Number_of_Bits`, and adding the specified `Baseline`.
+During decoding, the next state value is determined by using current state value as row number,
+then reading the required `Number_of_Bits` from the bitstream, and adding the specified `Baseline`.
+
+Note:
+as a trivial example, it follows that, for a symbol with a Probability of `1`,
+`Baseline` is necessarily `0`, and `Number_of_Bits` is necessarily `Accuracy_Log`.
 
-See [Appendix A] for the results of this process applied to the default distributions.
+See [Appendix A] to see the outcome of this process applied to the default distributions.
 
 [Appendix A]: #appendix-a---decoding-tables-for-predefined-codes
 
@@ -1241,15 +1270,17 @@ This specification limits maximum code length to 11 bits.
 
 #### Representation
 
-All literal values from zero (included) to last present one (excluded)
+All literal symbols from zero (included) to last present one (excluded)
 are represented by `Weight` with values from `0` to `Max_Number_of_Bits`.
 Transformation from `Weight` to `Number_of_Bits` follows this formula :
 ```
 Number_of_Bits = Weight ? (Max_Number_of_Bits + 1 - Weight) : 0
 ```
-When a literal value is not present, it receives a `Weight` of 0.
+When a literal symbol is not present, it receives a `Weight` of 0.
 The least frequent symbol receives a `Weight` of 1.
-Consequently, the `Weight` 1 is necessarily present.
+If no literal has a `Weight` of 1, then the data is considered corrupted.
+If there are not at least two literals with non-zero `Weight`, then the data
+is considered corrupted.
 The most frequent symbol receives a `Weight` anywhere between 1 and 11 (max).
 The last symbol's `Weight` is deduced from previously retrieved Weights,
 by completing to the nearest power of 2. It's necessarily non 0.
@@ -1262,33 +1293,38 @@ otherwise the representation is considered corrupted.
 __Example__ :
 Let's presume the following Huffman tree must be described :
 
-|  literal value   |  0  |  1  |  2  |  3  |  4  |  5  |
+|  literal symbol  |  A  |  B  |  C  |  D  |  E  |  F  |
 | ---------------- | --- | --- | --- | --- | --- | --- |
 | `Number_of_Bits` |  1  |  2  |  3  |  0  |  4  |  4  |
 
 The tree depth is 4, since its longest elements uses 4 bits
-(longest elements are the one with smallest frequency).
-Literal value `5` will not be listed, as it can be determined from previous values 0-4,
-nor will values above `5` as they are all 0.
-Values from `0` to `4` will be listed using `Weight` instead of `Number_of_Bits`.
+(longest elements are the ones with smallest frequency).
+
+All symbols will now receive a `Weight` instead of `Number_of_Bits`.
 Weight formula is :
 ```
 Weight = Number_of_Bits ? (Max_Number_of_Bits + 1 - Number_of_Bits) : 0
 ```
-It gives the following series of weights :
+It gives the following series of Weights :
+
+| literal symbol |  A  |  B  |  C  |  D  |  E  |  F  |
+| -------------- | --- | --- | --- | --- | --- | --- |
+|   `Weight`     |  4  |  3  |  2  |  0  |  1  |  1  |
+
+This list will be sent to the decoder, with the following modifications:
 
-| literal value |  0  |  1  |  2  |  3  |  4  |
-| ------------- | --- | --- | --- | --- | --- |
-|   `Weight`    |  4  |  3  |  2  |  0  |  1  |
+- `F` will not be listed, because it can be determined from previous symbols
+- nor will symbols above `F` as they are all 0
+- on the other hand, all symbols before `A`, starting with `\0`, will be listed, with a Weight of 0.
 
 The decoder will do the inverse operation :
-having collected weights of literal symbols from `0` to `4`,
-it knows the last literal, `5`, is present with a non-zero `Weight`.
-The `Weight` of `5` can be determined by advancing to the next power of 2.
+having collected weights of literal symbols from `A` to `E`,
+it knows the last literal, `F`, is present with a non-zero `Weight`.
+The `Weight` of `F` can be determined by advancing to the next power of 2.
 The sum of `2^(Weight-1)` (excluding 0's) is :
 `8 + 4 + 2 + 0 + 1 = 15`.
 Nearest larger power of 2 value is 16.
-Therefore, `Max_Number_of_Bits = 4` and `Weight[5] = log_2(16 - 15) + 1 = 1`.
+Therefore, `Max_Number_of_Bits = log2(16) = 4` and `Weight[F] = log_2(16 - 15) + 1 = 1`.
 
 #### Huffman Tree header
 
@@ -1328,7 +1364,7 @@ sharing a single distribution table.
 To decode an FSE bitstream, it is necessary to know its compressed size.
 Compressed size is provided by `headerByte`.
 It's also necessary to know its _maximum possible_ decompressed size,
-which is `255`, since literal values span from `0` to `255`,
+which is `255`, since literal symbols span from `0` to `255`,
 and last symbol's `Weight` is not represented.
 
 An FSE bitstream starts by a header, describing probabilities distribution.
@@ -1350,6 +1386,13 @@ If updating state after decoding a symbol would require more bits than
 remain in the stream, it is assumed that extra bits are 0.  Then,
 symbols for each of the final states are decoded and the process is complete.
 
+If this process would produce more weights than the maximum number of decoded
+weights (255), then the data is considered corrupted.
+
+If either of the 2 initial states are absent or truncated, then the data is
+considered corrupted.  Consequently, it is not possible to encode fewer than
+2 weights using this mode.
+
 #### Conversion from weights to Huffman prefix codes
 
 All present symbols shall now have a `Weight` value.
@@ -1357,26 +1400,28 @@ It is possible to transform weights into `Number_of_Bits`, using this formula:
 ```
 Number_of_Bits = (Weight>0) ? Max_Number_of_Bits + 1 - Weight : 0
 ```
-Symbols are sorted by `Weight`.
-Within same `Weight`, symbols keep natural sequential order.
+In order to determine which prefix code is assigned to each Symbol,
+Symbols are first sorted by `Weight`, then by natural sequential order.
 Symbols with a `Weight` of zero are removed.
-Then, starting from lowest `Weight`, prefix codes are distributed in sequential order.
+Then, starting from lowest `Weight` (hence highest `Number_of_Bits`),
+prefix codes are assigned in ascending order.
 
 __Example__ :
-Let's presume the following list of weights has been decoded :
+Let's assume the following list of weights has been decoded:
 
-| Literal  |  0  |  1  |  2  |  3  |  4  |  5  |
+| Literal  |  A  |  B  |  C  |  D  |  E  |  F  |
 | -------- | --- | --- | --- | --- | --- | --- |
 | `Weight` |  4  |  3  |  2  |  0  |  1  |  1  |
 
 Sorted by weight and then natural sequential order,
-it gives the following distribution :
+it gives the following prefix codes distribution:
 
-| Literal          |  3  |  4  |  5  |  2  |  1  |   0  |
-| ---------------- | --- | --- | --- | --- | --- | ---- |
-| `Weight`         |  0  |  1  |  1  |  2  |  3  |   4  |
-| `Number_of_Bits` |  0  |  4  |  4  |  3  |  2  |   1  |
-| prefix codes     | N/A | 0000| 0001| 001 | 01  |   1  |
+| Literal          |  D  |   E  |   F  |   C  |   B  |   A  |
+| ---------------- | --- | ---- | ---- | ---- | ---- | ---- |
+| `Weight`         |  0  |   1  |   1  |   2  |   3  |   4  |
+| `Number_of_Bits` |  0  |   4  |   4  |   3  |   2  |   1  |
+| prefix code      | N/A | 0000 | 0001 | 001  | 01   | 1    |
+| ascending order  | N/A | 0000 | 0001 | 001x | 01xx | 1xxx |
 
 ### Huffman-coded Streams
 
@@ -1399,10 +1444,10 @@ it's possible to read the bitstream in a __little-endian__ fashion,
 keeping track of already used bits. Since the bitstream is encoded in reverse
 order, starting from the end read symbols in forward order.
 
-For example, if the literal sequence "0145" was encoded using above prefix code,
+For example, if the literal sequence `ABEF` was encoded using above prefix code,
 it would be encoded (in reverse order) as:
 
-|Symbol  |   5  |   4  |  1 | 0 | Padding |
+|Symbol  |   F  |   E  |  B | A | Padding |
 |--------|------|------|----|---|---------|
 |Encoding|`0000`|`0001`|`01`|`1`| `00001` |
 
@@ -1697,6 +1742,10 @@ or at least provide a meaningful error code explaining for which reason it canno
 
 Version changes
 ---------------
+- 0.4.3 : clarifications for Huffman prefix code assignment example
+- 0.4.2 : refactor FSE table construction process, inspired by Donald Pian
+- 0.4.1 : clarifications on a few error scenarios, by Eric Lasota
+- 0.4.0 : fixed imprecise behavior for nbSeq==0, detected by Igor Pavlov
 - 0.3.9 : clarifications for Huffman-compressed literal sizes.
 - 0.3.8 : clarifications for Huffman Blocks and Huffman Tree descriptions.
 - 0.3.7 : clarifications for Repeat_Offsets, matching RFC8878

zstd.mod/zstd/doc/zstd_manual.html

@@ -1,16 +1,17 @@
 <html>
 <head>
 <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
-<title>zstd 1.5.5 Manual</title>
+<title>zstd 1.5.7 Manual</title>
 </head>
 <body>
-<h1>zstd 1.5.5 Manual</h1>
+<h1>zstd 1.5.7 Manual</h1>
+Note: the content of this file has been automatically generated by parsing "zstd.h" 
 <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">Simple API</a></li>
+<li><a href="#Chapter3">Simple Core API</a></li>
 <li><a href="#Chapter4">Explicit context</a></li>
 <li><a href="#Chapter5">Advanced compression API (Requires v1.4.0+)</a></li>
 <li><a href="#Chapter6">Advanced decompression API (Requires v1.4.0+)</a></li>
@@ -74,7 +75,7 @@
 </b><p>  Return runtime library version, like "1.4.5". Requires v1.3.0+. 
 </p></pre><BR>
 
-<a name="Chapter3"></a><h2>Simple API</h2><pre></pre>
+<a name="Chapter3"></a><h2>Simple Core API</h2><pre></pre>
 
 <pre><b>size_t ZSTD_compress( void* dst, size_t dstCapacity,
                 const void* src, size_t srcSize,
@@ -88,38 +89,42 @@
 
 <pre><b>size_t ZSTD_decompress( void* dst, size_t dstCapacity,
                   const void* src, size_t compressedSize);
-</b><p>  `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
-  `dstCapacity` is an upper bound of originalSize to regenerate.
-  If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
-  @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
-            or an errorCode if it fails (which can be tested using ZSTD_isError()). 
+</b><p> `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
+  Multiple compressed frames can be decompressed at once with this method.
+  The result will be the concatenation of all decompressed frames, back to back.
+ `dstCapacity` is an upper bound of originalSize to regenerate.
+  First frame's decompressed size can be extracted using ZSTD_getFrameContentSize().
+  If maximum upper bound isn't known, prefer using streaming mode to decompress data.
+ @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
+           or an errorCode if it fails (which can be tested using ZSTD_isError()). 
 </p></pre><BR>
 
+<h3>Decompression helper functions</h3><pre></pre><b><pre></pre></b><BR>
 <pre><b>#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
 #define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
 unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
-</b><p>  `src` should point to the start of a ZSTD encoded frame.
-  `srcSize` must be at least as large as the frame header.
-            hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
-  @return : - decompressed size of `src` frame content, if known
-            - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
-            - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
-   note 1 : a 0 return value means the frame is valid but "empty".
-   note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode.
-            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
-            In which case, it's necessary to use streaming mode to decompress data.
-            Optionally, application can rely on some implicit limit,
-            as ZSTD_decompress() only needs an upper bound of decompressed size.
-            (For example, data could be necessarily cut into blocks <= 16 KB).
-   note 3 : decompressed size is always present when compression is completed using single-pass functions,
-            such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict().
-   note 4 : decompressed size can be very large (64-bits value),
-            potentially larger than what local system can handle as a single memory segment.
-            In which case, it's necessary to use streaming mode to decompress data.
-   note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
-            Always ensure return value fits within application's authorized limits.
-            Each application can set its own limits.
-   note 6 : This function replaces ZSTD_getDecompressedSize() 
+</b><p> `src` should point to the start of a ZSTD encoded frame.
+ `srcSize` must be at least as large as the frame header.
+           hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
+ @return : - decompressed size of `src` frame content, if known
+           - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+           - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
+  note 1 : a 0 return value means the frame is valid but "empty".
+  note 2 : decompressed size is an optional field, it may not be present (typically in streaming mode).
+           When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
+           In which case, it's necessary to use streaming mode to decompress data.
+           Optionally, application can rely on some implicit limit,
+           as ZSTD_decompress() only needs an upper bound of decompressed size.
+           (For example, data could be necessarily cut into blocks <= 16 KB).
+  note 3 : decompressed size is always present when compression is completed using single-pass functions,
+           such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict().
+  note 4 : decompressed size can be very large (64-bits value),
+           potentially larger than what local system can handle as a single memory segment.
+           In which case, it's necessary to use streaming mode to decompress data.
+  note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+           Always ensure return value fits within application's authorized limits.
+           Each application can set its own limits.
+  note 6 : This function replaces ZSTD_getDecompressedSize() 
 </p></pre><BR>
 
 <pre><b>ZSTD_DEPRECATED("Replaced by ZSTD_getFrameContentSize")
@@ -140,67 +145,71 @@ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
         or an error code if input is invalid 
 </p></pre><BR>
 
-<h3>Helper functions</h3><pre></pre><b><pre></b>/* ZSTD_compressBound() :<b>
- * maximum compressed size in worst case single-pass scenario.
- * When invoking `ZSTD_compress()` or any other one-pass compression function,
- * it's recommended to provide @dstCapacity >= ZSTD_compressBound(srcSize)
- * as it eliminates one potential failure scenario,
- * aka not enough room in dst buffer to write the compressed frame.
- * Note : ZSTD_compressBound() itself can fail, if @srcSize > ZSTD_MAX_INPUT_SIZE .
- *        In which case, ZSTD_compressBound() will return an error code
- *        which can be tested using ZSTD_isError().
- *
- * ZSTD_COMPRESSBOUND() :
- * same as ZSTD_compressBound(), but as a macro.
- * It can be used to produce constants, which can be useful for static allocation,
- * for example to size a static array on stack.
- * Will produce constant value 0 if srcSize too large.
- */
-#define ZSTD_MAX_INPUT_SIZE ((sizeof(size_t)==8) ? 0xFF00FF00FF00FF00LLU : 0xFF00FF00U)
+<h3>Compression helper functions</h3><pre></pre><b><pre></pre></b><BR>
+<pre><b>#define ZSTD_MAX_INPUT_SIZE ((sizeof(size_t)==8) ? 0xFF00FF00FF00FF00ULL : 0xFF00FF00U)
 #define ZSTD_COMPRESSBOUND(srcSize)   (((size_t)(srcSize) >= ZSTD_MAX_INPUT_SIZE) ? 0 : (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>
+</b><p> maximum compressed size in worst case single-pass scenario.
+ When invoking `ZSTD_compress()`, or any other one-pass compression function,
+ it's recommended to provide @dstCapacity >= ZSTD_compressBound(srcSize)
+ as it eliminates one potential failure scenario,
+ aka not enough room in dst buffer to write the compressed frame.
+ Note : ZSTD_compressBound() itself can fail, if @srcSize >= ZSTD_MAX_INPUT_SIZE .
+        In which case, ZSTD_compressBound() will return an error code
+        which can be tested using ZSTD_isError().
+
+ ZSTD_COMPRESSBOUND() :
+ same as ZSTD_compressBound(), but as a macro.
+ It can be used to produce constants, which can be useful for static allocation,
+ for example to size a static array on stack.
+ Will produce constant value 0 if srcSize is too large.
+ 
+</p></pre><BR>
+
+<h3>Error helper functions</h3><pre></pre><b><pre>#include "zstd_errors.h" </b>/* list of errors */<b>
 </b>/* ZSTD_isError() :<b>
  * Most ZSTD_* functions returning a size_t value can be tested for error,
  * using ZSTD_isError().
  * @return 1 if error, 0 otherwise
  */
-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, requires v1.4.0+ */<b>
-int         ZSTD_maxCLevel(void);               </b>/*!< maximum compression level available */<b>
-int         ZSTD_defaultCLevel(void);           </b>/*!< default compression level, specified by ZSTD_CLEVEL_DEFAULT, requires v1.5.0+ */<b>
+unsigned     ZSTD_isError(size_t result);      </b>/*!< tells if a `size_t` function result is an error code */<b>
+ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); </b>/* convert a result into an error code, which can be compared to error enum list */<b>
+const char*  ZSTD_getErrorName(size_t result); </b>/*!< provides readable string from a function result */<b>
+int          ZSTD_minCLevel(void);             </b>/*!< minimum negative compression level allowed, requires v1.4.0+ */<b>
+int          ZSTD_maxCLevel(void);             </b>/*!< maximum compression level available */<b>
+int          ZSTD_defaultCLevel(void);         </b>/*!< default compression level, specified by ZSTD_CLEVEL_DEFAULT, requires v1.5.0+ */<b>
 </pre></b><BR>
 <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.
-  This will make workload friendlier for system's memory.
+  it is recommended to allocate a compression context just once,
+  and reuse it for each successive compression operation.
+  This will make the workload easier for system's memory.
   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.
+  Note 2: For parallel execution in multi-threaded environments,
+         use one different context per thread .
  
 </pre><b><pre>typedef struct ZSTD_CCtx_s ZSTD_CCtx;
 ZSTD_CCtx* ZSTD_createCCtx(void);
-size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);  </b>/* accept NULL pointer */<b>
+size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);  </b>/* compatible with NULL pointer */<b>
 </pre></b><BR>
 <pre><b>size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx,
                          void* dst, size_t dstCapacity,
                    const void* src, size_t srcSize,
                          int compressionLevel);
 </b><p>  Same as ZSTD_compress(), using an explicit ZSTD_CCtx.
-  Important : in order to behave similarly to `ZSTD_compress()`,
-  this function compresses at requested compression level,
-  __ignoring any other parameter__ .
+  Important : in order to mirror `ZSTD_compress()` behavior,
+  this function compresses at the requested compression level,
+  __ignoring any other advanced parameter__ .
   If any advanced parameter was set using the advanced API,
-  they will all be reset. Only `compressionLevel` remains.
+  they will all be reset. Only @compressionLevel remains.
  
 </p></pre><BR>
 
 <h3>Decompression context</h3><pre>  When decompressing many times,
   it is recommended to allocate a context only once,
-  and re-use it for each successive compression operation.
+  and reuse it for each successive compression operation.
   This will make workload friendlier for system's memory.
   Use one context per thread for parallel execution. 
 </pre><b><pre>typedef struct ZSTD_DCtx_s ZSTD_DCtx;
@@ -212,7 +221,7 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
                      const void* src, size_t srcSize);
 </b><p>  Same as ZSTD_decompress(),
   requires an allocated ZSTD_DCtx.
-  Compatible with sticky parameters.
+  Compatible with sticky parameters (see below).
  
 </p></pre><BR>
 
@@ -296,6 +305,19 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
                               * The higher the value of selected strategy, the more complex it is,
                               * resulting in stronger and slower compression.
                               * Special: value 0 means "use default strategy". */
+
+    ZSTD_c_targetCBlockSize=130, </b>/* v1.5.6+<b>
+                                  * Attempts to fit compressed block size into approximately targetCBlockSize.
+                                  * Bound by ZSTD_TARGETCBLOCKSIZE_MIN and ZSTD_TARGETCBLOCKSIZE_MAX.
+                                  * Note that it's not a guarantee, just a convergence target (default:0).
+                                  * No target when targetCBlockSize == 0.
+                                  * This is helpful in low bandwidth streaming environments to improve end-to-end latency,
+                                  * when a client can make use of partial documents (a prominent example being Chrome).
+                                  * Note: this parameter is stable since v1.5.6.
+                                  * It was present as an experimental parameter in earlier versions,
+                                  * but it's not recommended using it with earlier library versions
+                                  * due to massive performance regressions.
+                                  */
     </b>/* LDM mode parameters */<b>
     ZSTD_c_enableLongDistanceMatching=160, </b>/* Enable long distance matching.<b>
                                      * This parameter is designed to improve compression ratio
@@ -375,14 +397,14 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
      * ZSTD_c_forceMaxWindow
      * ZSTD_c_forceAttachDict
      * ZSTD_c_literalCompressionMode
-     * ZSTD_c_targetCBlockSize
      * ZSTD_c_srcSizeHint
      * ZSTD_c_enableDedicatedDictSearch
      * ZSTD_c_stableInBuffer
      * ZSTD_c_stableOutBuffer
      * ZSTD_c_blockDelimiters
      * ZSTD_c_validateSequences
-     * ZSTD_c_useBlockSplitter
+     * ZSTD_c_blockSplitterLevel
+     * ZSTD_c_splitAfterSequences
      * ZSTD_c_useRowMatchFinder
      * ZSTD_c_prefetchCDictTables
      * ZSTD_c_enableSeqProducerFallback
@@ -396,7 +418,7 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
      ZSTD_c_experimentalParam3=1000,
      ZSTD_c_experimentalParam4=1001,
      ZSTD_c_experimentalParam5=1002,
-     ZSTD_c_experimentalParam6=1003,
+     </b>/* was ZSTD_c_experimentalParam6=1003; is now ZSTD_c_targetCBlockSize */<b>
      ZSTD_c_experimentalParam7=1004,
      ZSTD_c_experimentalParam8=1005,
      ZSTD_c_experimentalParam9=1006,
@@ -409,7 +431,8 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
      ZSTD_c_experimentalParam16=1013,
      ZSTD_c_experimentalParam17=1014,
      ZSTD_c_experimentalParam18=1015,
-     ZSTD_c_experimentalParam19=1016
+     ZSTD_c_experimentalParam19=1016,
+     ZSTD_c_experimentalParam20=1017
 } ZSTD_cParameter;
 </b></pre><BR>
 <pre><b>typedef struct {
@@ -483,6 +506,7 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
                        void* dst, size_t dstCapacity,
                  const void* src, size_t srcSize);
 </b><p>  Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API.
+  (note that this entry point doesn't even expose a compression level parameter).
   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*()
@@ -513,6 +537,7 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
      * ZSTD_d_forceIgnoreChecksum
      * ZSTD_d_refMultipleDDicts
      * ZSTD_d_disableHuffmanAssembly
+     * ZSTD_d_maxBlockSize
      * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
      * note : never ever use experimentalParam? names directly
      */
@@ -520,7 +545,8 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
      ZSTD_d_experimentalParam2=1001,
      ZSTD_d_experimentalParam3=1002,
      ZSTD_d_experimentalParam4=1003,
-     ZSTD_d_experimentalParam5=1004
+     ZSTD_d_experimentalParam5=1004,
+     ZSTD_d_experimentalParam6=1005
 
 } ZSTD_dParameter;
 </b></pre><BR>
@@ -568,14 +594,14 @@ size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  </b>/* accept NULL pointer */<b>
   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.
+  It is recommended to reuse 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.
+  it will reuse 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
@@ -666,6 +692,11 @@ size_t ZSTD_freeCStream(ZSTD_CStream* zcs);  </b>/* accept NULL pointer */<b>
             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.
+  - note: if an operation ends with an error, it may leave @cctx in an undefined state.
+          Therefore, it's UB to invoke ZSTD_compressStream2() of ZSTD_compressStream() on such a state.
+          In order to be re-employed after an error, a state must be reset,
+          which can be done explicitly (ZSTD_CCtx_reset()),
+          or is sometimes implied by methods starting a new compression job (ZSTD_initCStream(), ZSTD_compressCCtx())
  
 </p></pre><BR>
 
@@ -698,7 +729,7 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
 <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.
+  ZSTD_DStream objects can be re-employed multiple times.
 
   Use ZSTD_initDStream() to start a new decompression operation.
  @return : recommended first input size
@@ -708,16 +739,21 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
   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.,
+
+  However, when `output.pos == output.size`, it's more difficult to know.
+  If @return > 0, the frame is not complete, meaning
+  either there is still some data left to flush within internal buffers,
+  or there is more input to read to complete the frame (or both).
   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.
+                                that will never request more than the remaining content of the compressed frame.
  
 <BR></pre>
 
@@ -743,14 +779,21 @@ size_t ZSTD_freeDStream(ZSTD_DStream* zds);  </b>/* accept NULL pointer */<b>
  Function will update both input and output `pos` fields exposing current state via these fields:
  - `input.pos < input.size`, some input remaining and caller should provide remaining input
    on the next call.
- - `output.pos < output.size`, decoder finished and flushed all remaining buffers.
- - `output.pos == output.size`, potentially uncflushed data present in the internal buffers,
-   call ZSTD_decompressStream() again to flush remaining data to output.
+ - `output.pos < output.size`, decoder flushed internal output buffer.
+ - `output.pos == output.size`, unflushed data potentially present in the internal buffers,
+   check ZSTD_decompressStream() @return value,
+   if > 0, invoke it again to flush remaining data to output.
  Note : with no additional input, amount of data flushed <= 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 some decoding or flushing to do to complete current frame.
+
+ Note: when an operation returns with an error code, the @zds state may be left in undefined state.
+       It's UB to invoke `ZSTD_decompressStream()` on such a state.
+       In order to re-use such a state, it must be first reset,
+       which can be done explicitly (`ZSTD_DCtx_reset()`),
+       or is implied for operations starting some new decompression job (`ZSTD_initDStream`, `ZSTD_decompressDCtx()`, `ZSTD_decompress_usingDict()`)
  
 </p></pre><BR>
 
@@ -869,7 +912,7 @@ size_t ZSTD_freeDStream(ZSTD_DStream* zds);  </b>/* accept NULL pointer */<b>
 <a name="Chapter13"></a><h2>Advanced dictionary and prefix API (Requires v1.4.0+)</h2><pre>
  This API allows dictionaries to be used with ZSTD_compress2(),
  ZSTD_compressStream2(), and ZSTD_decompressDCtx().
- Dictionaries are sticky, they remain valid when same context is re-used,
+ Dictionaries are sticky, they remain valid when same context is reused,
  they only reset when the context is reset
  with ZSTD_reset_parameters or ZSTD_reset_session_and_parameters.
  In contrast, Prefixes are single-use.
@@ -1041,7 +1084,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
                                *
                                * Note: This field is optional. ZSTD_generateSequences() will calculate the value of
                                * 'rep', but repeat offsets do not necessarily need to be calculated from an external
-                               * sequence provider's perspective. For example, ZSTD_compressSequences() does not
+                               * sequence provider perspective. For example, ZSTD_compressSequences() does not
                                * use this 'rep' field at all (as of now).
                                */
 } ZSTD_Sequence;
@@ -1146,14 +1189,14 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 } ZSTD_literalCompressionMode_e;
 </b></pre><BR>
 <pre><b>typedef enum {
-  </b>/* Note: This enum controls features which are conditionally beneficial. Zstd typically will make a final<b>
-   * decision on whether or not to enable the feature (ZSTD_ps_auto), but setting the switch to ZSTD_ps_enable
-   * or ZSTD_ps_disable allow for a force enable/disable the feature.
+  </b>/* Note: This enum controls features which are conditionally beneficial.<b>
+   * Zstd can take a decision on whether or not to enable the feature (ZSTD_ps_auto),
+   * but setting the switch to ZSTD_ps_enable or ZSTD_ps_disable force enable/disable the feature.
    */
   ZSTD_ps_auto = 0,         </b>/* Let the library automatically determine whether the feature shall be enabled */<b>
   ZSTD_ps_enable = 1,       </b>/* Force-enable the feature */<b>
   ZSTD_ps_disable = 2       </b>/* Do not use the feature */<b>
-} ZSTD_paramSwitch_e;
+} ZSTD_ParamSwitch_e;
 </b></pre><BR>
 <a name="Chapter15"></a><h2>Frame header and size functions</h2><pre></pre>
 
@@ -1201,13 +1244,13 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
            or an error code (if srcSize is too small) 
 </p></pre><BR>
 
-<pre><b>typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e;
+<pre><b>typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_FrameType_e;
 </b></pre><BR>
 <pre><b>typedef struct {
     unsigned long long frameContentSize; </b>/* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */<b>
     unsigned long long windowSize;       </b>/* can be very large, up to <= frameContentSize */<b>
     unsigned blockSizeMax;
-    ZSTD_frameType_e frameType;          </b>/* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */<b>
+    ZSTD_FrameType_e frameType;          </b>/* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */<b>
     unsigned headerSize;
     unsigned dictID;
     unsigned checksumFlag;
@@ -1215,11 +1258,11 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
     unsigned _reserved2;
 } ZSTD_frameHeader;
 </b></pre><BR>
-<pre><b>ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize);   </b>/**< doesn't consume input */<b>
+<pre><b>ZSTDLIB_STATIC_API 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) */
-ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format);
+ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_FrameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format);
 </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,
@@ -1272,9 +1315,9 @@ ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr,
 </p></pre><BR>
 
 <pre><b>typedef enum {
-  ZSTD_sf_noBlockDelimiters = 0,         </b>/* Representation of ZSTD_Sequence has no block delimiters, sequences only */<b>
-  ZSTD_sf_explicitBlockDelimiters = 1    </b>/* Representation of ZSTD_Sequence contains explicit block delimiters */<b>
-} ZSTD_sequenceFormat_e;
+  ZSTD_sf_noBlockDelimiters = 0,         </b>/* ZSTD_Sequence[] has no block delimiters, just sequences */<b>
+  ZSTD_sf_explicitBlockDelimiters = 1    </b>/* ZSTD_Sequence[] contains explicit block delimiters */<b>
+} ZSTD_SequenceFormat_e;
 </b></pre><BR>
 <pre><b>ZSTDLIB_STATIC_API size_t ZSTD_sequenceBound(size_t srcSize);
 </b><p> `srcSize` : size of the input buffer
@@ -1285,19 +1328,37 @@ ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr,
  
 </p></pre><BR>
 
-<pre><b></b><p> Generate sequences using ZSTD_compress2(), given a source buffer.
+<pre><b>ZSTD_DEPRECATED("For debugging only, will be replaced by ZSTD_extractSequences()")
+ZSTDLIB_STATIC_API size_t
+ZSTD_generateSequences(ZSTD_CCtx* zc,
+           ZSTD_Sequence* outSeqs, size_t outSeqsCapacity,
+           const void* src, size_t srcSize);
+</b><p> WARNING: This function is meant for debugging and informational purposes ONLY!
+ Its implementation is flawed, and it will be deleted in a future version.
+ It is not guaranteed to succeed, as there are several cases where it will give
+ up and fail. You should NOT use this function in production code.
+
+ This function is deprecated, and will be removed in a future version.
+
+ Generate sequences using ZSTD_compress2(), given a source buffer.
+
+ @param zc The compression context to be used for ZSTD_compress2(). Set any
+           compression parameters you need on this context.
+ @param outSeqs The output sequences buffer of size @p outSeqsSize
+ @param outSeqsCapacity The size of the output sequences buffer.
+                    ZSTD_sequenceBound(srcSize) is an upper bound on the number
+                    of sequences that can be generated.
+ @param src The source buffer to generate sequences from of size @p srcSize.
+ @param srcSize The size of the source buffer.
 
  Each block will end with a dummy sequence
  with offset == 0, matchLength == 0, and litLength == length of last literals.
  litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0)
  simply acts as a block delimiter.
 
- @zc can be used to insert custom compression params.
- This function invokes ZSTD_compress2().
-
- The output of this function can be fed into ZSTD_compressSequences() with CCtx
- setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters
- @return : number of sequences generated
+ @returns The number of sequences generated, necessarily less than
+          ZSTD_sequenceBound(srcSize), or an error code that can be checked
+          with ZSTD_isError().
  
 </p></pre><BR>
 
@@ -1315,13 +1376,14 @@ ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr,
 </p></pre><BR>
 
 <pre><b>ZSTDLIB_STATIC_API size_t
-ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
-            const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
-            const void* src, size_t srcSize);
+ZSTD_compressSequences(ZSTD_CCtx* cctx,
+           void* dst, size_t dstCapacity,
+     const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+     const void* src, size_t srcSize);
 </b><p> Compress an array of ZSTD_Sequence, associated with @src buffer, into dst.
  @src contains the entire input (not just the literals).
  If @srcSize > sum(sequence.length), the remaining bytes are considered all literals
- If a dictionary is included, then the cctx should reference the dict. (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.)
+ If a dictionary is included, then the cctx should reference the dict (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.).
  The entire source is compressed into a single frame.
 
  The compression behavior changes based on cctx params. In particular:
@@ -1330,11 +1392,17 @@ ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
     the block size derived from the cctx, and sequences may be split. This is the default setting.
 
     If ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, the array of ZSTD_Sequence is expected to contain
-    block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided.
+    valid block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided.
+
+    When ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, it's possible to decide generating repcodes
+    using the advanced parameter ZSTD_c_repcodeResolution. Repcodes will improve compression ratio, though the benefit
+    can vary greatly depending on Sequences. On the other hand, repcode resolution is an expensive operation.
+    By default, it's disabled at low (<10) compression levels, and enabled above the threshold (>=10).
+    ZSTD_c_repcodeResolution makes it possible to directly manage this processing in either direction.
 
-    If ZSTD_c_validateSequences == 0, this function will blindly accept the sequences provided. Invalid sequences cause undefined
-    behavior. If ZSTD_c_validateSequences == 1, then if sequence is invalid (see doc/zstd_compression_format.md for
-    specifics regarding offset/matchlength requirements) then the function will bail out and return an error.
+    If ZSTD_c_validateSequences == 0, this function blindly accepts the Sequences provided. Invalid Sequences cause undefined
+    behavior. If ZSTD_c_validateSequences == 1, then the function will detect invalid Sequences (see doc/zstd_compression_format.md for
+    specifics regarding offset/matchlength requirements) and then bail out and return an error.
 
     In addition to the two adjustable experimental params, there are other important cctx params.
     - ZSTD_c_minMatch MUST be set as less than or equal to the smallest match generated by the match finder. It has a minimum value of ZSTD_MINMATCH_MIN.
@@ -1342,9 +1410,33 @@ ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
     - ZSTD_c_windowLog affects offset validation: this function will return an error at higher debug levels if a provided offset
       is larger than what the spec allows for a given window log and dictionary (if present). See: doc/zstd_compression_format.md
 
- Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused.
- Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly,
-         and cannot emit an RLE block that disagrees with the repcode history
+ Note: Repcodes are, as of now, always re-calculated within this function, ZSTD_Sequence.rep is effectively unused.
+ Dev Note: Once ability to ingest repcodes become available, the explicit block delims mode must respect those repcodes exactly,
+         and cannot emit an RLE block that disagrees with the repcode history.
+ @return : final compressed size, or a ZSTD error code.
+ 
+</p></pre><BR>
+
+<pre><b>ZSTDLIB_STATIC_API size_t
+ZSTD_compressSequencesAndLiterals(ZSTD_CCtx* cctx,
+                      void* dst, size_t dstCapacity,
+                const ZSTD_Sequence* inSeqs, size_t nbSequences,
+                const void* literals, size_t litSize, size_t litCapacity,
+                size_t decompressedSize);
+</b><p> This is a variant of ZSTD_compressSequences() which,
+ instead of receiving (src,srcSize) as input parameter, receives (literals,litSize),
+ aka all the literals, already extracted and laid out into a single continuous buffer.
+ This can be useful if the process generating the sequences also happens to generate the buffer of literals,
+ thus skipping an extraction + caching stage.
+ It's a speed optimization, useful when the right conditions are met,
+ but it also features the following limitations:
+ - Only supports explicit delimiter mode
+ - Currently does not support Sequences validation (so input Sequences are trusted)
+ - Not compatible with frame checksum, which must be disabled
+ - If any block is incompressible, will fail and return an error
+ - @litSize must be == sum of all @.litLength fields in @inSeqs. Any discrepancy will generate an error.
+ - the buffer @literals must have a size @litCapacity which is larger than @litSize by at least 8 bytes.
+ - @decompressedSize must be correct, and correspond to the sum of all Sequences. Any discrepancy will generate an error.
  @return : final compressed size, or a ZSTD error code.
  
 </p></pre><BR>
@@ -1386,58 +1478,61 @@ ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
 
 <a name="Chapter16"></a><h2>Memory management</h2><pre></pre>
 
-<pre><b>ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
+<pre><b>ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize(int maxCompressionLevel);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateDCtxSize(void);
 </b><p>  These functions make it possible to estimate memory usage
   of a future {D,C}Ctx, before its creation.
+  This is useful in combination with ZSTD_initStatic(),
+  which makes it possible to employ a static buffer for ZSTD_CCtx* state.
 
   ZSTD_estimateCCtxSize() will provide a memory budget large enough
-  for any compression level up to selected one.
-  Note : Unlike ZSTD_estimateCStreamSize*(), this estimate
-         does not include space for a window buffer.
-         Therefore, the estimation is only guaranteed for single-shot compressions, not streaming.
+  to compress data of any size using one-shot compression ZSTD_compressCCtx() or ZSTD_compress2()
+  associated with any compression level up to max specified one.
   The estimate will assume the input may be arbitrarily large,
   which is the worst case.
 
+  Note that the size estimation is specific for one-shot compression,
+  it is not valid for streaming (see ZSTD_estimateCStreamSize*())
+  nor other potential ways of using a ZSTD_CCtx* state.
+
   When srcSize can be bound by a known and rather "small" value,
-  this fact can be used to provide a tighter estimation
-  because the CCtx compression context will need less memory.
-  This tighter estimation can be provided by more advanced functions
+  this knowledge can be used to provide a tighter budget estimation
+  because the ZSTD_CCtx* state will need less memory for small inputs.
+  This tighter estimation can be provided by employing more advanced functions
   ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(),
   and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter().
   Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits.
 
   Note : only single-threaded compression is supported.
   ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1.
-
-  Note 2 : ZSTD_estimateCCtxSize* functions are not compatible with the Block-Level Sequence Producer API at this time.
-  Size estimates assume that no external sequence producer is registered.
  
 </p></pre><BR>
 
-<pre><b>ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize(int compressionLevel);
+<pre><b>ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize(int maxCompressionLevel);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params);
-ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize(size_t windowSize);
+ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize(size_t maxWindowSize);
 ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize);
-</b><p>  ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one.
-  It will also consider src size to be arbitrarily "large", which is worst case.
+</b><p>  ZSTD_estimateCStreamSize() will provide a memory budget large enough for streaming compression
+  using any compression level up to the max specified one.
+  It will also consider src size to be arbitrarily "large", which is a worst case scenario.
   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_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.
+  ZSTD_estimateCStreamSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1.
+  Note 2 : ZSTD_estimateCStreamSize* functions are not compatible with the Block-Level Sequence Producer API at this time.
+  Size estimates assume that no external sequence producer is registered.
+
+  ZSTD_DStream memory budget depends on frame's window Size.
   This information can be passed manually, using ZSTD_estimateDStreamSize,
   or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame();
+  Any frame requesting a window size larger than max specified one will be rejected.
   Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
          an internal ?Dict will be created, which additional size is not estimated here.
          In this case, get total size by adding ZSTD_estimate?DictSize
-  Note 2 : only single-threaded compression is supported.
-  ZSTD_estimateCStreamSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1.
-  Note 3 : ZSTD_estimateCStreamSize* functions are not compatible with the Block-Level Sequence Producer API at this time.
-  Size estimates assume that no external sequence producer is registered.
  
 </p></pre><BR>
 
@@ -1483,13 +1578,14 @@ static
 #ifdef __GNUC__
 __attribute__((__unused__))
 #endif
-ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL };  </b>/**< this constant defers to stdlib's functions */<b>
 </b><p>  These prototypes make it possible to pass your own allocation/free functions.
   ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below.
   All allocation/free operations will be completed using these custom variants instead of regular <stdlib.h> ones.
  
 </p></pre><BR>
 
+<pre><b>ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL };  </b>/**< this constant defers to stdlib's functions */<b>
+</b></pre><BR>
 <pre><b>typedef struct POOL_ctx_s ZSTD_threadPool;
 ZSTDLIB_STATIC_API ZSTD_threadPool* ZSTD_createThreadPool(size_t numThreads);
 ZSTDLIB_STATIC_API void ZSTD_freeThreadPool (ZSTD_threadPool* pool);  </b>/* accept NULL pointer */<b>
@@ -1857,7 +1953,7 @@ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
        explicitly specified.
 
   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.
+  This is typically useful to skip dictionary loading stage, since it will reuse 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.
   If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end.
@@ -1918,7 +2014,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
 </b><p>
      ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
 
- re-use decompression parameters from previous init; saves dictionary loading
+ reuse decompression parameters from previous init; saves dictionary loading
  
 </p></pre><BR>
 
@@ -1926,7 +2022,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
 ZSTD_registerSequenceProducer(
   ZSTD_CCtx* cctx,
   void* sequenceProducerState,
-  ZSTD_sequenceProducer_F* sequenceProducer
+  ZSTD_sequenceProducer_F sequenceProducer
 );
 </b><p> Instruct zstd to use a block-level external sequence producer function.
 
@@ -1948,6 +2044,22 @@ ZSTD_registerSequenceProducer(
  calling this function. 
 </p></pre><BR>
 
+<pre><b>ZSTDLIB_STATIC_API void
+ZSTD_CCtxParams_registerSequenceProducer(
+  ZSTD_CCtx_params* params,
+  void* sequenceProducerState,
+  ZSTD_sequenceProducer_F sequenceProducer
+);
+</b><p> Same as ZSTD_registerSequenceProducer(), but operates on ZSTD_CCtx_params.
+ This is used for accurate size estimation with ZSTD_estimateCCtxSize_usingCCtxParams(),
+ which is needed when creating a ZSTD_CCtx with ZSTD_initStaticCCtx().
+
+ If you are using the external sequence producer API in a scenario where ZSTD_initStaticCCtx()
+ is required, then this function is for you. Otherwise, you probably don't need it.
+
+ See tests/zstreamtest.c for example usage. 
+</p></pre><BR>
+
 <a name="Chapter20"></a><h2>Buffer-less and synchronous inner streaming functions (DEPRECATED)</h2><pre>
   This API is deprecated, and will be removed in a future version.
   It allows streaming (de)compression with user allocated buffers.
@@ -1964,7 +2076,7 @@ ZSTD_registerSequenceProducer(
 <a name="Chapter21"></a><h2>Buffer-less streaming compression (synchronous mode)</h2><pre>
   A ZSTD_CCtx object is required to track streaming operations.
   Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource.
-  ZSTD_CCtx object can be re-used multiple times within successive compression operations.
+  ZSTD_CCtx object can be reused multiple times within successive compression operations.
 
   Start by initializing a context.
   Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression.
@@ -1985,7 +2097,7 @@ ZSTD_registerSequenceProducer(
   It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame.
   Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders.
 
-  `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again.
+  `ZSTD_CCtx` object can be reused (ZSTD_compressBegin()) to compress again.
 <BR></pre>
 
 <h3>Buffer-less streaming compression functions</h3><pre></pre><b><pre>ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.")
@@ -2002,7 +2114,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const Z
 <a name="Chapter22"></a><h2>Buffer-less streaming decompression (synchronous mode)</h2><pre>
   A ZSTD_DCtx object is required to track streaming operations.
   Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
-  A ZSTD_DCtx object can be re-used multiple times.
+  A ZSTD_DCtx object can be reused multiple times.
 
   First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
   Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough.
@@ -2012,7 +2124,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const Z
            >0 : `srcSize` is too small, please provide at least result bytes on next attempt.
            errorCode, which can be tested using ZSTD_isError().
 
-  It fills a ZSTD_frameHeader structure with important information to correctly decode the frame,
+  It fills a ZSTD_FrameHeader structure with important information to correctly decode the frame,
   such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`).
   Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information.
   As a consequence, check that values remain within valid application range.

zstd.mod/zstd/examples/streaming_compression.c

@@ -42,7 +42,13 @@ static void compressFile_orDie(const char* fname, const char* outName, int cLeve
      */
     CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, cLevel) );
     CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1) );
-    ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, nbThreads);
+    if (nbThreads > 1) {
+        size_t const r = ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, nbThreads);
+        if (ZSTD_isError(r)) {
+            fprintf (stderr, "Note: the linked libzstd library doesn't support multithreading. "
+                             "Reverting to single-thread mode. \n");
+        }
+    }
 
     /* This loop read from the input file, compresses that entire chunk,
      * and writes all output produced to the output file.
@@ -117,7 +123,7 @@ int main(int argc, const char** argv)
     }
 
     int cLevel = 1;
-    int nbThreads = 4;
+    int nbThreads = 1;
 
     if (argc >= 3) {
       cLevel = atoi (argv[2]);

zstd.mod/zstd/lib/Makefile

@@ -8,6 +8,9 @@
 # You may select, at your option, one of the above-listed licenses.
 # ################################################################
 
+# default target (when running `make` with no argument)
+lib-release:
+
 # Modules
 ZSTD_LIB_COMPRESSION ?= 1
 ZSTD_LIB_DECOMPRESSION ?= 1
@@ -54,13 +57,14 @@ VERSION := $(ZSTD_VERSION)
 # Note: by default, the static library is built single-threaded and dynamic library is built
 # multi-threaded. It is possible to force multi or single threaded builds by appending
 # -mt or -nomt to the build target (like lib-mt for multi-threaded, lib-nomt for single-threaded).
-.PHONY: default
-default: lib-release
+
 
 CPPFLAGS_DYNLIB  += -DZSTD_MULTITHREAD # dynamic library build defaults to multi-threaded
 LDFLAGS_DYNLIB   += -pthread
-CPPFLAGS_STATLIB +=                    # static library build defaults to single-threaded
+CPPFLAGS_STATICLIB +=                  # static library build defaults to single-threaded
 
+# pkg-config Libs.private points to LDFLAGS_DYNLIB
+PCLIB := $(LDFLAGS_DYNLIB)
 
 ifeq ($(findstring GCC,$(CCVER)),GCC)
 decompress/zstd_decompress_block.o : CFLAGS+=-fno-tree-vectorize
@@ -69,13 +73,15 @@ endif
 
 # macOS linker doesn't support -soname, and use different extension
 # see : https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html
-ifeq ($(UNAME), Darwin)
+UNAME_TARGET_SYSTEM ?= $(UNAME)
+
+ifeq ($(UNAME_TARGET_SYSTEM), Darwin)
   SHARED_EXT = dylib
   SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT)
   SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT)
   SONAME_FLAGS = -install_name $(LIBDIR)/libzstd.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER)
 else
-  ifeq ($(UNAME), AIX)
+  ifeq ($(UNAME_TARGET_SYSTEM), AIX)
     SONAME_FLAGS =
   else
     SONAME_FLAGS = -Wl,-soname=libzstd.$(SHARED_EXT).$(LIBVER_MAJOR)
@@ -91,7 +97,7 @@ all: lib
 
 
 .PHONY: libzstd.a  # must be run every time
-libzstd.a: CPPFLAGS += $(CPPFLAGS_STATLIB)
+libzstd.a: CPPFLAGS += $(CPPFLAGS_STATICLIB)
 
 SET_CACHE_DIRECTORY = \
    +$(MAKE) --no-print-directory $@ \
@@ -109,19 +115,19 @@ libzstd.a:
 else
 # BUILD_DIR is defined
 
-ZSTD_STATLIB_DIR := $(BUILD_DIR)/static
-ZSTD_STATLIB := $(ZSTD_STATLIB_DIR)/libzstd.a
-ZSTD_STATLIB_OBJ := $(addprefix $(ZSTD_STATLIB_DIR)/,$(ZSTD_LOCAL_OBJ))
-$(ZSTD_STATLIB): ARFLAGS = rcs
-$(ZSTD_STATLIB): | $(ZSTD_STATLIB_DIR)
-$(ZSTD_STATLIB): $(ZSTD_STATLIB_OBJ)
+ZSTD_STATICLIB_DIR := $(BUILD_DIR)/static
+ZSTD_STATICLIB := $(ZSTD_STATICLIB_DIR)/libzstd.a
+ZSTD_STATICLIB_OBJ := $(addprefix $(ZSTD_STATICLIB_DIR)/,$(ZSTD_LOCAL_OBJ))
+$(ZSTD_STATICLIB): ARFLAGS = rcs
+$(ZSTD_STATICLIB): | $(ZSTD_STATICLIB_DIR)
+$(ZSTD_STATICLIB): $(ZSTD_STATICLIB_OBJ)
   # Check for multithread flag at target execution time
 	$(if $(filter -DZSTD_MULTITHREAD,$(CPPFLAGS)),\
     @echo compiling multi-threaded static library $(LIBVER),\
     @echo compiling single-threaded static library $(LIBVER))
 	$(AR) $(ARFLAGS) $@ $^
 
-libzstd.a: $(ZSTD_STATLIB)
+libzstd.a: $(ZSTD_STATICLIB)
 	cp -f $< $@
 
 endif
@@ -182,14 +188,17 @@ lib : libzstd.a libzstd
 # make does not consider implicit pattern rule for .PHONY target
 
 %-mt : CPPFLAGS_DYNLIB  := -DZSTD_MULTITHREAD
-%-mt : CPPFLAGS_STATLIB := -DZSTD_MULTITHREAD
+%-mt : CPPFLAGS_STATICLIB := -DZSTD_MULTITHREAD
 %-mt : LDFLAGS_DYNLIB   := -pthread
+%-mt : PCLIB :=
+%-mt : PCMTLIB := $(LDFLAGS_DYNLIB)
 %-mt : %
 	@echo multi-threaded build completed
 
 %-nomt : CPPFLAGS_DYNLIB  :=
 %-nomt : LDFLAGS_DYNLIB   :=
-%-nomt : CPPFLAGS_STATLIB :=
+%-nomt : CPPFLAGS_STATICLIB :=
+%-nomt : PCLIB :=
 %-nomt : %
 	@echo single-threaded build completed
 
@@ -200,42 +209,52 @@ lib : libzstd.a libzstd
 
 # Generate .h dependencies automatically
 
-DEPFLAGS = -MT $@ -MMD -MP -MF
+# -MMD: compiler generates dependency information as a side-effect of compilation, without system headers
+# -MP: adds phony target for each dependency other than main file.
+DEPFLAGS = -MMD -MP
 
-$(ZSTD_DYNLIB_DIR)/%.o : %.c $(ZSTD_DYNLIB_DIR)/%.d | $(ZSTD_DYNLIB_DIR)
+# ensure that ZSTD_DYNLIB_DIR exists prior to generating %.o
+$(ZSTD_DYNLIB_DIR)/%.o : %.c | $(ZSTD_DYNLIB_DIR)
 	@echo CC $@
-	$(COMPILE.c) $(DEPFLAGS) $(ZSTD_DYNLIB_DIR)/$*.d $(OUTPUT_OPTION) $<
+	$(COMPILE.c) $(DEPFLAGS) $(OUTPUT_OPTION) $<
 
-$(ZSTD_STATLIB_DIR)/%.o : %.c $(ZSTD_STATLIB_DIR)/%.d | $(ZSTD_STATLIB_DIR)
+$(ZSTD_STATICLIB_DIR)/%.o : %.c | $(ZSTD_STATICLIB_DIR)
 	@echo CC $@
-	$(COMPILE.c) $(DEPFLAGS) $(ZSTD_STATLIB_DIR)/$*.d $(OUTPUT_OPTION) $<
+	$(COMPILE.c) $(DEPFLAGS) $(OUTPUT_OPTION) $<
 
 $(ZSTD_DYNLIB_DIR)/%.o : %.S | $(ZSTD_DYNLIB_DIR)
 	@echo AS $@
 	$(COMPILE.S) $(OUTPUT_OPTION) $<
 
-$(ZSTD_STATLIB_DIR)/%.o : %.S | $(ZSTD_STATLIB_DIR)
+$(ZSTD_STATICLIB_DIR)/%.o : %.S | $(ZSTD_STATICLIB_DIR)
 	@echo AS $@
 	$(COMPILE.S) $(OUTPUT_OPTION) $<
 
-MKDIR ?= mkdir
-$(BUILD_DIR) $(ZSTD_DYNLIB_DIR) $(ZSTD_STATLIB_DIR):
-	$(MKDIR) -p $@
+MKDIR ?= mkdir -p
+$(BUILD_DIR) $(ZSTD_DYNLIB_DIR) $(ZSTD_STATICLIB_DIR):
+	$(MKDIR) $@
 
-DEPFILES := $(ZSTD_DYNLIB_OBJ:.o=.d) $(ZSTD_STATLIB_OBJ:.o=.d)
+DEPFILES := $(ZSTD_DYNLIB_OBJ:.o=.d) $(ZSTD_STATICLIB_OBJ:.o=.d)
 $(DEPFILES):
 
-include $(wildcard $(DEPFILES))
+# The leading '-' means: do not fail is include fails (ex: directory does not exist yet)
+-include $(wildcard $(DEPFILES))
 
 
-# Special case : building library in single-thread mode _and_ without zstdmt_compress.c
-ZSTDMT_FILES = compress/zstdmt_compress.c
-ZSTD_NOMT_FILES = $(filter-out $(ZSTDMT_FILES),$(ZSTD_FILES))
+# Special case : build library in single-thread mode _and_ without zstdmt_compress.c
+# Note : we still need threading.c and pool.c for the dictionary builder,
+# but they will correctly behave single-threaded.
+ZSTDMT_FILES = zstdmt_compress.c
+ZSTD_NOMT_FILES = $(filter-out $(ZSTDMT_FILES),$(notdir $(ZSTD_FILES)))
 libzstd-nomt: CFLAGS += -fPIC -fvisibility=hidden
 libzstd-nomt: LDFLAGS += -shared
 libzstd-nomt: $(ZSTD_NOMT_FILES)
 	@echo compiling single-thread dynamic library $(LIBVER)
 	@echo files : $(ZSTD_NOMT_FILES)
+	@if echo "$(ZSTD_NOMT_FILES)" | tr ' ' '\n' | $(GREP) -q zstdmt; then \
+        echo "Error: Found zstdmt in list."; \
+        exit 1; \
+    fi
 	$(CC) $(FLAGS) $^ $(LDFLAGS) $(SONAME_FLAGS) -o $@
 
 .PHONY: clean
@@ -249,7 +268,7 @@ clean:
 #-----------------------------------------------------------------------------
 # make install is validated only for below listed environments
 #-----------------------------------------------------------------------------
-ifneq (,$(filter $(UNAME),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku AIX))
+ifneq (,$(filter Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku AIX MSYS_NT% CYGWIN_NT%,$(UNAME)))
 
 lib: libzstd.pc
 
@@ -280,13 +299,21 @@ PCLIBPREFIX := $(if $(findstring $(LIBDIR),$(PCLIBDIR)),,$${exec_prefix})
 # to PREFIX, rather than as a resolved value.
 PCEXEC_PREFIX := $(if $(HAS_EXPLICIT_EXEC_PREFIX),$(EXEC_PREFIX),$${prefix})
 
-ifneq (,$(filter $(UNAME),FreeBSD NetBSD DragonFly))
+
+ifneq ($(MT),)
+  PCLIB :=
+  PCMTLIB := $(LDFLAGS_DYNLIB)
+else
+  PCLIB := $(LDFLAGS_DYNLIB)
+endif
+
+ifneq (,$(filter FreeBSD NetBSD DragonFly,$(UNAME)))
   PKGCONFIGDIR ?= $(PREFIX)/libdata/pkgconfig
 else
   PKGCONFIGDIR ?= $(LIBDIR)/pkgconfig
 endif
 
-ifneq (,$(filter $(UNAME),SunOS))
+ifneq (,$(filter SunOS,$(UNAME)))
   INSTALL ?= ginstall
 else
   INSTALL ?= install
@@ -296,6 +323,10 @@ INSTALL_PROGRAM ?= $(INSTALL)
 INSTALL_DATA    ?= $(INSTALL) -m 644
 
 
+# pkg-config library define.
+# For static single-threaded library declare -pthread in Libs.private
+# For static multi-threaded library declare -pthread in Libs and Cflags
+.PHONY: libzstd.pc
 libzstd.pc: libzstd.pc.in
 	@echo creating pkgconfig
 	@sed \
@@ -304,7 +335,8 @@ libzstd.pc: libzstd.pc.in
 	        -e 's|@INCLUDEDIR@|$(PCINCPREFIX)$(PCINCDIR)|' \
 	        -e 's|@LIBDIR@|$(PCLIBPREFIX)$(PCLIBDIR)|' \
 	        -e 's|@VERSION@|$(VERSION)|' \
-	        -e 's|@LIBS_PRIVATE@|$(LDFLAGS_DYNLIB)|' \
+	        -e 's|@LIBS_MT@|$(PCMTLIB)|' \
+	        -e 's|@LIBS_PRIVATE@|$(PCLIB)|' \
 	        $< >$@
 
 .PHONY: install

zstd.mod/zstd/lib/README.md

@@ -27,12 +27,16 @@ Enabling multithreading requires 2 conditions :
 
 For convenience, we provide a build target to generate multi and single threaded libraries:
 - Force enable multithreading on both dynamic and static libraries by appending `-mt` to the target, e.g. `make lib-mt`.
+  Note that the `.pc` generated on calling `make lib-mt` will already include the require Libs and Cflags.
 - Force disable multithreading on both dynamic and static libraries by appending `-nomt` to the target, e.g. `make lib-nomt`.
 - By default, as mentioned before, dynamic library is multithreaded, and static library is single-threaded, e.g. `make lib`.
 
 When linking a POSIX program with a multithreaded version of `libzstd`,
 note that it's necessary to invoke the `-pthread` flag during link stage.
 
+The `.pc` generated from `make install` or `make install-pc` always assume a single-threaded static library
+is compiled. To correctly generate a `.pc` for the multi-threaded static library, set `MT=1` as ENV variable.
+
 Multithreading capabilities are exposed
 via the [advanced API defined in `lib/zstd.h`](https://github.com/facebook/zstd/blob/v1.4.3/lib/zstd.h#L351).
 
@@ -88,7 +92,7 @@ The file structure is designed to make this selection manually achievable for an
         For example, advanced API for version `v0.4` is exposed in `lib/legacy/zstd_v04.h` .
 
 - While invoking `make libzstd`, it's possible to define build macros
-        `ZSTD_LIB_COMPRESSION, ZSTD_LIB_DECOMPRESSION`, `ZSTD_LIB_DICTBUILDER`,
+        `ZSTD_LIB_COMPRESSION`, `ZSTD_LIB_DECOMPRESSION`, `ZSTD_LIB_DICTBUILDER`,
         and `ZSTD_LIB_DEPRECATED` as `0` to forgo compilation of the
         corresponding features. This will also disable compilation of all
         dependencies (e.g. `ZSTD_LIB_COMPRESSION=0` will also disable
@@ -119,6 +123,15 @@ The file structure is designed to make this selection manually achievable for an
   binary is achieved by using `HUF_FORCE_DECOMPRESS_X1` and
   `ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT` (implied by `ZSTD_LIB_MINIFY`).
 
+  On the compressor side, Zstd's compression levels map to several internal
+  strategies. In environments where the higher compression levels aren't used,
+  it is possible to exclude all but the fastest strategy with
+  `ZSTD_LIB_EXCLUDE_COMPRESSORS_DFAST_AND_UP=1`. (Note that this will change
+  the behavior of the default compression level.) Or if you want to retain the
+  default compressor as well, you can set
+  `ZSTD_LIB_EXCLUDE_COMPRESSORS_GREEDY_AND_UP=1`, at the cost of an additional
+  ~20KB or so.
+
   For squeezing the last ounce of size out, you can also define
   `ZSTD_NO_INLINE`, which disables inlining, and `ZSTD_STRIP_ERROR_STRINGS`,
   which removes the error messages that are otherwise returned by
@@ -136,6 +149,13 @@ The file structure is designed to make this selection manually achievable for an
   will expose the deprecated `ZSTDMT` API exposed by `zstdmt_compress.h` in
   the shared library, which is now hidden by default.
 
+- The build macro `STATIC_BMI2` can be set to 1 to force usage of `bmi2` instructions.
+  It is generally not necessary to set this build macro,
+  because `STATIC_BMI2` will be automatically set to 1
+  on detecting the presence of the corresponding instruction set in the compilation target.
+  It's nonetheless available as an optional manual toggle for better control,
+  and can also be used to forcefully disable `bmi2` instructions by setting it to 0.
+
 - The build macro `DYNAMIC_BMI2` can be set to 1 or 0 in order to generate binaries
   which can detect at runtime the presence of BMI2 instructions, and use them only if present.
   These instructions contribute to better performance, notably on the decoder side.
@@ -169,6 +189,10 @@ The file structure is designed to make this selection manually achievable for an
   `ZSTDERRORLIB_VSIBILITY`, and `ZDICTLIB_VISIBILITY` if unset, for backwards compatibility
   with the old macro names.
 
+- The C compiler macro `HUF_DISABLE_FAST_DECODE` disables the newer Huffman fast C
+  and assembly decoding loops. You may want to use this macro if these loops are
+  slower on your platform.
+
 #### Windows : using MinGW+MSYS to create DLL
 
 DLL can be created using MinGW+MSYS with the `make libzstd` command.

zstd.mod/zstd/lib/common/allocations.h

@@ -14,7 +14,7 @@
 #define ZSTD_DEPS_NEED_MALLOC
 #include "zstd_deps.h"   /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */
 
-#include "mem.h" /* MEM_STATIC */
+#include "compiler.h" /* MEM_STATIC */
 #define ZSTD_STATIC_LINKING_ONLY
 #include "../zstd.h" /* ZSTD_customMem */
 

zstd.mod/zstd/lib/common/bits.h

@@ -28,27 +28,29 @@ MEM_STATIC unsigned ZSTD_countTrailingZeros32_fallback(U32 val)
 MEM_STATIC unsigned ZSTD_countTrailingZeros32(U32 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_tzcnt_u32(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanForward(&r, val);
-                return (unsigned)r;
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)__builtin_ctz(val);
-#   else
-        return ZSTD_countTrailingZeros32_fallback(val);
-#   endif
+#if defined(_MSC_VER)
+#  if STATIC_BMI2
+    return (unsigned)_tzcnt_u32(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanForward(&r, val);
+        return (unsigned)r;
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)__builtin_ctz(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_ctz(val);
+#else
+    return ZSTD_countTrailingZeros32_fallback(val);
+#endif
 }
 
-MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val) {
+MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val)
+{
     assert(val != 0);
     {
         static const U32 DeBruijnClz[32] = {0, 9, 1, 10, 13, 21, 2, 29,
@@ -67,86 +69,89 @@ MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val) {
 MEM_STATIC unsigned ZSTD_countLeadingZeros32(U32 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_lzcnt_u32(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanReverse(&r, val);
-                return (unsigned)(31 - r);
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)__builtin_clz(val);
-#   else
-        return ZSTD_countLeadingZeros32_fallback(val);
-#   endif
+#if defined(_MSC_VER)
+#  if STATIC_BMI2
+    return (unsigned)_lzcnt_u32(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanReverse(&r, val);
+        return (unsigned)(31 - r);
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)__builtin_clz(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_clz(val);
+#else
+    return ZSTD_countLeadingZeros32_fallback(val);
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_countTrailingZeros64(U64 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER) && defined(_WIN64)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_tzcnt_u64(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanForward64(&r, val);
-                return (unsigned)r;
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4) && defined(__LP64__)
-        return (unsigned)__builtin_ctzll(val);
-#   else
-        {
-            U32 mostSignificantWord = (U32)(val >> 32);
-            U32 leastSignificantWord = (U32)val;
-            if (leastSignificantWord == 0) {
-                return 32 + ZSTD_countTrailingZeros32(mostSignificantWord);
-            } else {
-                return ZSTD_countTrailingZeros32(leastSignificantWord);
-            }
+#if defined(_MSC_VER) && defined(_WIN64)
+#  if STATIC_BMI2
+    return (unsigned)_tzcnt_u64(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanForward64(&r, val);
+        return (unsigned)r;
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4) && defined(__LP64__)
+    return (unsigned)__builtin_ctzll(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_ctzll(val);
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (leastSignificantWord == 0) {
+            return 32 + ZSTD_countTrailingZeros32(mostSignificantWord);
+        } else {
+            return ZSTD_countTrailingZeros32(leastSignificantWord);
         }
-#   endif
+    }
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_countLeadingZeros64(U64 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER) && defined(_WIN64)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_lzcnt_u64(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanReverse64(&r, val);
-                return (unsigned)(63 - r);
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)(__builtin_clzll(val));
-#   else
-        {
-            U32 mostSignificantWord = (U32)(val >> 32);
-            U32 leastSignificantWord = (U32)val;
-            if (mostSignificantWord == 0) {
-                return 32 + ZSTD_countLeadingZeros32(leastSignificantWord);
-            } else {
-                return ZSTD_countLeadingZeros32(mostSignificantWord);
-            }
+#if defined(_MSC_VER) && defined(_WIN64)
+#  if STATIC_BMI2
+    return (unsigned)_lzcnt_u64(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanReverse64(&r, val);
+        return (unsigned)(63 - r);
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)(__builtin_clzll(val));
+#elif defined(__ICCARM__)
+    return (unsigned)(__builtin_clzll(val));
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (mostSignificantWord == 0) {
+            return 32 + ZSTD_countLeadingZeros32(leastSignificantWord);
+        } else {
+            return ZSTD_countLeadingZeros32(mostSignificantWord);
         }
-#   endif
+    }
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_NbCommonBytes(size_t val)

zstd.mod/zstd/lib/common/bitstream.h

@@ -14,9 +14,6 @@
 #ifndef BITSTREAM_H_MODULE
 #define BITSTREAM_H_MODULE
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
 /*
 *  This API consists of small unitary functions, which must be inlined for best performance.
 *  Since link-time-optimization is not available for all compilers,
@@ -32,7 +29,6 @@ extern "C" {
 #include "error_private.h"  /* error codes and messages */
 #include "bits.h"           /* ZSTD_highbit32 */
 
-
 /*=========================================
 *  Target specific
 =========================================*/
@@ -52,12 +48,13 @@ extern "C" {
 /*-******************************************
 *  bitStream encoding API (write forward)
 ********************************************/
+typedef size_t BitContainerType;
 /* bitStream can mix input from multiple sources.
  * A critical property of these streams is that they encode and decode in **reverse** direction.
  * So the first bit sequence you add will be the last to be read, like a LIFO stack.
  */
 typedef struct {
-    size_t bitContainer;
+    BitContainerType bitContainer;
     unsigned bitPos;
     char*  startPtr;
     char*  ptr;
@@ -65,7 +62,7 @@ typedef struct {
 } BIT_CStream_t;
 
 MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
-MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 MEM_STATIC void   BIT_flushBits(BIT_CStream_t* bitC);
 MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 
@@ -74,7 +71,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 *  `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
 *
 *  bits are first added to a local register.
-*  Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
+*  Local register is BitContainerType, 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
 *  Writing data into memory is an explicit operation, performed by the flushBits function.
 *  Hence keep track how many bits are potentially stored into local register to avoid register overflow.
 *  After a flushBits, a maximum of 7 bits might still be stored into local register.
@@ -91,28 +88,28 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 *  bitStream decoding API (read backward)
 **********************************************/
 typedef struct {
-    size_t   bitContainer;
+    BitContainerType bitContainer;
     unsigned bitsConsumed;
     const char* ptr;
     const char* start;
     const char* limitPtr;
 } BIT_DStream_t;
 
-typedef enum { BIT_DStream_unfinished = 0,
-               BIT_DStream_endOfBuffer = 1,
-               BIT_DStream_completed = 2,
-               BIT_DStream_overflow = 3 } BIT_DStream_status;  /* result of BIT_reloadDStream() */
-               /* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
+typedef enum { BIT_DStream_unfinished = 0,  /* fully refilled */
+               BIT_DStream_endOfBuffer = 1, /* still some bits left in bitstream */
+               BIT_DStream_completed = 2,   /* bitstream entirely consumed, bit-exact */
+               BIT_DStream_overflow = 3     /* user requested more bits than present in bitstream */
+    } BIT_DStream_status;  /* result of BIT_reloadDStream() */
 
 MEM_STATIC size_t   BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
-MEM_STATIC size_t   BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
+MEM_STATIC BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
 MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
 MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 
 
 /* Start by invoking BIT_initDStream().
 *  A chunk of the bitStream is then stored into a local register.
-*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (BitContainerType).
 *  You can then retrieve bitFields stored into the local register, **in reverse order**.
 *  Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
 *  A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
@@ -124,7 +121,7 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 /*-****************************************
 *  unsafe API
 ******************************************/
-MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 /* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
 
 MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
@@ -162,10 +159,15 @@ MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
     return 0;
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getLowerBits(BitContainerType bitContainer, U32 const nbBits)
 {
-#if defined(STATIC_BMI2) && STATIC_BMI2 == 1 && !defined(ZSTD_NO_INTRINSICS)
-    return  _bzhi_u64(bitContainer, nbBits);
+#if STATIC_BMI2 && !defined(ZSTD_NO_INTRINSICS)
+#  if (defined(__x86_64__) || defined(_M_X64)) && !defined(__ILP32__)
+    return _bzhi_u64(bitContainer, nbBits);
+#  else
+    DEBUG_STATIC_ASSERT(sizeof(bitContainer) == sizeof(U32));
+    return _bzhi_u32(bitContainer, nbBits);
+#  endif
 #else
     assert(nbBits < BIT_MASK_SIZE);
     return bitContainer & BIT_mask[nbBits];
@@ -176,7 +178,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 co
  *  can add up to 31 bits into `bitC`.
  *  Note : does not check for register overflow ! */
 MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
-                            size_t value, unsigned nbBits)
+                            BitContainerType value, unsigned nbBits)
 {
     DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32);
     assert(nbBits < BIT_MASK_SIZE);
@@ -189,7 +191,7 @@ MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
  *  works only if `value` is _clean_,
  *  meaning all high bits above nbBits are 0 */
 MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
-                                size_t value, unsigned nbBits)
+                                BitContainerType value, unsigned nbBits)
 {
     assert((value>>nbBits) == 0);
     assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
@@ -236,7 +238,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
     BIT_addBitsFast(bitC, 1, 1);   /* endMark */
     BIT_flushBits(bitC);
     if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
-    return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
+    return (size_t)(bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
 }
 
 
@@ -267,22 +269,22 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
         bitD->bitContainer = *(const BYTE*)(bitD->start);
         switch(srcSize)
         {
-        case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
+        case 7: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
                 ZSTD_FALLTHROUGH;
 
-        case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
+        case 6: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
                 ZSTD_FALLTHROUGH;
 
-        case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
+        case 5: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
                 ZSTD_FALLTHROUGH;
 
-        case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
+        case 4: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[3]) << 24;
                 ZSTD_FALLTHROUGH;
 
-        case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
+        case 3: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[2]) << 16;
                 ZSTD_FALLTHROUGH;
 
-        case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) <<  8;
+        case 2: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[1]) <<  8;
                 ZSTD_FALLTHROUGH;
 
         default: break;
@@ -297,12 +299,12 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
     return srcSize;
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getUpperBits(size_t bitContainer, U32 const start)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getUpperBits(BitContainerType bitContainer, U32 const start)
 {
     return bitContainer >> start;
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getMiddleBits(BitContainerType bitContainer, U32 const start, U32 const nbBits)
 {
     U32 const regMask = sizeof(bitContainer)*8 - 1;
     /* if start > regMask, bitstream is corrupted, and result is undefined */
@@ -312,7 +314,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 c
      * such cpus old (pre-Haswell, 2013) and their performance is not of that
      * importance.
      */
-#if defined(__x86_64__) || defined(_M_X86)
+#if defined(__x86_64__) || defined(_M_X64)
     return (bitContainer >> (start & regMask)) & ((((U64)1) << nbBits) - 1);
 #else
     return (bitContainer >> (start & regMask)) & BIT_mask[nbBits];
@@ -325,7 +327,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 c
  *  On 32-bits, maxNbBits==24.
  *  On 64-bits, maxNbBits==56.
  * @return : value extracted */
-MEM_STATIC  FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
 {
     /* arbitrate between double-shift and shift+mask */
 #if 1
@@ -341,14 +343,14 @@ MEM_STATIC  FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t*  bitD, U3
 
 /*! BIT_lookBitsFast() :
  *  unsafe version; only works if nbBits >= 1 */
-MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
+MEM_STATIC BitContainerType BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
 {
     U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
     assert(nbBits >= 1);
     return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask);
 }
 
-MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
+FORCE_INLINE_TEMPLATE void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
 {
     bitD->bitsConsumed += nbBits;
 }
@@ -357,23 +359,38 @@ MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
  *  Read (consume) next n bits from local register and update.
  *  Pay attention to not read more than nbBits contained into local register.
  * @return : extracted value. */
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBits(bitD, nbBits);
+    BitContainerType const value = BIT_lookBits(bitD, nbBits);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
 
 /*! BIT_readBitsFast() :
  *  unsafe version; only works if nbBits >= 1 */
-MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
+MEM_STATIC BitContainerType BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBitsFast(bitD, nbBits);
+    BitContainerType const value = BIT_lookBitsFast(bitD, nbBits);
     assert(nbBits >= 1);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
 
+/*! BIT_reloadDStream_internal() :
+ *  Simple variant of BIT_reloadDStream(), with two conditions:
+ *  1. bitstream is valid : bitsConsumed <= sizeof(bitD->bitContainer)*8
+ *  2. look window is valid after shifted down : bitD->ptr >= bitD->start
+ */
+MEM_STATIC BIT_DStream_status BIT_reloadDStream_internal(BIT_DStream_t* bitD)
+{
+    assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8);
+    bitD->ptr -= bitD->bitsConsumed >> 3;
+    assert(bitD->ptr >= bitD->start);
+    bitD->bitsConsumed &= 7;
+    bitD->bitContainer = MEM_readLEST(bitD->ptr);
+    return BIT_DStream_unfinished;
+}
+
 /*! BIT_reloadDStreamFast() :
  *  Similar to BIT_reloadDStream(), but with two differences:
  *  1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold!
@@ -384,31 +401,35 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD)
 {
     if (UNLIKELY(bitD->ptr < bitD->limitPtr))
         return BIT_DStream_overflow;
-    assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8);
-    bitD->ptr -= bitD->bitsConsumed >> 3;
-    bitD->bitsConsumed &= 7;
-    bitD->bitContainer = MEM_readLEST(bitD->ptr);
-    return BIT_DStream_unfinished;
+    return BIT_reloadDStream_internal(bitD);
 }
 
 /*! BIT_reloadDStream() :
  *  Refill `bitD` from buffer previously set in BIT_initDStream() .
- *  This function is safe, it guarantees it will not read beyond src buffer.
+ *  This function is safe, it guarantees it will not never beyond src buffer.
  * @return : status of `BIT_DStream_t` internal register.
  *           when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
-MEM_STATIC FORCE_INLINE_ATTR BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
+FORCE_INLINE_TEMPLATE BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
 {
-    if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))  /* overflow detected, like end of stream */
+    /* note : once in overflow mode, a bitstream remains in this mode until it's reset */
+    if (UNLIKELY(bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))) {
+        static const BitContainerType zeroFilled = 0;
+        bitD->ptr = (const char*)&zeroFilled; /* aliasing is allowed for char */
+        /* overflow detected, erroneous scenario or end of stream: no update */
         return BIT_DStream_overflow;
+    }
+
+    assert(bitD->ptr >= bitD->start);
 
     if (bitD->ptr >= bitD->limitPtr) {
-        return BIT_reloadDStreamFast(bitD);
+        return BIT_reloadDStream_internal(bitD);
     }
     if (bitD->ptr == bitD->start) {
+        /* reached end of bitStream => no update */
         if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer;
         return BIT_DStream_completed;
     }
-    /* start < ptr < limitPtr */
+    /* start < ptr < limitPtr => cautious update */
     {   U32 nbBytes = bitD->bitsConsumed >> 3;
         BIT_DStream_status result = BIT_DStream_unfinished;
         if (bitD->ptr - nbBytes < bitD->start) {
@@ -430,8 +451,4 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
     return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
 }
 
-#if defined (__cplusplus)
-}
-#endif
-
 #endif /* BITSTREAM_H_MODULE */

zstd.mod/zstd/lib/common/compiler.h

@@ -11,6 +11,8 @@
 #ifndef ZSTD_COMPILER_H
 #define ZSTD_COMPILER_H
 
+#include <stddef.h>
+
 #include "portability_macros.h"
 
 /*-*******************************************************
@@ -25,7 +27,7 @@
 #  define INLINE_KEYWORD
 #endif
 
-#if defined(__GNUC__) || defined(__ICCARM__)
+#if defined(__GNUC__) || defined(__IAR_SYSTEMS_ICC__)
 #  define FORCE_INLINE_ATTR __attribute__((always_inline))
 #elif defined(_MSC_VER)
 #  define FORCE_INLINE_ATTR __forceinline
@@ -51,12 +53,19 @@
 #  define WIN_CDECL
 #endif
 
+/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */
+#if defined(__GNUC__) || defined(__IAR_SYSTEMS_ICC__)
+#  define UNUSED_ATTR __attribute__((unused))
+#else
+#  define UNUSED_ATTR
+#endif
+
 /**
  * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
  * parameters. They must be inlined for the compiler to eliminate the constant
  * branches.
  */
-#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
+#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR UNUSED_ATTR
 /**
  * HINT_INLINE is used to help the compiler generate better code. It is *not*
  * used for "templates", so it can be tweaked based on the compilers
@@ -71,21 +80,37 @@
 #if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5
 #  define HINT_INLINE static INLINE_KEYWORD
 #else
-#  define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR
+#  define HINT_INLINE FORCE_INLINE_TEMPLATE
 #endif
 
-/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */
+/* "soft" inline :
+ * The compiler is free to select if it's a good idea to inline or not.
+ * The main objective is to silence compiler warnings
+ * when a defined function in included but not used.
+ *
+ * Note : this macro is prefixed `MEM_` because it used to be provided by `mem.h` unit.
+ * Updating the prefix is probably preferable, but requires a fairly large codemod,
+ * since this name is used everywhere.
+ */
+#ifndef MEM_STATIC  /* already defined in Linux Kernel mem.h */
 #if defined(__GNUC__)
-#  define UNUSED_ATTR __attribute__((unused))
+#  define MEM_STATIC static __inline UNUSED_ATTR
+#elif defined(__IAR_SYSTEMS_ICC__)
+#  define MEM_STATIC static inline UNUSED_ATTR
+#elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
+#  define MEM_STATIC static inline
+#elif defined(_MSC_VER)
+#  define MEM_STATIC static __inline
 #else
-#  define UNUSED_ATTR
+#  define MEM_STATIC static  /* this version may generate warnings for unused static functions; disable the relevant warning */
+#endif
 #endif
 
 /* force no inlining */
 #ifdef _MSC_VER
 #  define FORCE_NOINLINE static __declspec(noinline)
 #else
-#  if defined(__GNUC__) || defined(__ICCARM__)
+#  if defined(__GNUC__) || defined(__IAR_SYSTEMS_ICC__)
 #    define FORCE_NOINLINE static __attribute__((__noinline__))
 #  else
 #    define FORCE_NOINLINE static
@@ -94,7 +119,7 @@
 
 
 /* target attribute */
-#if defined(__GNUC__) || defined(__ICCARM__)
+#if defined(__GNUC__) || defined(__IAR_SYSTEMS_ICC__)
 #  define TARGET_ATTRIBUTE(target) __attribute__((__target__(target)))
 #else
 #  define TARGET_ATTRIBUTE(target)
@@ -109,10 +134,10 @@
 /* prefetch
  * can be disabled, by declaring NO_PREFETCH build macro */
 #if defined(NO_PREFETCH)
-#  define PREFETCH_L1(ptr)  (void)(ptr)  /* disabled */
-#  define PREFETCH_L2(ptr)  (void)(ptr)  /* disabled */
+#  define PREFETCH_L1(ptr)  do { (void)(ptr); } while (0)  /* disabled */
+#  define PREFETCH_L2(ptr)  do { (void)(ptr); } while (0)  /* disabled */
 #else
-#  if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86))  /* _mm_prefetch() is not defined outside of x86/x64 */
+#  if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86)) && !defined(_M_ARM64EC)  /* _mm_prefetch() is not defined outside of x86/x64 */
 #    include <mmintrin.h>   /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
 #    define PREFETCH_L1(ptr)  _mm_prefetch((const char*)(ptr), _MM_HINT_T0)
 #    define PREFETCH_L2(ptr)  _mm_prefetch((const char*)(ptr), _MM_HINT_T1)
@@ -120,24 +145,25 @@
 #    define PREFETCH_L1(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */)
 #    define PREFETCH_L2(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
 #  elif defined(__aarch64__)
-#    define PREFETCH_L1(ptr)  __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr)))
-#    define PREFETCH_L2(ptr)  __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr)))
+#    define PREFETCH_L1(ptr)  do { __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr))); } while (0)
+#    define PREFETCH_L2(ptr)  do { __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr))); } while (0)
 #  else
-#    define PREFETCH_L1(ptr) (void)(ptr)  /* disabled */
-#    define PREFETCH_L2(ptr) (void)(ptr)  /* disabled */
+#    define PREFETCH_L1(ptr) do { (void)(ptr); } while (0)  /* disabled */
+#    define PREFETCH_L2(ptr) do { (void)(ptr); } while (0)  /* disabled */
 #  endif
 #endif  /* NO_PREFETCH */
 
 #define CACHELINE_SIZE 64
 
-#define PREFETCH_AREA(p, s)  {            \
-    const char* const _ptr = (const char*)(p);  \
-    size_t const _size = (size_t)(s);     \
-    size_t _pos;                          \
-    for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) {  \
-        PREFETCH_L2(_ptr + _pos);         \
-    }                                     \
-}
+#define PREFETCH_AREA(p, s)                              \
+    do {                                                 \
+        const char* const _ptr = (const char*)(p);       \
+        size_t const _size = (size_t)(s);                \
+        size_t _pos;                                     \
+        for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) { \
+            PREFETCH_L2(_ptr + _pos);                    \
+        }                                                \
+    } while (0)
 
 /* vectorization
  * older GCC (pre gcc-4.3 picked as the cutoff) uses a different syntax,
@@ -166,9 +192,9 @@
 #endif
 
 #if __has_builtin(__builtin_unreachable) || (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5)))
-#  define ZSTD_UNREACHABLE { assert(0), __builtin_unreachable(); }
+#  define ZSTD_UNREACHABLE do { assert(0), __builtin_unreachable(); } while (0)
 #else
-#  define ZSTD_UNREACHABLE { assert(0); }
+#  define ZSTD_UNREACHABLE do { assert(0); } while (0)
 #endif
 
 /* disable warnings */
@@ -181,30 +207,21 @@
 #  pragma warning(disable : 4324)        /* disable: C4324: padded structure */
 #endif
 
-/*Like DYNAMIC_BMI2 but for compile time determination of BMI2 support*/
-#ifndef STATIC_BMI2
-#  if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86))
-#    ifdef __AVX2__  //MSVC does not have a BMI2 specific flag, but every CPU that supports AVX2 also supports BMI2
-#       define STATIC_BMI2 1
-#    endif
-#  elif defined(__BMI2__) && defined(__x86_64__) && defined(__GNUC__)
-#    define STATIC_BMI2 1
-#  endif
-#endif
-
-#ifndef STATIC_BMI2
-    #define STATIC_BMI2 0
-#endif
-
 /* compile time determination of SIMD support */
 #if !defined(ZSTD_NO_INTRINSICS)
-#  if defined(__SSE2__) || defined(_M_AMD64) || (defined (_M_IX86) && defined(_M_IX86_FP) && (_M_IX86_FP >= 2))
+#  if defined(__AVX2__)
+#    define ZSTD_ARCH_X86_AVX2
+#  endif
+#  if defined(__SSE2__) || defined(_M_X64) || (defined (_M_IX86) && defined(_M_IX86_FP) && (_M_IX86_FP >= 2))
 #    define ZSTD_ARCH_X86_SSE2
 #  endif
 #  if defined(__ARM_NEON) || defined(_M_ARM64)
 #    define ZSTD_ARCH_ARM_NEON
 #  endif
 #
+#  if defined(ZSTD_ARCH_X86_AVX2)
+#    include <immintrin.h>
+#  endif
 #  if defined(ZSTD_ARCH_X86_SSE2)
 #    include <emmintrin.h>
 #  elif defined(ZSTD_ARCH_ARM_NEON)
@@ -249,9 +266,15 @@
 #endif
 
 /*-**************************************************************
-*  Alignment check
+*  Alignment
 *****************************************************************/
 
+/* @return 1 if @u is a 2^n value, 0 otherwise
+ * useful to check a value is valid for alignment restrictions */
+MEM_STATIC int ZSTD_isPower2(size_t u) {
+    return (u & (u-1)) == 0;
+}
+
 /* this test was initially positioned in mem.h,
  * but this file is removed (or replaced) for linux kernel
  * so it's now hosted in compiler.h,
@@ -277,10 +300,93 @@
 # endif
 #endif /* ZSTD_ALIGNOF */
 
+#ifndef ZSTD_ALIGNED
+/* C90-compatible alignment macro (GCC/Clang). Adjust for other compilers if needed. */
+# if defined(__GNUC__) || defined(__clang__)
+#  define ZSTD_ALIGNED(a) __attribute__((aligned(a)))
+# elif defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L) /* C11 */
+#  define ZSTD_ALIGNED(a) _Alignas(a)
+#elif defined(_MSC_VER)
+#  define ZSTD_ALIGNED(n) __declspec(align(n))
+# else
+   /* this compiler will require its own alignment instruction */
+#  define ZSTD_ALIGNED(...)
+# endif
+#endif /* ZSTD_ALIGNED */
+
+
 /*-**************************************************************
 *  Sanitizer
 *****************************************************************/
 
+/**
+ * Zstd relies on pointer overflow in its decompressor.
+ * We add this attribute to functions that rely on pointer overflow.
+ */
+#ifndef ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+#  if __has_attribute(no_sanitize)
+#    if !defined(__clang__) && defined(__GNUC__) && __GNUC__ < 8
+       /* gcc < 8 only has signed-integer-overlow which triggers on pointer overflow */
+#      define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("signed-integer-overflow")))
+#    else
+       /* older versions of clang [3.7, 5.0) will warn that pointer-overflow is ignored. */
+#      define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("pointer-overflow")))
+#    endif
+#  else
+#    define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+#  endif
+#endif
+
+/**
+ * Helper function to perform a wrapped pointer difference without triggering
+ * UBSAN.
+ *
+ * @returns lhs - rhs with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+ptrdiff_t ZSTD_wrappedPtrDiff(unsigned char const* lhs, unsigned char const* rhs)
+{
+    return lhs - rhs;
+}
+
+/**
+ * Helper function to perform a wrapped pointer add without triggering UBSAN.
+ *
+ * @return ptr + add with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+unsigned char const* ZSTD_wrappedPtrAdd(unsigned char const* ptr, ptrdiff_t add)
+{
+    return ptr + add;
+}
+
+/**
+ * Helper function to perform a wrapped pointer subtraction without triggering
+ * UBSAN.
+ *
+ * @return ptr - sub with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+unsigned char const* ZSTD_wrappedPtrSub(unsigned char const* ptr, ptrdiff_t sub)
+{
+    return ptr - sub;
+}
+
+/**
+ * Helper function to add to a pointer that works around C's undefined behavior
+ * of adding 0 to NULL.
+ *
+ * @returns `ptr + add` except it defines `NULL + 0 == NULL`.
+ */
+MEM_STATIC
+unsigned char* ZSTD_maybeNullPtrAdd(unsigned char* ptr, ptrdiff_t add)
+{
+    return add > 0 ? ptr + add : ptr;
+}
+
 /* Issue #3240 reports an ASAN failure on an llvm-mingw build. Out of an
  * abundance of caution, disable our custom poisoning on mingw. */
 #ifdef __MINGW32__

zstd.mod/zstd/lib/common/cpu.h

@@ -35,6 +35,7 @@ MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) {
     U32 f7b = 0;
     U32 f7c = 0;
 #if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_IX86))
+#if !defined(_M_X64) || !defined(__clang__) || __clang_major__ >= 16
     int reg[4];
     __cpuid((int*)reg, 0);
     {
@@ -50,6 +51,41 @@ MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) {
             f7c = (U32)reg[2];
         }
     }
+#else
+    /* Clang compiler has a bug (fixed in https://reviews.llvm.org/D101338) in
+     * which the `__cpuid` intrinsic does not save and restore `rbx` as it needs
+     * to due to being a reserved register. So in that case, do the `cpuid`
+     * ourselves. Clang supports inline assembly anyway.
+     */
+    U32 n;
+    __asm__(
+        "pushq %%rbx\n\t"
+        "cpuid\n\t"
+        "popq %%rbx\n\t"
+        : "=a"(n)
+        : "a"(0)
+        : "rcx", "rdx");
+    if (n >= 1) {
+      U32 f1a;
+      __asm__(
+          "pushq %%rbx\n\t"
+          "cpuid\n\t"
+          "popq %%rbx\n\t"
+          : "=a"(f1a), "=c"(f1c), "=d"(f1d)
+          : "a"(1)
+          :);
+    }
+    if (n >= 7) {
+      __asm__(
+          "pushq %%rbx\n\t"
+          "cpuid\n\t"
+          "movq %%rbx, %%rax\n\t"
+          "popq %%rbx"
+          : "=a"(f7b), "=c"(f7c)
+          : "a"(7), "c"(0)
+          : "rdx");
+    }
+#endif
 #elif defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__)
     /* The following block like the normal cpuid branch below, but gcc
      * reserves ebx for use of its pic register so we must specially

zstd.mod/zstd/lib/common/debug.c

@@ -21,4 +21,10 @@
 
 #include "debug.h"
 
+#if !defined(ZSTD_LINUX_KERNEL) || (DEBUGLEVEL>=2)
+/* We only use this when DEBUGLEVEL>=2, but we get -Werror=pedantic errors if a
+ * translation unit is empty. So remove this from Linux kernel builds, but
+ * otherwise just leave it in.
+ */
 int g_debuglevel = DEBUGLEVEL;
+#endif

zstd.mod/zstd/lib/common/debug.h

@@ -32,10 +32,6 @@
 #ifndef DEBUG_H_12987983217
 #define DEBUG_H_12987983217
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 
 /* static assert is triggered at compile time, leaving no runtime artefact.
  * static assert only works with compile-time constants.
@@ -85,23 +81,27 @@ extern int g_debuglevel; /* the variable is only declared,
                             It's useful when enabling very verbose levels
                             on selective conditions (such as position in src) */
 
-#  define RAWLOG(l, ...) {                                       \
-                if (l<=g_debuglevel) {                           \
-                    ZSTD_DEBUG_PRINT(__VA_ARGS__);               \
-            }   }
-#  define DEBUGLOG(l, ...) {                                     \
-                if (l<=g_debuglevel) {                           \
-                    ZSTD_DEBUG_PRINT(__FILE__ ": " __VA_ARGS__); \
-                    ZSTD_DEBUG_PRINT(" \n");                     \
-            }   }
+#  define RAWLOG(l, ...)                   \
+    do {                                   \
+        if (l<=g_debuglevel) {             \
+            ZSTD_DEBUG_PRINT(__VA_ARGS__); \
+        }                                  \
+    } while (0)
+
+#define STRINGIFY(x) #x
+#define TOSTRING(x) STRINGIFY(x)
+#define LINE_AS_STRING TOSTRING(__LINE__)
+
+#  define DEBUGLOG(l, ...)                               \
+    do {                                                 \
+        if (l<=g_debuglevel) {                           \
+            ZSTD_DEBUG_PRINT(__FILE__ ":" LINE_AS_STRING ": " __VA_ARGS__); \
+            ZSTD_DEBUG_PRINT(" \n");                     \
+        }                                                \
+    } while (0)
 #else
-#  define RAWLOG(l, ...)      {}    /* disabled */
-#  define DEBUGLOG(l, ...)    {}    /* disabled */
-#endif
-
-
-#if defined (__cplusplus)
-}
+#  define RAWLOG(l, ...)   do { } while (0)    /* disabled */
+#  define DEBUGLOG(l, ...) do { } while (0)    /* disabled */
 #endif
 
 #endif /* DEBUG_H_12987983217 */

zstd.mod/zstd/lib/common/error_private.c

@@ -40,6 +40,7 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported";
     case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large";
     case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small";
+    case PREFIX(cannotProduce_uncompressedBlock): return "This mode cannot generate an uncompressed block";
     case PREFIX(stabilityCondition_notRespected): return "pledged buffer stability condition is not respected";
     case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
     case PREFIX(dictionary_wrong): return "Dictionary mismatch";

zstd.mod/zstd/lib/common/error_private.h

@@ -13,11 +13,6 @@
 #ifndef ERROR_H_MODULE
 #define ERROR_H_MODULE
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
-
 /* ****************************************
 *  Dependencies
 ******************************************/
@@ -26,7 +21,6 @@ extern "C" {
 #include "debug.h"
 #include "zstd_deps.h"       /* size_t */
 
-
 /* ****************************************
 *  Compiler-specific
 ******************************************/
@@ -60,8 +54,13 @@ ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
 ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) { if (!ERR_isError(code)) return (ERR_enum)0; return (ERR_enum) (0-code); }
 
 /* check and forward error code */
-#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e
-#define CHECK_F(f)   { CHECK_V_F(_var_err__, f); }
+#define CHECK_V_F(e, f)     \
+    size_t const e = f;     \
+    do {                    \
+        if (ERR_isError(e)) \
+            return e;       \
+    } while (0)
+#define CHECK_F(f)   do { CHECK_V_F(_var_err__, f); } while (0)
 
 
 /*-****************************************
@@ -95,10 +94,12 @@ void _force_has_format_string(const char *format, ...) {
  * We want to force this function invocation to be syntactically correct, but
  * we don't want to force runtime evaluation of its arguments.
  */
-#define _FORCE_HAS_FORMAT_STRING(...) \
-  if (0) { \
-    _force_has_format_string(__VA_ARGS__); \
-  }
+#define _FORCE_HAS_FORMAT_STRING(...)              \
+    do {                                           \
+        if (0) {                                   \
+            _force_has_format_string(__VA_ARGS__); \
+        }                                          \
+    } while (0)
 
 #define ERR_QUOTE(str) #str
 
@@ -109,51 +110,49 @@ void _force_has_format_string(const char *format, ...) {
  * 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__, ERR_QUOTE(cond), ERR_QUOTE(ERROR(err))); \
-    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-    RAWLOG(3, ": " __VA_ARGS__); \
-    RAWLOG(3, "\n"); \
-    return ERROR(err); \
-  }
+#define RETURN_ERROR_IF(cond, err, ...)                                        \
+    do {                                                                       \
+        if (cond) {                                                            \
+            RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s",          \
+                  __FILE__, __LINE__, ERR_QUOTE(cond), ERR_QUOTE(ERROR(err))); \
+            _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                             \
+            RAWLOG(3, ": " __VA_ARGS__);                                       \
+            RAWLOG(3, "\n");                                                   \
+            return ERROR(err);                                                 \
+        }                                                                      \
+    } while (0)
 
 /**
  * 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__, ERR_QUOTE(ERROR(err))); \
-    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-    RAWLOG(3, ": " __VA_ARGS__); \
-    RAWLOG(3, "\n"); \
-    return ERROR(err); \
-  } while(0);
+#define RETURN_ERROR(err, ...)                                               \
+    do {                                                                     \
+        RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \
+              __FILE__, __LINE__, ERR_QUOTE(ERROR(err)));                    \
+        _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                               \
+        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__, ERR_QUOTE(err), ERR_getErrorName(err_code)); \
-      _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-      RAWLOG(3, ": " __VA_ARGS__); \
-      RAWLOG(3, "\n"); \
-      return err_code; \
-    } \
-  } while(0);
-
-#if defined (__cplusplus)
-}
-#endif
+#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__, ERR_QUOTE(err), ERR_getErrorName(err_code)); \
+            _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                                 \
+            RAWLOG(3, ": " __VA_ARGS__);                                           \
+            RAWLOG(3, "\n");                                                       \
+            return err_code;                                                       \
+        }                                                                          \
+    } while(0)
 
 #endif /* ERROR_H_MODULE */

zstd.mod/zstd/lib/common/fse.h

@@ -11,11 +11,6 @@
  * in the COPYING file in the root directory of this source tree).
  * You may select, at your option, one of the above-listed licenses.
 ****************************************************************** */
-
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 #ifndef FSE_H
 #define FSE_H
 
@@ -25,7 +20,6 @@ extern "C" {
 ******************************************/
 #include "zstd_deps.h"    /* size_t, ptrdiff_t */
 
-
 /*-*****************************************
 *  FSE_PUBLIC_API : control library symbols visibility
 ******************************************/
@@ -229,13 +223,11 @@ If there is an error, the function will return an error code, which can be teste
 
 #endif  /* FSE_H */
 
+
 #if defined(FSE_STATIC_LINKING_ONLY) && !defined(FSE_H_FSE_STATIC_LINKING_ONLY)
 #define FSE_H_FSE_STATIC_LINKING_ONLY
-
-/* *** Dependency *** */
 #include "bitstream.h"
 
-
 /* *****************************************
 *  Static allocation
 *******************************************/
@@ -464,13 +456,13 @@ MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, un
     FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
     const U16* const stateTable = (const U16*)(statePtr->stateTable);
     U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
-    BIT_addBits(bitC, statePtr->value, nbBitsOut);
+    BIT_addBits(bitC, (BitContainerType)statePtr->value, nbBitsOut);
     statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
 }
 
 MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr)
 {
-    BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
+    BIT_addBits(bitC, (BitContainerType)statePtr->value, statePtr->stateLog);
     BIT_flushBits(bitC);
 }
 
@@ -630,10 +622,4 @@ MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
 
 #define FSE_TABLESTEP(tableSize) (((tableSize)>>1) + ((tableSize)>>3) + 3)
 
-
 #endif /* FSE_STATIC_LINKING_ONLY */
-
-
-#if defined (__cplusplus)
-}
-#endif

zstd.mod/zstd/lib/common/fse_decompress.c

@@ -22,8 +22,7 @@
 #define FSE_STATIC_LINKING_ONLY
 #include "fse.h"
 #include "error_private.h"
-#define ZSTD_DEPS_NEED_MALLOC
-#include "zstd_deps.h"
+#include "zstd_deps.h"  /* ZSTD_memcpy */
 #include "bits.h"       /* ZSTD_highbit32 */
 
 
@@ -84,7 +83,7 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
                     symbolNext[s] = 1;
                 } else {
                     if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
-                    symbolNext[s] = normalizedCounter[s];
+                    symbolNext[s] = (U16)normalizedCounter[s];
         }   }   }
         ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
     }
@@ -99,8 +98,7 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
          * all symbols have counts <= 8. We ensure we have 8 bytes at the end of
          * our buffer to handle the over-write.
          */
-        {
-            U64 const add = 0x0101010101010101ull;
+        {   U64 const add = 0x0101010101010101ull;
             size_t pos = 0;
             U64 sv = 0;
             U32 s;
@@ -111,9 +109,8 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
                 for (i = 8; i < n; i += 8) {
                     MEM_write64(spread + pos + i, sv);
                 }
-                pos += n;
-            }
-        }
+                pos += (size_t)n;
+        }   }
         /* Now we spread those positions across the table.
          * The benefit of doing it in two stages is that we avoid the
          * variable size inner loop, which caused lots of branch misses.
@@ -193,6 +190,8 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
     FSE_initDState(&state1, &bitD, dt);
     FSE_initDState(&state2, &bitD, dt);
 
+    RETURN_ERROR_IF(BIT_reloadDStream(&bitD)==BIT_DStream_overflow, corruption_detected, "");
+
 #define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
 
     /* 4 symbols per loop */
@@ -232,12 +231,12 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
             break;
     }   }
 
-    return op-ostart;
+    assert(op >= ostart);
+    return (size_t)(op-ostart);
 }
 
 typedef struct {
     short ncount[FSE_MAX_SYMBOL_VALUE + 1];
-    FSE_DTable dtable[1]; /* Dynamically sized */
 } FSE_DecompressWksp;
 
 
@@ -252,13 +251,18 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
     unsigned tableLog;
     unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
     FSE_DecompressWksp* const wksp = (FSE_DecompressWksp*)workSpace;
+    size_t const dtablePos = sizeof(FSE_DecompressWksp) / sizeof(FSE_DTable);
+    FSE_DTable* const dtable = (FSE_DTable*)workSpace + dtablePos;
 
-    DEBUG_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
+    FSE_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
     if (wkspSize < sizeof(*wksp)) return ERROR(GENERIC);
 
+    /* correct offset to dtable depends on this property */
+    FSE_STATIC_ASSERT(sizeof(FSE_DecompressWksp) % sizeof(FSE_DTable) == 0);
+
     /* normal FSE decoding mode */
-    {
-        size_t const NCountLength = FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2);
+    {   size_t const NCountLength =
+            FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2);
         if (FSE_isError(NCountLength)) return NCountLength;
         if (tableLog > maxLog) return ERROR(tableLog_tooLarge);
         assert(NCountLength <= cSrcSize);
@@ -271,16 +275,16 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
     workSpace = (BYTE*)workSpace + sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
     wkspSize -= sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
 
-    CHECK_F( FSE_buildDTable_internal(wksp->dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
+    CHECK_F( FSE_buildDTable_internal(dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
 
     {
-        const void* ptr = wksp->dtable;
+        const void* ptr = dtable;
         const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
         const U32 fastMode = DTableH->fastMode;
 
         /* select fast mode (static) */
-        if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 1);
-        return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 0);
+        if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, dtable, 1);
+        return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, dtable, 0);
     }
 }
 

zstd.mod/zstd/lib/common/huf.h

@@ -12,10 +12,6 @@
  * You may select, at your option, one of the above-listed licenses.
 ****************************************************************** */
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 #ifndef HUF_H_298734234
 #define HUF_H_298734234
 
@@ -25,7 +21,6 @@ extern "C" {
 #define FSE_STATIC_LINKING_ONLY
 #include "fse.h"
 
-
 /* ***   Tool functions *** */
 #define HUF_BLOCKSIZE_MAX (128 * 1024)   /**< maximum input size for a single block compressed with HUF_compress */
 size_t HUF_compressBound(size_t size);   /**< maximum compressed size (worst case) */
@@ -197,9 +192,22 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void
 
 /** HUF_getNbBitsFromCTable() :
  *  Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX
- *  Note 1 : is not inlined, as HUF_CElt definition is private */
+ *  Note 1 : If symbolValue > HUF_readCTableHeader(symbolTable).maxSymbolValue, returns 0
+ *  Note 2 : is not inlined, as HUF_CElt definition is private
+ */
 U32 HUF_getNbBitsFromCTable(const HUF_CElt* symbolTable, U32 symbolValue);
 
+typedef struct {
+    BYTE tableLog;
+    BYTE maxSymbolValue;
+    BYTE unused[sizeof(size_t) - 2];
+} HUF_CTableHeader;
+
+/** HUF_readCTableHeader() :
+ *  @returns The header from the CTable specifying the tableLog and the maxSymbolValue.
+ */
+HUF_CTableHeader HUF_readCTableHeader(HUF_CElt const* ctable);
+
 /*
  * HUF_decompress() does the following:
  * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics
@@ -267,7 +275,3 @@ size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize
 #endif
 
 #endif   /* HUF_H_298734234 */
-
-#if defined (__cplusplus)
-}
-#endif

zstd.mod/zstd/lib/common/mem.h

@@ -11,10 +11,6 @@
 #ifndef MEM_H_MODULE
 #define MEM_H_MODULE
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 /*-****************************************
 *  Dependencies
 ******************************************/
@@ -30,15 +26,8 @@ extern "C" {
 #if defined(_MSC_VER)   /* Visual Studio */
 #   include <stdlib.h>  /* _byteswap_ulong */
 #   include <intrin.h>  /* _byteswap_* */
-#endif
-#if defined(__GNUC__)
-#  define MEM_STATIC static __inline __attribute__((unused))
-#elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
-#  define MEM_STATIC static inline
-#elif defined(_MSC_VER)
-#  define MEM_STATIC static __inline
-#else
-#  define MEM_STATIC static  /* this version may generate warnings for unused static functions; disable the relevant warning */
+#elif defined(__ICCARM__)
+#   include <intrinsics.h>
 #endif
 
 /*-**************************************************************
@@ -83,7 +72,6 @@ extern "C" {
   typedef   signed long long  S64;
 #endif
 
-
 /*-**************************************************************
 *  Memory I/O API
 *****************************************************************/
@@ -159,10 +147,12 @@ MEM_STATIC unsigned MEM_isLittleEndian(void)
     return 1;
 #elif defined(__clang__) && __BIG_ENDIAN__
     return 0;
-#elif defined(_MSC_VER) && (_M_AMD64 || _M_IX86)
+#elif defined(_MSC_VER) && (_M_X64 || _M_IX86)
     return 1;
 #elif defined(__DMC__) && defined(_M_IX86)
     return 1;
+#elif defined(__IAR_SYSTEMS_ICC__) && __LITTLE_ENDIAN__
+    return 1;
 #else
     const union { U32 u; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental  */
     return one.c[0];
@@ -255,6 +245,8 @@ MEM_STATIC U32 MEM_swap32(U32 in)
 #elif (defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403)) \
   || (defined(__clang__) && __has_builtin(__builtin_bswap32))
     return __builtin_bswap32(in);
+#elif defined(__ICCARM__)
+    return __REV(in);
 #else
     return MEM_swap32_fallback(in);
 #endif
@@ -427,9 +419,4 @@ MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val)
 /* code only tested on 32 and 64 bits systems */
 MEM_STATIC void MEM_check(void) { DEBUG_STATIC_ASSERT((sizeof(size_t)==4) || (sizeof(size_t)==8)); }
 
-
-#if defined (__cplusplus)
-}
-#endif
-
 #endif /* MEM_H_MODULE */

zstd.mod/zstd/lib/common/pool.c

@@ -223,7 +223,7 @@ static int POOL_resize_internal(POOL_ctx* ctx, size_t numThreads)
     {   ZSTD_pthread_t* const threadPool = (ZSTD_pthread_t*)ZSTD_customCalloc(numThreads * sizeof(ZSTD_pthread_t), ctx->customMem);
         if (!threadPool) return 1;
         /* replace existing thread pool */
-        ZSTD_memcpy(threadPool, ctx->threads, ctx->threadCapacity * sizeof(*threadPool));
+        ZSTD_memcpy(threadPool, ctx->threads, ctx->threadCapacity * sizeof(ZSTD_pthread_t));
         ZSTD_customFree(ctx->threads, ctx->customMem);
         ctx->threads = threadPool;
         /* Initialize additional threads */

zstd.mod/zstd/lib/common/pool.h

@@ -11,10 +11,6 @@
 #ifndef POOL_H
 #define POOL_H
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 
 #include "zstd_deps.h"
 #define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_customMem */
@@ -47,7 +43,7 @@ void POOL_joinJobs(POOL_ctx* ctx);
 /*! POOL_resize() :
  *  Expands or shrinks pool's number of threads.
  *  This is more efficient than releasing + creating a new context,
- *  since it tries to preserve and re-use existing threads.
+ *  since it tries to preserve and reuse existing threads.
  * `numThreads` must be at least 1.
  * @return : 0 when resize was successful,
  *           !0 (typically 1) if there is an error.
@@ -82,9 +78,4 @@ void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque);
  */
 int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque);
 
-
-#if defined (__cplusplus)
-}
-#endif
-
 #endif

zstd.mod/zstd/lib/common/portability_macros.h

@@ -68,30 +68,45 @@
 /* Mark the internal assembly functions as hidden  */
 #ifdef __ELF__
 # define ZSTD_HIDE_ASM_FUNCTION(func) .hidden func
+#elif defined(__APPLE__)
+# define ZSTD_HIDE_ASM_FUNCTION(func) .private_extern func
 #else
 # define ZSTD_HIDE_ASM_FUNCTION(func)
 #endif
 
+/* Compile time determination of BMI2 support */
+#ifndef STATIC_BMI2
+#  if defined(__BMI2__)
+#    define STATIC_BMI2 1
+#  elif defined(_MSC_VER) && defined(__AVX2__)
+#    define STATIC_BMI2 1 /* MSVC does not have a BMI2 specific flag, but every CPU that supports AVX2 also supports BMI2 */
+#  endif
+#endif
+
+#ifndef STATIC_BMI2
+#  define STATIC_BMI2 0
+#endif
+
 /* Enable runtime BMI2 dispatch based on the CPU.
  * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
  */
 #ifndef DYNAMIC_BMI2
-  #if ((defined(__clang__) && __has_attribute(__target__)) \
+#  if ((defined(__clang__) && __has_attribute(__target__)) \
       || (defined(__GNUC__) \
           && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
-      && (defined(__x86_64__) || defined(_M_X64)) \
+      && (defined(__i386__) || defined(__x86_64__) || defined(_M_IX86) || defined(_M_X64)) \
       && !defined(__BMI2__)
-  #  define DYNAMIC_BMI2 1
-  #else
-  #  define DYNAMIC_BMI2 0
-  #endif
+#    define DYNAMIC_BMI2 1
+#  else
+#    define DYNAMIC_BMI2 0
+#  endif
 #endif
 
 /**
- * Only enable assembly for GNUC compatible compilers,
+ * Only enable assembly for GNU C compatible compilers,
  * because other platforms may not support GAS assembly syntax.
  *
- * Only enable assembly for Linux / MacOS, other platforms may
+ * Only enable assembly for Linux / MacOS / Win32, other platforms may
  * work, but they haven't been tested. This could likely be
  * extended to BSD systems.
  *
@@ -99,7 +114,7 @@
  * 100% of code to be instrumented to work.
  */
 #if defined(__GNUC__)
-#  if defined(__linux__) || defined(__linux) || defined(__APPLE__)
+#  if defined(__linux__) || defined(__linux) || defined(__APPLE__) || defined(_WIN32)
 #    if ZSTD_MEMORY_SANITIZER
 #      define ZSTD_ASM_SUPPORTED 0
 #    elif ZSTD_DATAFLOW_SANITIZER

zstd.mod/zstd/lib/common/threading.c

@@ -73,10 +73,12 @@ int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused,
     ZSTD_thread_params_t thread_param;
     (void)unused;
 
+    if (thread==NULL) return -1;
+    *thread = NULL;
+
     thread_param.start_routine = start_routine;
     thread_param.arg = arg;
     thread_param.initialized = 0;
-    *thread = NULL;
 
     /* Setup thread initialization synchronization */
     if(ZSTD_pthread_cond_init(&thread_param.initialized_cond, NULL)) {
@@ -91,7 +93,7 @@ int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused,
 
     /* Spawn thread */
     *thread = (HANDLE)_beginthreadex(NULL, 0, worker, &thread_param, 0, NULL);
-    if (!thread) {
+    if (*thread==NULL) {
         ZSTD_pthread_mutex_destroy(&thread_param.initialized_mutex);
         ZSTD_pthread_cond_destroy(&thread_param.initialized_cond);
         return errno;
@@ -137,6 +139,7 @@ int ZSTD_pthread_join(ZSTD_pthread_t thread)
 
 int ZSTD_pthread_mutex_init(ZSTD_pthread_mutex_t* mutex, pthread_mutexattr_t const* attr)
 {
+    assert(mutex != NULL);
     *mutex = (pthread_mutex_t*)ZSTD_malloc(sizeof(pthread_mutex_t));
     if (!*mutex)
         return 1;
@@ -145,6 +148,7 @@ int ZSTD_pthread_mutex_init(ZSTD_pthread_mutex_t* mutex, pthread_mutexattr_t con
 
 int ZSTD_pthread_mutex_destroy(ZSTD_pthread_mutex_t* mutex)
 {
+    assert(mutex != NULL);
     if (!*mutex)
         return 0;
     {
@@ -156,6 +160,7 @@ int ZSTD_pthread_mutex_destroy(ZSTD_pthread_mutex_t* mutex)
 
 int ZSTD_pthread_cond_init(ZSTD_pthread_cond_t* cond, pthread_condattr_t const* attr)
 {
+    assert(cond != NULL);
     *cond = (pthread_cond_t*)ZSTD_malloc(sizeof(pthread_cond_t));
     if (!*cond)
         return 1;
@@ -164,6 +169,7 @@ int ZSTD_pthread_cond_init(ZSTD_pthread_cond_t* cond, pthread_condattr_t const*
 
 int ZSTD_pthread_cond_destroy(ZSTD_pthread_cond_t* cond)
 {
+    assert(cond != NULL);
     if (!*cond)
         return 0;
     {

zstd.mod/zstd/lib/common/threading.h

@@ -16,10 +16,6 @@
 
 #include "debug.h"
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 #if defined(ZSTD_MULTITHREAD) && defined(_WIN32)
 
 /**
@@ -72,7 +68,6 @@ int ZSTD_pthread_join(ZSTD_pthread_t thread);
  * add here more wrappers as required
  */
 
-
 #elif defined(ZSTD_MULTITHREAD)    /* posix assumed ; need a better detection method */
 /* ===   POSIX Systems   === */
 #  include <pthread.h>
@@ -143,8 +138,5 @@ typedef int ZSTD_pthread_cond_t;
 
 #endif /* ZSTD_MULTITHREAD */
 
-#if defined (__cplusplus)
-}
-#endif
 
 #endif /* THREADING_H_938743 */

zstd.mod/zstd/lib/common/xxhash.c

@@ -1,24 +1,18 @@
 /*
- *  xxHash - Fast Hash algorithm
- *  Copyright (c) Meta Platforms, Inc. and affiliates.
- *
- *  You can contact the author at :
- *  - xxHash homepage: https://cyan4973.github.io/xxHash/
- *  - xxHash source repository : https://github.com/Cyan4973/xxHash
+ * xxHash - Extremely Fast Hash algorithm
+ * Copyright (c) Yann Collet - Meta Platforms, Inc
  *
  * 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.
-*/
-
-
+ */
 
 /*
  * xxhash.c instantiates functions defined in xxhash.h
  */
 
-#define XXH_STATIC_LINKING_ONLY   /* access advanced declarations */
-#define XXH_IMPLEMENTATION   /* access definitions */
+#define XXH_STATIC_LINKING_ONLY /* access advanced declarations */
+#define XXH_IMPLEMENTATION      /* access definitions */
 
 #include "xxhash.h"

zstd.mod/zstd/lib/common/zstd_deps.h

@@ -24,6 +24,18 @@
 #ifndef ZSTD_DEPS_COMMON
 #define ZSTD_DEPS_COMMON
 
+/* Even though we use qsort_r only for the dictionary builder, the macro
+ * _GNU_SOURCE has to be declared *before* the inclusion of any standard
+ * header and the script 'combine.sh' combines the whole zstd source code
+ * in a single file.
+ */
+#if defined(__linux) || defined(__linux__) || defined(linux) || defined(__gnu_linux__) || \
+    defined(__CYGWIN__) || defined(__MSYS__)
+#if !defined(_GNU_SOURCE) && !defined(__ANDROID__) /* NDK doesn't ship qsort_r(). */
+#define _GNU_SOURCE
+#endif
+#endif
+
 #include <limits.h>
 #include <stddef.h>
 #include <string.h>

zstd.mod/zstd/lib/common/zstd_internal.h

@@ -39,10 +39,6 @@
 #  define ZSTD_TRACE 0
 #endif
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 /* ---- static assert (debug) --- */
 #define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)
 #define ZSTD_isError ERR_isError   /* for inlining */
@@ -95,7 +91,7 @@ typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
 #define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */)   /* for a non-null block */
 #define MIN_LITERALS_FOR_4_STREAMS 6
 
-typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
+typedef enum { set_basic, set_rle, set_compressed, set_repeat } SymbolEncodingType_e;
 
 #define LONGNBSEQ 0x7F00
 
@@ -178,7 +174,7 @@ static void ZSTD_copy8(void* dst, const void* src) {
     ZSTD_memcpy(dst, src, 8);
 #endif
 }
-#define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
+#define COPY8(d,s) do { ZSTD_copy8(d,s); d+=8; s+=8; } while (0)
 
 /* Need to use memmove here since the literal buffer can now be located within
    the dst buffer. In circumstances where the op "catches up" to where the
@@ -198,7 +194,7 @@ static void ZSTD_copy16(void* dst, const void* src) {
     ZSTD_memcpy(dst, copy16_buf, 16);
 #endif
 }
-#define COPY16(d,s) { ZSTD_copy16(d,s); d+=16; s+=16; }
+#define COPY16(d,s) do { ZSTD_copy16(d,s); d+=16; s+=16; } while (0)
 
 #define WILDCOPY_OVERLENGTH 32
 #define WILDCOPY_VECLEN 16
@@ -227,7 +223,7 @@ void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e
     if (ovtype == ZSTD_overlap_src_before_dst && diff < WILDCOPY_VECLEN) {
         /* Handle short offset copies. */
         do {
-            COPY8(op, ip)
+            COPY8(op, ip);
         } while (op < oend);
     } else {
         assert(diff >= WILDCOPY_VECLEN || diff <= -WILDCOPY_VECLEN);
@@ -278,62 +274,6 @@ typedef enum {
 /*-*******************************************
 *  Private declarations
 *********************************************/
-typedef struct seqDef_s {
-    U32 offBase;   /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */
-    U16 litLength;
-    U16 mlBase;    /* mlBase == matchLength - MINMATCH */
-} seqDef;
-
-/* Controls whether seqStore has a single "long" litLength or matchLength. See seqStore_t. */
-typedef enum {
-    ZSTD_llt_none = 0,             /* no longLengthType */
-    ZSTD_llt_literalLength = 1,    /* represents a long literal */
-    ZSTD_llt_matchLength = 2       /* represents a long match */
-} ZSTD_longLengthType_e;
-
-typedef struct {
-    seqDef* sequencesStart;
-    seqDef* sequences;      /* ptr to end of sequences */
-    BYTE*  litStart;
-    BYTE*  lit;             /* ptr to end of literals */
-    BYTE*  llCode;
-    BYTE*  mlCode;
-    BYTE*  ofCode;
-    size_t maxNbSeq;
-    size_t maxNbLit;
-
-    /* longLengthPos and longLengthType to allow us to represent either a single litLength or matchLength
-     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
-     * the existing value of the litLength or matchLength by 0x10000.
-     */
-    ZSTD_longLengthType_e longLengthType;
-    U32                   longLengthPos;  /* Index of the sequence to apply long length modification to */
-} seqStore_t;
-
-typedef struct {
-    U32 litLength;
-    U32 matchLength;
-} ZSTD_sequenceLength;
-
-/**
- * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences
- * indicated by longLengthPos and longLengthType, and adds MINMATCH back to matchLength.
- */
-MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq)
-{
-    ZSTD_sequenceLength seqLen;
-    seqLen.litLength = seq->litLength;
-    seqLen.matchLength = seq->mlBase + MINMATCH;
-    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
-        if (seqStore->longLengthType == ZSTD_llt_literalLength) {
-            seqLen.litLength += 0x10000;
-        }
-        if (seqStore->longLengthType == ZSTD_llt_matchLength) {
-            seqLen.matchLength += 0x10000;
-        }
-    }
-    return seqLen;
-}
 
 /**
  * Contains the compressed frame size and an upper-bound for the decompressed frame size.
@@ -347,10 +287,6 @@ typedef struct {
     unsigned long long decompressedBound;
 } ZSTD_frameSizeInfo;   /* decompress & legacy */
 
-const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
-int ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
-
-
 /* ZSTD_invalidateRepCodes() :
  * ensures next compression will not use repcodes from previous block.
  * Note : only works with regular variant;
@@ -366,13 +302,13 @@ typedef struct {
 
 /*! ZSTD_getcBlockSize() :
  *  Provides the size of compressed block from block header `src` */
-/* Used by: decompress, fullbench (does not get its definition from here) */
+/*  Used by: decompress, fullbench */
 size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
                           blockProperties_t* bpPtr);
 
 /*! ZSTD_decodeSeqHeaders() :
  *  decode sequence header from src */
-/* Used by: decompress, fullbench (does not get its definition from here) */
+/*  Used by: zstd_decompress_block, fullbench */
 size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                        const void* src, size_t srcSize);
 
@@ -385,8 +321,4 @@ MEM_STATIC int ZSTD_cpuSupportsBmi2(void)
     return ZSTD_cpuid_bmi1(cpuid) && ZSTD_cpuid_bmi2(cpuid);
 }
 
-#if defined (__cplusplus)
-}
-#endif
-
 #endif   /* ZSTD_CCOMMON_H_MODULE */

zstd.mod/zstd/lib/common/zstd_trace.h

@@ -11,23 +11,20 @@
 #ifndef ZSTD_TRACE_H
 #define ZSTD_TRACE_H
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
 #include <stddef.h>
 
 /* weak symbol support
  * For now, enable conservatively:
  * - Only GNUC
  * - Only ELF
- * - Only x86-64, i386 and aarch64
+ * - Only x86-64, i386, aarch64 and risc-v.
  * Also, explicitly disable on platforms known not to work so they aren't
  * forgotten in the future.
  */
 #if !defined(ZSTD_HAVE_WEAK_SYMBOLS) && \
     defined(__GNUC__) && defined(__ELF__) && \
-    (defined(__x86_64__) || defined(_M_X64) || defined(__i386__) || defined(_M_IX86) || defined(__aarch64__)) && \
+    (defined(__x86_64__) || defined(_M_X64) || defined(__i386__) || \
+     defined(_M_IX86) || defined(__aarch64__) || defined(__riscv)) && \
     !defined(__APPLE__) && !defined(_WIN32) && !defined(__MINGW32__) && \
     !defined(__CYGWIN__) && !defined(_AIX)
 #  define ZSTD_HAVE_WEAK_SYMBOLS 1
@@ -64,7 +61,7 @@ typedef struct {
     /**
      * Non-zero if streaming (de)compression is used.
      */
-    unsigned streaming;
+    int streaming;
     /**
      * The dictionary ID.
      */
@@ -73,7 +70,7 @@ typedef struct {
      * Is the dictionary cold?
      * Only set on decompression.
      */
-    unsigned dictionaryIsCold;
+    int dictionaryIsCold;
     /**
      * The dictionary size or zero if no dictionary.
      */
@@ -156,8 +153,4 @@ ZSTD_WEAK_ATTR void ZSTD_trace_decompress_end(
 
 #endif /* ZSTD_TRACE */
 
-#if defined (__cplusplus)
-}
-#endif
-
 #endif /* ZSTD_TRACE_H */

zstd.mod/zstd/lib/compress/fse_compress.c

@@ -25,7 +25,7 @@
 #include "../common/error_private.h"
 #define ZSTD_DEPS_NEED_MALLOC
 #define ZSTD_DEPS_NEED_MATH64
-#include "../common/zstd_deps.h"  /* ZSTD_malloc, ZSTD_free, ZSTD_memcpy, ZSTD_memset */
+#include "../common/zstd_deps.h"  /* ZSTD_memset */
 #include "../common/bits.h" /* ZSTD_highbit32 */
 
 
@@ -225,8 +225,8 @@ size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog)
     size_t const maxHeaderSize = (((maxSymbolValue+1) * tableLog
                                    + 4 /* bitCount initialized at 4 */
                                    + 2 /* first two symbols may use one additional bit each */) / 8)
-                                    + 1 /* round up to whole nb bytes */
-                                    + 2 /* additional two bytes for bitstream flush */;
+                                   + 1 /* round up to whole nb bytes */
+                                   + 2 /* additional two bytes for bitstream flush */;
     return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND;  /* maxSymbolValue==0 ? use default */
 }
 
@@ -255,7 +255,7 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize,
     /* Init */
     remaining = tableSize+1;   /* +1 for extra accuracy */
     threshold = tableSize;
-    nbBits = tableLog+1;
+    nbBits = (int)tableLog+1;
 
     while ((symbol < alphabetSize) && (remaining>1)) {  /* stops at 1 */
         if (previousIs0) {
@@ -274,7 +274,7 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize,
             }
             while (symbol >= start+3) {
                 start+=3;
-                bitStream += 3 << bitCount;
+                bitStream += 3U << bitCount;
                 bitCount += 2;
             }
             bitStream += (symbol-start) << bitCount;
@@ -294,7 +294,7 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize,
             count++;   /* +1 for extra accuracy */
             if (count>=threshold)
                 count += max;   /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */
-            bitStream += count << bitCount;
+            bitStream += (U32)count << bitCount;
             bitCount  += nbBits;
             bitCount  -= (count<max);
             previousIs0  = (count==1);
@@ -322,7 +322,8 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize,
     out[1] = (BYTE)(bitStream>>8);
     out+= (bitCount+7) /8;
 
-    return (out-ostart);
+    assert(out >= ostart);
+    return (size_t)(out-ostart);
 }
 
 

zstd.mod/zstd/lib/compress/hist.c

@@ -26,6 +26,16 @@ unsigned HIST_isError(size_t code) { return ERR_isError(code); }
 /*-**************************************************************
  *  Histogram functions
  ****************************************************************/
+void HIST_add(unsigned* count, const void* src, size_t srcSize)
+{
+    const BYTE* ip = (const BYTE*)src;
+    const BYTE* const end = ip + srcSize;
+
+    while (ip<end) {
+        count[*ip++]++;
+    }
+}
+
 unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
                            const void* src, size_t srcSize)
 {

zstd.mod/zstd/lib/compress/hist.h

@@ -73,3 +73,10 @@ size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
  */
 unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
                            const void* src, size_t srcSize);
+
+/*! HIST_add() :
+ *  Lowest level: just add nb of occurrences of characters from @src into @count.
+ *  @count is not reset. @count array is presumed large enough (i.e. 1 KB).
+ @  This function does not need any additional stack memory.
+ */
+void HIST_add(unsigned* count, const void* src, size_t srcSize);

zstd.mod/zstd/lib/compress/huf_compress.c

@@ -220,6 +220,25 @@ static void HUF_setValue(HUF_CElt* elt, size_t value)
     }
 }
 
+HUF_CTableHeader HUF_readCTableHeader(HUF_CElt const* ctable)
+{
+    HUF_CTableHeader header;
+    ZSTD_memcpy(&header, ctable, sizeof(header));
+    return header;
+}
+
+static void HUF_writeCTableHeader(HUF_CElt* ctable, U32 tableLog, U32 maxSymbolValue)
+{
+    HUF_CTableHeader header;
+    HUF_STATIC_ASSERT(sizeof(ctable[0]) == sizeof(header));
+    ZSTD_memset(&header, 0, sizeof(header));
+    assert(tableLog < 256);
+    header.tableLog = (BYTE)tableLog;
+    assert(maxSymbolValue < 256);
+    header.maxSymbolValue = (BYTE)maxSymbolValue;
+    ZSTD_memcpy(ctable, &header, sizeof(header));
+}
+
 typedef struct {
     HUF_CompressWeightsWksp wksp;
     BYTE bitsToWeight[HUF_TABLELOG_MAX + 1];   /* precomputed conversion table */
@@ -237,6 +256,9 @@ size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize,
 
     HUF_STATIC_ASSERT(HUF_CTABLE_WORKSPACE_SIZE >= sizeof(HUF_WriteCTableWksp));
 
+    assert(HUF_readCTableHeader(CTable).maxSymbolValue == maxSymbolValue);
+    assert(HUF_readCTableHeader(CTable).tableLog == huffLog);
+
     /* check conditions */
     if (workspaceSize < sizeof(HUF_WriteCTableWksp)) return ERROR(GENERIC);
     if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge);
@@ -283,7 +305,9 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void
     if (tableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
     if (nbSymbols > *maxSymbolValuePtr+1) return ERROR(maxSymbolValue_tooSmall);
 
-    CTable[0] = tableLog;
+    *maxSymbolValuePtr = nbSymbols - 1;
+
+    HUF_writeCTableHeader(CTable, tableLog, *maxSymbolValuePtr);
 
     /* Prepare base value per rank */
     {   U32 n, nextRankStart = 0;
@@ -315,7 +339,6 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void
         { U32 n; for (n=0; n<nbSymbols; n++) HUF_setValue(ct + n, valPerRank[HUF_getNbBits(ct[n])]++); }
     }
 
-    *maxSymbolValuePtr = nbSymbols - 1;
     return readSize;
 }
 
@@ -323,6 +346,8 @@ U32 HUF_getNbBitsFromCTable(HUF_CElt const* CTable, U32 symbolValue)
 {
     const HUF_CElt* const ct = CTable + 1;
     assert(symbolValue <= HUF_SYMBOLVALUE_MAX);
+    if (symbolValue > HUF_readCTableHeader(CTable).maxSymbolValue)
+        return 0;
     return (U32)HUF_getNbBits(ct[symbolValue]);
 }
 
@@ -723,7 +748,8 @@ static void HUF_buildCTableFromTree(HUF_CElt* CTable, nodeElt const* huffNode, i
         HUF_setNbBits(ct + huffNode[n].byte, huffNode[n].nbBits);   /* push nbBits per symbol, symbol order */
     for (n=0; n<alphabetSize; n++)
         HUF_setValue(ct + n, valPerRank[HUF_getNbBits(ct[n])]++);   /* assign value within rank, symbol order */
-    CTable[0] = maxNbBits;
+
+    HUF_writeCTableHeader(CTable, maxNbBits, maxSymbolValue);
 }
 
 size_t
@@ -776,13 +802,20 @@ size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count,
 }
 
 int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) {
-  HUF_CElt const* ct = CTable + 1;
-  int bad = 0;
-  int s;
-  for (s = 0; s <= (int)maxSymbolValue; ++s) {
-    bad |= (count[s] != 0) & (HUF_getNbBits(ct[s]) == 0);
-  }
-  return !bad;
+    HUF_CTableHeader header = HUF_readCTableHeader(CTable);
+    HUF_CElt const* ct = CTable + 1;
+    int bad = 0;
+    int s;
+
+    assert(header.tableLog <= HUF_TABLELOG_ABSOLUTEMAX);
+
+    if (header.maxSymbolValue < maxSymbolValue)
+        return 0;
+
+    for (s = 0; s <= (int)maxSymbolValue; ++s) {
+        bad |= (count[s] != 0) & (HUF_getNbBits(ct[s]) == 0);
+    }
+    return !bad;
 }
 
 size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); }
@@ -1024,17 +1057,17 @@ HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize,
                                    const void* src, size_t srcSize,
                                    const HUF_CElt* CTable)
 {
-    U32 const tableLog = (U32)CTable[0];
+    U32 const tableLog = HUF_readCTableHeader(CTable).tableLog;
     HUF_CElt const* ct = CTable + 1;
     const BYTE* ip = (const BYTE*) src;
     BYTE* const ostart = (BYTE*)dst;
     BYTE* const oend = ostart + dstSize;
-    BYTE* op = ostart;
     HUF_CStream_t bitC;
 
     /* init */
     if (dstSize < 8) return 0;   /* not enough space to compress */
-    { size_t const initErr = HUF_initCStream(&bitC, op, (size_t)(oend-op));
+    { BYTE* op = ostart;
+      size_t const initErr = HUF_initCStream(&bitC, op, (size_t)(oend-op));
       if (HUF_isError(initErr)) return 0; }
 
     if (dstSize < HUF_tightCompressBound(srcSize, (size_t)tableLog) || tableLog > 11)
@@ -1255,7 +1288,7 @@ unsigned HUF_optimalTableLog(
 
     {   BYTE* dst = (BYTE*)workSpace + sizeof(HUF_WriteCTableWksp);
         size_t dstSize = wkspSize - sizeof(HUF_WriteCTableWksp);
-        size_t maxBits, hSize, newSize;
+        size_t hSize, newSize;
         const unsigned symbolCardinality = HUF_cardinality(count, maxSymbolValue);
         const unsigned minTableLog = HUF_minTableLog(symbolCardinality);
         size_t optSize = ((size_t) ~0) - 1;
@@ -1266,12 +1299,14 @@ unsigned HUF_optimalTableLog(
         /* Search until size increases */
         for (optLogGuess = minTableLog; optLogGuess <= maxTableLog; optLogGuess++) {
             DEBUGLOG(7, "checking for huffLog=%u", optLogGuess);
-            maxBits = HUF_buildCTable_wksp(table, count, maxSymbolValue, optLogGuess, workSpace, wkspSize);
-            if (ERR_isError(maxBits)) continue;
 
-            if (maxBits < optLogGuess && optLogGuess > minTableLog) break;
+            {   size_t maxBits = HUF_buildCTable_wksp(table, count, maxSymbolValue, optLogGuess, workSpace, wkspSize);
+                if (ERR_isError(maxBits)) continue;
+
+                if (maxBits < optLogGuess && optLogGuess > minTableLog) break;
 
-            hSize = HUF_writeCTable_wksp(dst, dstSize, table, maxSymbolValue, (U32)maxBits, workSpace, wkspSize);
+                hSize = HUF_writeCTable_wksp(dst, dstSize, table, maxSymbolValue, (U32)maxBits, workSpace, wkspSize);
+            }
 
             if (ERR_isError(hSize)) continue;
 
@@ -1372,12 +1407,6 @@ HUF_compress_internal (void* dst, size_t dstSize,
         huffLog = (U32)maxBits;
         DEBUGLOG(6, "bit distribution completed (%zu symbols)", showCTableBits(table->CTable + 1, maxSymbolValue+1));
     }
-    /* Zero unused symbols in CTable, so we can check it for validity */
-    {
-        size_t const ctableSize = HUF_CTABLE_SIZE_ST(maxSymbolValue);
-        size_t const unusedSize = sizeof(table->CTable) - ctableSize * sizeof(HUF_CElt);
-        ZSTD_memset(table->CTable + ctableSize, 0, unusedSize);
-    }
 
     /* Write table description header */
     {   CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, table->CTable, maxSymbolValue, huffLog,
@@ -1420,7 +1449,7 @@ size_t HUF_compress1X_repeat (void* dst, size_t dstSize,
 /* HUF_compress4X_repeat():
  * compress input using 4 streams.
  * consider skipping quickly
- * re-use an existing huffman compression table */
+ * reuse an existing huffman compression table */
 size_t HUF_compress4X_repeat (void* dst, size_t dstSize,
                       const void* src, size_t srcSize,
                       unsigned maxSymbolValue, unsigned huffLog,

zstd.mod/zstd/lib/compress/zstd_compress_internal.h

@@ -24,10 +24,7 @@
 #  include "zstdmt_compress.h"
 #endif
 #include "../common/bits.h" /* ZSTD_highbit32, ZSTD_NbCommonBytes */
-
-#if defined (__cplusplus)
-extern "C" {
-#endif
+#include "zstd_preSplit.h" /* ZSTD_SLIPBLOCK_WORKSPACESIZE */
 
 /*-*************************************
 *  Constants
@@ -39,7 +36,7 @@ extern "C" {
                                        It's not a big deal though : candidate will just be sorted again.
                                        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 mishandled after table re-use with a different strategy.
+                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table reuse with a different strategy.
                                        This constant is required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */
 
 
@@ -82,6 +79,70 @@ typedef struct {
     ZSTD_fseCTables_t fse;
 } ZSTD_entropyCTables_t;
 
+/***********************************************
+*  Sequences *
+***********************************************/
+typedef struct SeqDef_s {
+    U32 offBase;   /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */
+    U16 litLength;
+    U16 mlBase;    /* mlBase == matchLength - MINMATCH */
+} SeqDef;
+
+/* Controls whether seqStore has a single "long" litLength or matchLength. See SeqStore_t. */
+typedef enum {
+    ZSTD_llt_none = 0,             /* no longLengthType */
+    ZSTD_llt_literalLength = 1,    /* represents a long literal */
+    ZSTD_llt_matchLength = 2       /* represents a long match */
+} ZSTD_longLengthType_e;
+
+typedef struct {
+    SeqDef* sequencesStart;
+    SeqDef* sequences;      /* ptr to end of sequences */
+    BYTE*  litStart;
+    BYTE*  lit;             /* ptr to end of literals */
+    BYTE*  llCode;
+    BYTE*  mlCode;
+    BYTE*  ofCode;
+    size_t maxNbSeq;
+    size_t maxNbLit;
+
+    /* longLengthPos and longLengthType to allow us to represent either a single litLength or matchLength
+     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
+     * the existing value of the litLength or matchLength by 0x10000.
+     */
+    ZSTD_longLengthType_e longLengthType;
+    U32                   longLengthPos;  /* Index of the sequence to apply long length modification to */
+} SeqStore_t;
+
+typedef struct {
+    U32 litLength;
+    U32 matchLength;
+} ZSTD_SequenceLength;
+
+/**
+ * Returns the ZSTD_SequenceLength for the given sequences. It handles the decoding of long sequences
+ * indicated by longLengthPos and longLengthType, and adds MINMATCH back to matchLength.
+ */
+MEM_STATIC ZSTD_SequenceLength ZSTD_getSequenceLength(SeqStore_t const* seqStore, SeqDef const* seq)
+{
+    ZSTD_SequenceLength seqLen;
+    seqLen.litLength = seq->litLength;
+    seqLen.matchLength = seq->mlBase + MINMATCH;
+    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
+        if (seqStore->longLengthType == ZSTD_llt_literalLength) {
+            seqLen.litLength += 0x10000;
+        }
+        if (seqStore->longLengthType == ZSTD_llt_matchLength) {
+            seqLen.matchLength += 0x10000;
+        }
+    }
+    return seqLen;
+}
+
+const SeqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
+int ZSTD_seqToCodes(const SeqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
+
+
 /***********************************************
 *  Entropy buffer statistics structs and funcs *
 ***********************************************/
@@ -91,7 +152,7 @@ typedef struct {
  *  hufDesSize refers to the size of huffman tree description in bytes.
  *  This metadata is populated in ZSTD_buildBlockEntropyStats_literals() */
 typedef struct {
-    symbolEncodingType_e hType;
+    SymbolEncodingType_e hType;
     BYTE hufDesBuffer[ZSTD_MAX_HUF_HEADER_SIZE];
     size_t hufDesSize;
 } ZSTD_hufCTablesMetadata_t;
@@ -102,9 +163,9 @@ typedef struct {
  *  fseTablesSize refers to the size of fse tables in bytes.
  *  This metadata is populated in ZSTD_buildBlockEntropyStats_sequences() */
 typedef struct {
-    symbolEncodingType_e llType;
-    symbolEncodingType_e ofType;
-    symbolEncodingType_e mlType;
+    SymbolEncodingType_e llType;
+    SymbolEncodingType_e ofType;
+    SymbolEncodingType_e mlType;
     BYTE fseTablesBuffer[ZSTD_MAX_FSE_HEADERS_SIZE];
     size_t fseTablesSize;
     size_t lastCountSize; /* This is to account for bug in 1.3.4. More detail in ZSTD_entropyCompressSeqStore_internal() */
@@ -119,7 +180,7 @@ typedef struct {
  *  Builds entropy for the block.
  *  @return : 0 on success or error code */
 size_t ZSTD_buildBlockEntropyStats(
-                    const seqStore_t* seqStorePtr,
+                    const SeqStore_t* seqStorePtr,
                     const ZSTD_entropyCTables_t* prevEntropy,
                           ZSTD_entropyCTables_t* nextEntropy,
                     const ZSTD_CCtx_params* cctxParams,
@@ -148,34 +209,29 @@ typedef struct {
                            stopped. posInSequence <= seq[pos].litLength + seq[pos].matchLength */
   size_t size;          /* The number of sequences. <= capacity. */
   size_t capacity;      /* The capacity starting from `seq` pointer */
-} rawSeqStore_t;
+} RawSeqStore_t;
 
-typedef struct {
-    U32 idx;            /* Index in array of ZSTD_Sequence */
-    U32 posInSequence;  /* Position within sequence at idx */
-    size_t posInSrc;    /* Number of bytes given by sequences provided so far */
-} ZSTD_sequencePosition;
-
-UNUSED_ATTR static const rawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0};
+UNUSED_ATTR static const RawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0};
 
 typedef struct {
-    int price;
-    U32 off;
-    U32 mlen;
-    U32 litlen;
-    U32 rep[ZSTD_REP_NUM];
+    int price;  /* price from beginning of segment to this position */
+    U32 off;    /* offset of previous match */
+    U32 mlen;   /* length of previous match */
+    U32 litlen; /* nb of literals since previous match */
+    U32 rep[ZSTD_REP_NUM];  /* offset history after previous match */
 } ZSTD_optimal_t;
 
 typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e;
 
+#define ZSTD_OPT_SIZE (ZSTD_OPT_NUM+3)
 typedef struct {
     /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */
     unsigned* litFreq;           /* table of literals statistics, of size 256 */
     unsigned* litLengthFreq;     /* table of litLength statistics, of size (MaxLL+1) */
     unsigned* matchLengthFreq;   /* table of matchLength statistics, of size (MaxML+1) */
     unsigned* offCodeFreq;       /* table of offCode statistics, of size (MaxOff+1) */
-    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_NUM+1 */
-    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */
+    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_SIZE */
+    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_SIZE */
 
     U32  litSum;                 /* nb of literals */
     U32  litLengthSum;           /* nb of litLength codes */
@@ -187,7 +243,7 @@ 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_paramSwitch_e literalCompressionMode;
+    ZSTD_ParamSwitch_e literalCompressionMode;
 } optState_t;
 
 typedef struct {
@@ -209,11 +265,11 @@ typedef struct {
 
 #define ZSTD_WINDOW_START_INDEX 2
 
-typedef struct ZSTD_matchState_t ZSTD_matchState_t;
+typedef struct ZSTD_MatchState_t ZSTD_MatchState_t;
 
 #define ZSTD_ROW_HASH_CACHE_SIZE 8       /* Size of prefetching hash cache for row-based matchfinder */
 
-struct ZSTD_matchState_t {
+struct ZSTD_MatchState_t {
     ZSTD_window_t window;   /* State for window round buffer management */
     U32 loadedDictEnd;      /* index of end of dictionary, within context's referential.
                              * When loadedDictEnd != 0, a dictionary is in use, and still valid.
@@ -228,22 +284,22 @@ struct ZSTD_matchState_t {
     U32 rowHashLog;                          /* For row-based matchfinder: Hashlog based on nb of rows in the hashTable.*/
     BYTE* tagTable;                          /* For row-based matchFinder: A row-based table containing the hashes and head index. */
     U32 hashCache[ZSTD_ROW_HASH_CACHE_SIZE]; /* For row-based matchFinder: a cache of hashes to improve speed */
-    U64 hashSalt;                            /* For row-based matchFinder: salts the hash for re-use of tag table */
+    U64 hashSalt;                            /* For row-based matchFinder: salts the hash for reuse of tag table */
     U32 hashSaltEntropy;                     /* For row-based matchFinder: collects entropy for salt generation */
 
     U32* hashTable;
     U32* hashTable3;
     U32* chainTable;
 
-    U32 forceNonContiguous; /* Non-zero if we should force non-contiguous load for the next window update. */
+    int forceNonContiguous; /* Non-zero if we should force non-contiguous load for the next window update. */
 
     int dedicatedDictSearch;  /* Indicates whether this matchState is using the
                                * dedicated dictionary search structure.
                                */
     optState_t opt;         /* optimal parser state */
-    const ZSTD_matchState_t* dictMatchState;
+    const ZSTD_MatchState_t* dictMatchState;
     ZSTD_compressionParameters cParams;
-    const rawSeqStore_t* ldmSeqStore;
+    const RawSeqStore_t* ldmSeqStore;
 
     /* Controls prefetching in some dictMatchState matchfinders.
      * This behavior is controlled from the cctx ms.
@@ -261,7 +317,7 @@ struct ZSTD_matchState_t {
 typedef struct {
     ZSTD_compressedBlockState_t* prevCBlock;
     ZSTD_compressedBlockState_t* nextCBlock;
-    ZSTD_matchState_t matchState;
+    ZSTD_MatchState_t matchState;
 } ZSTD_blockState_t;
 
 typedef struct {
@@ -288,7 +344,7 @@ typedef struct {
 } ldmState_t;
 
 typedef struct {
-    ZSTD_paramSwitch_e enableLdm; /* ZSTD_ps_enable to enable LDM. ZSTD_ps_auto by default */
+    ZSTD_ParamSwitch_e enableLdm; /* ZSTD_ps_enable to enable LDM. ZSTD_ps_auto by default */
     U32 hashLog;            /* Log size of hashTable */
     U32 bucketSizeLog;      /* Log bucket size for collision resolution, at most 8 */
     U32 minMatchLength;     /* Minimum match length */
@@ -319,7 +375,7 @@ struct ZSTD_CCtx_params_s {
                                 * There is no guarantee that hint is close to actual source size */
 
     ZSTD_dictAttachPref_e attachDictPref;
-    ZSTD_paramSwitch_e literalCompressionMode;
+    ZSTD_ParamSwitch_e literalCompressionMode;
 
     /* Multithreading: used to pass parameters to mtctx */
     int nbWorkers;
@@ -338,14 +394,27 @@ struct ZSTD_CCtx_params_s {
     ZSTD_bufferMode_e outBufferMode;
 
     /* Sequence compression API */
-    ZSTD_sequenceFormat_e blockDelimiters;
+    ZSTD_SequenceFormat_e blockDelimiters;
     int validateSequences;
 
-    /* Block splitting */
-    ZSTD_paramSwitch_e useBlockSplitter;
+    /* Block splitting
+     * @postBlockSplitter executes split analysis after sequences are produced,
+     * it's more accurate but consumes more resources.
+     * @preBlockSplitter_level splits before knowing sequences,
+     * it's more approximative but also cheaper.
+     * Valid @preBlockSplitter_level values range from 0 to 6 (included).
+     * 0 means auto, 1 means do not split,
+     * then levels are sorted in increasing cpu budget, from 2 (fastest) to 6 (slowest).
+     * Highest @preBlockSplitter_level combines well with @postBlockSplitter.
+     */
+    ZSTD_ParamSwitch_e postBlockSplitter;
+    int preBlockSplitter_level;
+
+    /* Adjust the max block size*/
+    size_t maxBlockSize;
 
     /* Param for deciding whether to use row-based matchfinder */
-    ZSTD_paramSwitch_e useRowMatchFinder;
+    ZSTD_ParamSwitch_e useRowMatchFinder;
 
     /* Always load a dictionary in ext-dict mode (not prefix mode)? */
     int deterministicRefPrefix;
@@ -354,26 +423,25 @@ struct ZSTD_CCtx_params_s {
     ZSTD_customMem customMem;
 
     /* Controls prefetching in some dictMatchState matchfinders */
-    ZSTD_paramSwitch_e prefetchCDictTables;
+    ZSTD_ParamSwitch_e prefetchCDictTables;
 
     /* Controls whether zstd will fall back to an internal matchfinder
      * if the external matchfinder returns an error code. */
     int enableMatchFinderFallback;
 
-    /* Indicates whether an external matchfinder has been referenced.
-     * Users can't set this externally.
-     * It is set internally in ZSTD_registerSequenceProducer(). */
-    int useSequenceProducer;
-
-    /* Adjust the max block size*/
-    size_t maxBlockSize;
+    /* Parameters for the external sequence producer API.
+     * Users set these parameters through ZSTD_registerSequenceProducer().
+     * It is not possible to set these parameters individually through the public API. */
+    void* extSeqProdState;
+    ZSTD_sequenceProducer_F extSeqProdFunc;
 
     /* Controls repcode search in external sequence parsing */
-    ZSTD_paramSwitch_e searchForExternalRepcodes;
+    ZSTD_ParamSwitch_e searchForExternalRepcodes;
 };  /* typedef'd to ZSTD_CCtx_params within "zstd.h" */
 
 #define COMPRESS_SEQUENCES_WORKSPACE_SIZE (sizeof(unsigned) * (MaxSeq + 2))
 #define ENTROPY_WORKSPACE_SIZE (HUF_WORKSPACE_SIZE + COMPRESS_SEQUENCES_WORKSPACE_SIZE)
+#define TMP_WORKSPACE_SIZE (MAX(ENTROPY_WORKSPACE_SIZE, ZSTD_SLIPBLOCK_WORKSPACESIZE))
 
 /**
  * Indicates whether this compression proceeds directly from user-provided
@@ -391,24 +459,16 @@ typedef enum {
  */
 #define ZSTD_MAX_NB_BLOCK_SPLITS 196
 typedef struct {
-    seqStore_t fullSeqStoreChunk;
-    seqStore_t firstHalfSeqStore;
-    seqStore_t secondHalfSeqStore;
-    seqStore_t currSeqStore;
-    seqStore_t nextSeqStore;
+    SeqStore_t fullSeqStoreChunk;
+    SeqStore_t firstHalfSeqStore;
+    SeqStore_t secondHalfSeqStore;
+    SeqStore_t currSeqStore;
+    SeqStore_t nextSeqStore;
 
     U32 partitions[ZSTD_MAX_NB_BLOCK_SPLITS];
     ZSTD_entropyCTablesMetadata_t entropyMetadata;
 } ZSTD_blockSplitCtx;
 
-/* Context for block-level external matchfinder API */
-typedef struct {
-  void* mState;
-  ZSTD_sequenceProducer_F* mFinder;
-  ZSTD_Sequence* seqBuffer;
-  size_t seqBufferCapacity;
-} ZSTD_externalMatchCtx;
-
 struct ZSTD_CCtx_s {
     ZSTD_compressionStage_e stage;
     int cParamsChanged;                  /* == 1 if cParams(except wlog) or compression level are changed in requestedParams. Triggers transmission of new params to ZSTDMT (if available) then reset to 0. */
@@ -420,7 +480,7 @@ struct ZSTD_CCtx_s {
     size_t dictContentSize;
 
     ZSTD_cwksp workspace; /* manages buffer for dynamic allocations */
-    size_t blockSize;
+    size_t blockSizeMax;
     unsigned long long pledgedSrcSizePlusOne;  /* this way, 0 (default) == unknown */
     unsigned long long consumedSrcSize;
     unsigned long long producedCSize;
@@ -432,13 +492,14 @@ struct ZSTD_CCtx_s {
     int isFirstBlock;
     int initialized;
 
-    seqStore_t seqStore;      /* sequences storage ptrs */
+    SeqStore_t seqStore;      /* sequences storage ptrs */
     ldmState_t ldmState;      /* long distance matching state */
     rawSeq* ldmSequences;     /* Storage for the ldm output sequences */
     size_t maxNbLdmSequences;
-    rawSeqStore_t externSeqStore; /* Mutable reference to external sequences */
+    RawSeqStore_t externSeqStore; /* Mutable reference to external sequences */
     ZSTD_blockState_t blockState;
-    U32* entropyWorkspace;  /* entropy workspace of ENTROPY_WORKSPACE_SIZE bytes */
+    void* tmpWorkspace;  /* used as substitute of stack space - must be aligned for S64 type */
+    size_t tmpWkspSize;
 
     /* Whether we are streaming or not */
     ZSTD_buffered_policy_e bufferedPolicy;
@@ -479,8 +540,9 @@ struct ZSTD_CCtx_s {
     /* Workspace for block splitter */
     ZSTD_blockSplitCtx blockSplitCtx;
 
-    /* Workspace for external matchfinder */
-    ZSTD_externalMatchCtx externalMatchCtx;
+    /* Buffer for output from external sequence producer */
+    ZSTD_Sequence* extSeqBuf;
+    size_t extSeqBufCapacity;
 };
 
 typedef enum { ZSTD_dtlm_fast, ZSTD_dtlm_full } ZSTD_dictTableLoadMethod_e;
@@ -511,12 +573,12 @@ typedef enum {
                                  * behavior of taking both the source size and the dict size into account
                                  * when selecting and adjusting parameters.
                                  */
-} ZSTD_cParamMode_e;
+} ZSTD_CParamMode_e;
 
-typedef size_t (*ZSTD_blockCompressor) (
-        ZSTD_matchState_t* bs, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+typedef size_t (*ZSTD_BlockCompressor_f) (
+        ZSTD_MatchState_t* bs, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize);
-ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramSwitch_e rowMatchfinderMode, ZSTD_dictMode_e dictMode);
+ZSTD_BlockCompressor_f ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_ParamSwitch_e rowMatchfinderMode, ZSTD_dictMode_e dictMode);
 
 
 MEM_STATIC U32 ZSTD_LLcode(U32 litLength)
@@ -562,6 +624,25 @@ MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
     return 1;
 }
 
+/* ZSTD_selectAddr:
+ * @return index >= lowLimit ? candidate : backup,
+ * tries to force branchless codegen. */
+MEM_STATIC const BYTE*
+ZSTD_selectAddr(U32 index, U32 lowLimit, const BYTE* candidate, const BYTE* backup)
+{
+#if defined(__GNUC__) && defined(__x86_64__)
+    __asm__ (
+        "cmp %1, %2\n"
+        "cmova %3, %0\n"
+        : "+r"(candidate)
+        : "r"(index), "r"(lowLimit), "r"(backup)
+        );
+    return candidate;
+#else
+    return index >= lowLimit ? candidate : backup;
+#endif
+}
+
 /* ZSTD_noCompressBlock() :
  * Writes uncompressed block to dst buffer from given src.
  * Returns the size of the block */
@@ -644,14 +725,55 @@ ZSTD_safecopyLiterals(BYTE* op, BYTE const* ip, BYTE const* const iend, BYTE con
 #define OFFBASE_TO_OFFSET(o)  (assert(OFFBASE_IS_OFFSET(o)), (o) - ZSTD_REP_NUM)
 #define OFFBASE_TO_REPCODE(o) (assert(OFFBASE_IS_REPCODE(o)), (o))  /* returns ID 1,2,3 */
 
+/*! ZSTD_storeSeqOnly() :
+ *  Store a sequence (litlen, litPtr, offBase and matchLength) into SeqStore_t.
+ *  Literals themselves are not copied, but @litPtr is updated.
+ *  @offBase : Users should employ macros REPCODE_TO_OFFBASE() and OFFSET_TO_OFFBASE().
+ *  @matchLength : must be >= MINMATCH
+*/
+HINT_INLINE UNUSED_ATTR void
+ZSTD_storeSeqOnly(SeqStore_t* seqStorePtr,
+              size_t litLength,
+              U32 offBase,
+              size_t matchLength)
+{
+    assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq);
+
+    /* literal Length */
+    assert(litLength <= ZSTD_BLOCKSIZE_MAX);
+    if (UNLIKELY(litLength>0xFFFF)) {
+        assert(seqStorePtr->longLengthType == ZSTD_llt_none); /* there can only be a single long length */
+        seqStorePtr->longLengthType = ZSTD_llt_literalLength;
+        seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+    }
+    seqStorePtr->sequences[0].litLength = (U16)litLength;
+
+    /* match offset */
+    seqStorePtr->sequences[0].offBase = offBase;
+
+    /* match Length */
+    assert(matchLength <= ZSTD_BLOCKSIZE_MAX);
+    assert(matchLength >= MINMATCH);
+    {   size_t const mlBase = matchLength - MINMATCH;
+        if (UNLIKELY(mlBase>0xFFFF)) {
+            assert(seqStorePtr->longLengthType == ZSTD_llt_none); /* there can only be a single long length */
+            seqStorePtr->longLengthType = ZSTD_llt_matchLength;
+            seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+        }
+        seqStorePtr->sequences[0].mlBase = (U16)mlBase;
+    }
+
+    seqStorePtr->sequences++;
+}
+
 /*! ZSTD_storeSeq() :
- *  Store a sequence (litlen, litPtr, offBase and matchLength) into seqStore_t.
+ *  Store a sequence (litlen, litPtr, offBase and matchLength) into SeqStore_t.
  *  @offBase : Users should employ macros REPCODE_TO_OFFBASE() and OFFSET_TO_OFFBASE().
  *  @matchLength : must be >= MINMATCH
  *  Allowed to over-read literals up to litLimit.
 */
 HINT_INLINE UNUSED_ATTR void
-ZSTD_storeSeq(seqStore_t* seqStorePtr,
+ZSTD_storeSeq(SeqStore_t* seqStorePtr,
               size_t litLength, const BYTE* literals, const BYTE* litLimit,
               U32 offBase,
               size_t matchLength)
@@ -685,29 +807,7 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr,
     }
     seqStorePtr->lit += litLength;
 
-    /* literal Length */
-    if (litLength>0xFFFF) {
-        assert(seqStorePtr->longLengthType == ZSTD_llt_none); /* there can only be a single long length */
-        seqStorePtr->longLengthType = ZSTD_llt_literalLength;
-        seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
-    }
-    seqStorePtr->sequences[0].litLength = (U16)litLength;
-
-    /* match offset */
-    seqStorePtr->sequences[0].offBase = offBase;
-
-    /* match Length */
-    assert(matchLength >= MINMATCH);
-    {   size_t const mlBase = matchLength - MINMATCH;
-        if (mlBase>0xFFFF) {
-            assert(seqStorePtr->longLengthType == ZSTD_llt_none); /* there can only be a single long length */
-            seqStorePtr->longLengthType = ZSTD_llt_matchLength;
-            seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
-        }
-        seqStorePtr->sequences[0].mlBase = (U16)mlBase;
-    }
-
-    seqStorePtr->sequences++;
+    ZSTD_storeSeqOnly(seqStorePtr, litLength, offBase, matchLength);
 }
 
 /* ZSTD_updateRep() :
@@ -736,12 +836,12 @@ ZSTD_updateRep(U32 rep[ZSTD_REP_NUM], U32 const offBase, U32 const ll0)
 
 typedef struct repcodes_s {
     U32 rep[3];
-} repcodes_t;
+} Repcodes_t;
 
-MEM_STATIC repcodes_t
+MEM_STATIC Repcodes_t
 ZSTD_newRep(U32 const rep[ZSTD_REP_NUM], U32 const offBase, U32 const ll0)
 {
-    repcodes_t newReps;
+    Repcodes_t newReps;
     ZSTD_memcpy(&newReps, rep, sizeof(newReps));
     ZSTD_updateRep(newReps.rep, offBase, ll0);
     return newReps;
@@ -784,8 +884,8 @@ ZSTD_count_2segments(const BYTE* ip, const BYTE* match,
     size_t const matchLength = ZSTD_count(ip, match, vEnd);
     if (match + matchLength != mEnd) return matchLength;
     DEBUGLOG(7, "ZSTD_count_2segments: found a 2-parts match (current length==%zu)", matchLength);
-    DEBUGLOG(7, "distance from match beginning to end dictionary = %zi", mEnd - match);
-    DEBUGLOG(7, "distance from current pos to end buffer = %zi", iEnd - ip);
+    DEBUGLOG(7, "distance from match beginning to end dictionary = %i", (int)(mEnd - match));
+    DEBUGLOG(7, "distance from current pos to end buffer = %i", (int)(iEnd - ip));
     DEBUGLOG(7, "next byte : ip==%02X, istart==%02X", ip[matchLength], *iStart);
     DEBUGLOG(7, "final match length = %zu", matchLength + ZSTD_count(ip+matchLength, iStart, iEnd));
     return matchLength + ZSTD_count(ip+matchLength, iStart, iEnd);
@@ -923,11 +1023,12 @@ 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))
+/* Max @current value allowed:
+ * In 32-bit mode: we want to avoid crossing the 2 GB limit,
+ *                 reducing risks of side effects in case of signed operations on indexes.
+ * In 64-bit mode: we want to ensure that adding the maximum job size (512 MB)
+ *                 doesn't overflow U32 index capacity (4 GB) */
+#define ZSTD_CURRENT_MAX (MEM_64bits() ? 3500U MB : 2000U MB)
 /* Maximum chunk size before overflow correction needs to be called again */
 #define ZSTD_CHUNKSIZE_MAX                                                     \
     ( ((U32)-1)                  /* Maximum ending current index */            \
@@ -967,7 +1068,7 @@ MEM_STATIC U32 ZSTD_window_hasExtDict(ZSTD_window_t const window)
  * Inspects the provided matchState and figures out what dictMode should be
  * passed to the compressor.
  */
-MEM_STATIC ZSTD_dictMode_e ZSTD_matchState_dictMode(const ZSTD_matchState_t *ms)
+MEM_STATIC ZSTD_dictMode_e ZSTD_matchState_dictMode(const ZSTD_MatchState_t *ms)
 {
     return ZSTD_window_hasExtDict(ms->window) ?
         ZSTD_extDict :
@@ -1053,7 +1154,9 @@ MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window,
  * The least significant cycleLog bits of the indices must remain the same,
  * which may be 0. Every index up to maxDist in the past must be valid.
  */
-MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog,
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog,
                                            U32 maxDist, void const* src)
 {
     /* preemptive overflow correction:
@@ -1154,7 +1257,7 @@ ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
                      const void* blockEnd,
                            U32   maxDist,
                            U32*  loadedDictEndPtr,
-                     const ZSTD_matchState_t** dictMatchStatePtr)
+                     const ZSTD_MatchState_t** dictMatchStatePtr)
 {
     U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
     U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
@@ -1199,7 +1302,7 @@ ZSTD_checkDictValidity(const ZSTD_window_t* window,
                        const void* blockEnd,
                              U32   maxDist,
                              U32*  loadedDictEndPtr,
-                       const ZSTD_matchState_t** dictMatchStatePtr)
+                       const ZSTD_MatchState_t** dictMatchStatePtr)
 {
     assert(loadedDictEndPtr != NULL);
     assert(dictMatchStatePtr != NULL);
@@ -1246,9 +1349,11 @@ MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) {
  * forget about the extDict. Handles overlap of the prefix and extDict.
  * Returns non-zero if the segment is contiguous.
  */
-MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
-                                  void const* src, size_t srcSize,
-                                  int forceNonContiguous)
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+U32 ZSTD_window_update(ZSTD_window_t* window,
+                 const void* src, size_t srcSize,
+                       int forceNonContiguous)
 {
     BYTE const* const ip = (BYTE const*)src;
     U32 contiguous = 1;
@@ -1275,8 +1380,9 @@ MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
     /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */
     if ( (ip+srcSize > window->dictBase + window->lowLimit)
        & (ip < window->dictBase + window->dictLimit)) {
-        ptrdiff_t const highInputIdx = (ip + srcSize) - window->dictBase;
-        U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx;
+        size_t const highInputIdx = (size_t)((ip + srcSize) - window->dictBase);
+        U32 const lowLimitMax = (highInputIdx > (size_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx;
+        assert(highInputIdx < UINT_MAX);
         window->lowLimit = lowLimitMax;
         DEBUGLOG(5, "Overlapping extDict and input : new lowLimit = %u", window->lowLimit);
     }
@@ -1286,7 +1392,7 @@ MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
 /**
  * Returns the lowest allowed match index. It may either be in the ext-dict or the prefix.
  */
-MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog)
+MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_MatchState_t* ms, U32 curr, unsigned windowLog)
 {
     U32 const maxDistance = 1U << windowLog;
     U32 const lowestValid = ms->window.lowLimit;
@@ -1303,7 +1409,7 @@ MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_matchState_t* ms, U32 curr, u
 /**
  * Returns the lowest allowed match index in the prefix.
  */
-MEM_STATIC U32 ZSTD_getLowestPrefixIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog)
+MEM_STATIC U32 ZSTD_getLowestPrefixIndex(const ZSTD_MatchState_t* ms, U32 curr, unsigned windowLog)
 {
     U32    const maxDistance = 1U << windowLog;
     U32    const lowestValid = ms->window.dictLimit;
@@ -1316,6 +1422,13 @@ MEM_STATIC U32 ZSTD_getLowestPrefixIndex(const ZSTD_matchState_t* ms, U32 curr,
     return matchLowest;
 }
 
+/* index_safety_check:
+ * intentional underflow : ensure repIndex isn't overlapping dict + prefix
+ * @return 1 if values are not overlapping,
+ * 0 otherwise */
+MEM_STATIC int ZSTD_index_overlap_check(const U32 prefixLowestIndex, const U32 repIndex) {
+    return ((U32)((prefixLowestIndex-1)  - repIndex) >= 3);
+}
 
 
 /* debug functions */
@@ -1386,10 +1499,6 @@ MEM_STATIC int ZSTD_comparePackedTags(size_t packedTag1, size_t packedTag2) {
     return tag1 == tag2;
 }
 
-#if defined (__cplusplus)
-}
-#endif
-
 /* ===============================================================
  * Shared internal declarations
  * These prototypes may be called from sources not in lib/compress
@@ -1405,6 +1514,25 @@ size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace,
 
 void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs);
 
+typedef struct {
+    U32 idx;            /* Index in array of ZSTD_Sequence */
+    U32 posInSequence;  /* Position within sequence at idx */
+    size_t posInSrc;    /* Number of bytes given by sequences provided so far */
+} ZSTD_SequencePosition;
+
+/* for benchmark */
+size_t ZSTD_convertBlockSequences(ZSTD_CCtx* cctx,
+                        const ZSTD_Sequence* const inSeqs, size_t nbSequences,
+                        int const repcodeResolution);
+
+typedef struct {
+    size_t nbSequences;
+    size_t blockSize;
+    size_t litSize;
+} BlockSummary;
+
+BlockSummary ZSTD_get1BlockSummary(const ZSTD_Sequence* seqs, size_t nbSeqs);
+
 /* ==============================================================
  * Private declarations
  * These prototypes shall only be called from within lib/compress
@@ -1416,7 +1544,7 @@ void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs);
  * Note: srcSizeHint == 0 means 0!
  */
 ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams(
-        const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode);
+        const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_CParamMode_e mode);
 
 /*! ZSTD_initCStream_internal() :
  *  Private use only. Init streaming operation.
@@ -1428,7 +1556,7 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
                      const ZSTD_CDict* cdict,
                      const ZSTD_CCtx_params* params, unsigned long long pledgedSrcSize);
 
-void ZSTD_resetSeqStore(seqStore_t* ssPtr);
+void ZSTD_resetSeqStore(SeqStore_t* ssPtr);
 
 /*! ZSTD_getCParamsFromCDict() :
  *  as the name implies */
@@ -1467,11 +1595,10 @@ size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity);
  * This cannot be used when long range matching is enabled.
  * Zstd will use these sequences, and pass the literals to a secondary block
  * compressor.
- * @return : An error code on failure.
  * NOTE: seqs are not verified! Invalid sequences can cause out-of-bounds memory
  * access and data corruption.
  */
-size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq);
+void ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq);
 
 /** ZSTD_cycleLog() :
  *  condition for correct operation : hashLog > 1 */
@@ -1482,33 +1609,10 @@ U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat);
  */
 void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize);
 
-/* Returns 0 on success, and a ZSTD_error otherwise. This function scans through an array of
- * ZSTD_Sequence, storing the sequences it finds, until it reaches a block delimiter.
- * Note that the block delimiter must include the last literals of the block.
- */
-size_t
-ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx,
-                                              ZSTD_sequencePosition* seqPos,
-                                        const ZSTD_Sequence* const inSeqs, size_t inSeqsSize,
-                                        const void* src, size_t blockSize, ZSTD_paramSwitch_e externalRepSearch);
-
-/* Returns the number of bytes to move the current read position back by.
- * Only non-zero if we ended up splitting a sequence.
- * Otherwise, it may return a ZSTD error if something went wrong.
- *
- * This function will attempt to scan through blockSize bytes
- * represented by the sequences in @inSeqs,
- * storing any (partial) sequences.
- *
- * Occasionally, we may want to change the actual number of bytes we consumed from inSeqs to
- * avoid splitting a match, or to avoid splitting a match such that it would produce a match
- * smaller than MINMATCH. In this case, we return the number of bytes that we didn't read from this block.
- */
-size_t
-ZSTD_copySequencesToSeqStoreNoBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos,
-                                   const ZSTD_Sequence* const inSeqs, size_t inSeqsSize,
-                                   const void* src, size_t blockSize, ZSTD_paramSwitch_e externalRepSearch);
-
+/* Returns 1 if an external sequence producer is registered, otherwise returns 0. */
+MEM_STATIC int ZSTD_hasExtSeqProd(const ZSTD_CCtx_params* params) {
+    return params->extSeqProdFunc != NULL;
+}
 
 /* ===============================================================
  * Deprecated definitions that are still used internally to avoid

zstd.mod/zstd/lib/compress/zstd_compress_literals.c

@@ -140,7 +140,7 @@ size_t ZSTD_compressLiterals (
     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;
+    SymbolEncodingType_e hType = set_compressed;
     size_t cLitSize;
 
     DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i, srcSize=%u, dstCapacity=%zu)",

zstd.mod/zstd/lib/compress/zstd_compress_sequences.c

@@ -153,13 +153,13 @@ size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
     return cost >> 8;
 }
 
-symbolEncodingType_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_DefaultPolicy_e const isDefaultAllowed,
         ZSTD_strategy const strategy)
 {
     ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
@@ -241,7 +241,7 @@ typedef struct {
 
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                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,
@@ -293,7 +293,7 @@ ZSTD_encodeSequences_body(
             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)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     BIT_CStream_t blockStream;
     FSE_CState_t  stateMatchLength;
@@ -387,7 +387,7 @@ ZSTD_encodeSequences_default(
             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)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -405,7 +405,7 @@ ZSTD_encodeSequences_bmi2(
             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)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -421,7 +421,7 @@ size_t ZSTD_encodeSequences(
             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)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
 {
     DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
 #if DYNAMIC_BMI2

zstd.mod/zstd/lib/compress/zstd_compress_sequences.h

@@ -11,26 +11,27 @@
 #ifndef ZSTD_COMPRESS_SEQUENCES_H
 #define ZSTD_COMPRESS_SEQUENCES_H
 
+#include "zstd_compress_internal.h" /* SeqDef */
 #include "../common/fse.h" /* FSE_repeat, FSE_CTable */
-#include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+#include "../common/zstd_internal.h" /* SymbolEncodingType_e, ZSTD_strategy */
 
 typedef enum {
     ZSTD_defaultDisallowed = 0,
     ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
+} ZSTD_DefaultPolicy_e;
 
-symbolEncodingType_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_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,
+                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,
@@ -42,7 +43,7 @@ size_t ZSTD_encodeSequences(
             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);
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
 
 size_t ZSTD_fseBitCost(
     FSE_CTable const* ctable,

zstd.mod/zstd/lib/compress/zstd_compress_superblock.c

@@ -51,7 +51,7 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     BYTE* const oend = ostart + dstSize;
     BYTE* op = ostart + lhSize;
     U32 const singleStream = lhSize == 3;
-    symbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat;
+    SymbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat;
     size_t cLitSize = 0;
 
     DEBUGLOG(5, "ZSTD_compressSubBlock_literal (litSize=%zu, lhSize=%zu, writeEntropy=%d)", litSize, lhSize, writeEntropy);
@@ -76,8 +76,8 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     }
 
     {   int const flags = bmi2 ? HUF_flags_bmi2 : 0;
-        const size_t cSize = singleStream ? HUF_compress1X_usingCTable(op, oend-op, literals, litSize, hufTable, flags)
-                                          : HUF_compress4X_usingCTable(op, oend-op, literals, litSize, hufTable, flags);
+        const size_t cSize = singleStream ? HUF_compress1X_usingCTable(op, (size_t)(oend-op), literals, litSize, hufTable, flags)
+                                          : HUF_compress4X_usingCTable(op, (size_t)(oend-op), literals, litSize, hufTable, flags);
         op += cSize;
         cLitSize += cSize;
         if (cSize == 0 || ERR_isError(cSize)) {
@@ -102,7 +102,7 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     switch(lhSize)
     {
     case 3: /* 2 - 2 - 10 - 10 */
-        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<14);
+        {   U32 const lhc = hType + ((U32)(!singleStream) << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<14);
             MEM_writeLE24(ostart, lhc);
             break;
         }
@@ -122,30 +122,30 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     }
     *entropyWritten = 1;
     DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)litSize, (U32)(op-ostart));
-    return op-ostart;
+    return (size_t)(op-ostart);
 }
 
 static size_t
-ZSTD_seqDecompressedSize(seqStore_t const* seqStore,
-                   const seqDef* sequences, size_t nbSeq,
-                         size_t litSize, int lastSequence)
+ZSTD_seqDecompressedSize(SeqStore_t const* seqStore,
+                   const SeqDef* sequences, size_t nbSeqs,
+                         size_t litSize, int lastSubBlock)
 {
-    const seqDef* const sstart = sequences;
-    const seqDef* const send = sequences + nbSeq;
-    const seqDef* sp = sstart;
     size_t matchLengthSum = 0;
     size_t litLengthSum = 0;
-    (void)(litLengthSum); /* suppress unused variable warning on some environments */
-    while (send-sp > 0) {
-        ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp);
+    size_t n;
+    for (n=0; n<nbSeqs; n++) {
+        const ZSTD_SequenceLength seqLen = ZSTD_getSequenceLength(seqStore, sequences+n);
         litLengthSum += seqLen.litLength;
         matchLengthSum += seqLen.matchLength;
-        sp++;
     }
-    assert(litLengthSum <= litSize);
-    if (!lastSequence) {
+    DEBUGLOG(5, "ZSTD_seqDecompressedSize: %u sequences from %p: %u literals + %u matchlength",
+                (unsigned)nbSeqs, (const void*)sequences,
+                (unsigned)litLengthSum, (unsigned)matchLengthSum);
+    if (!lastSubBlock)
         assert(litLengthSum == litSize);
-    }
+    else
+        assert(litLengthSum <= litSize);
+    (void)litLengthSum;
     return matchLengthSum + litSize;
 }
 
@@ -162,7 +162,7 @@ ZSTD_seqDecompressedSize(seqStore_t const* seqStore,
 static size_t
 ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
                                 const ZSTD_fseCTablesMetadata_t* fseMetadata,
-                                const seqDef* sequences, size_t nbSeq,
+                                const SeqDef* sequences, size_t nbSeq,
                                 const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
                                 const ZSTD_CCtx_params* cctxParams,
                                 void* dst, size_t dstCapacity,
@@ -180,14 +180,14 @@ ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
     /* Sequences Header */
     RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
                     dstSize_tooSmall, "");
-    if (nbSeq < 0x7F)
+    if (nbSeq < 128)
         *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;
     if (nbSeq==0) {
-        return op - ostart;
+        return (size_t)(op - ostart);
     }
 
     /* seqHead : flags for FSE encoding type */
@@ -209,7 +209,7 @@ ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
     }
 
     {   size_t const bitstreamSize = ZSTD_encodeSequences(
-                                        op, oend - op,
+                                        op, (size_t)(oend - op),
                                         fseTables->matchlengthCTable, mlCode,
                                         fseTables->offcodeCTable, ofCode,
                                         fseTables->litlengthCTable, llCode,
@@ -253,7 +253,7 @@ ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
 #endif
 
     *entropyWritten = 1;
-    return op - ostart;
+    return (size_t)(op - ostart);
 }
 
 /** ZSTD_compressSubBlock() :
@@ -262,7 +262,7 @@ ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
  *            Or 0 if it failed to compress. */
 static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy,
                                     const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
-                                    const seqDef* sequences, size_t nbSeq,
+                                    const SeqDef* sequences, size_t nbSeq,
                                     const BYTE* literals, size_t litSize,
                                     const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
                                     const ZSTD_CCtx_params* cctxParams,
@@ -279,7 +279,8 @@ static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy,
                 litSize, nbSeq, writeLitEntropy, writeSeqEntropy, lastBlock);
     {   size_t cLitSize = ZSTD_compressSubBlock_literal((const HUF_CElt*)entropy->huf.CTable,
                                                         &entropyMetadata->hufMetadata, literals, litSize,
-                                                        op, oend-op, bmi2, writeLitEntropy, litEntropyWritten);
+                                                        op, (size_t)(oend-op),
+                                                        bmi2, writeLitEntropy, litEntropyWritten);
         FORWARD_IF_ERROR(cLitSize, "ZSTD_compressSubBlock_literal failed");
         if (cLitSize == 0) return 0;
         op += cLitSize;
@@ -289,18 +290,18 @@ static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy,
                                                   sequences, nbSeq,
                                                   llCode, mlCode, ofCode,
                                                   cctxParams,
-                                                  op, oend-op,
+                                                  op, (size_t)(oend-op),
                                                   bmi2, writeSeqEntropy, seqEntropyWritten);
         FORWARD_IF_ERROR(cSeqSize, "ZSTD_compressSubBlock_sequences failed");
         if (cSeqSize == 0) return 0;
         op += cSeqSize;
     }
     /* Write block header */
-    {   size_t cSize = (op-ostart)-ZSTD_blockHeaderSize;
+    {   size_t cSize = (size_t)(op-ostart) - ZSTD_blockHeaderSize;
         U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3);
         MEM_writeLE24(ostart, cBlockHeader24);
     }
-    return op-ostart;
+    return (size_t)(op-ostart);
 }
 
 static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t litSize,
@@ -326,7 +327,7 @@ static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t lit
     return 0;
 }
 
-static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type,
+static size_t ZSTD_estimateSubBlockSize_symbolType(SymbolEncodingType_e type,
                         const BYTE* codeTable, unsigned maxCode,
                         size_t nbSeq, const FSE_CTable* fseCTable,
                         const U8* additionalBits,
@@ -389,7 +390,11 @@ static size_t ZSTD_estimateSubBlockSize_sequences(const BYTE* ofCodeTable,
     return cSeqSizeEstimate + sequencesSectionHeaderSize;
 }
 
-static size_t ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize,
+typedef struct {
+    size_t estLitSize;
+    size_t estBlockSize;
+} EstimatedBlockSize;
+static EstimatedBlockSize ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize,
                                         const BYTE* ofCodeTable,
                                         const BYTE* llCodeTable,
                                         const BYTE* mlCodeTable,
@@ -397,15 +402,17 @@ static size_t ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize,
                                         const ZSTD_entropyCTables_t* entropy,
                                         const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
                                         void* workspace, size_t wkspSize,
-                                        int writeLitEntropy, int writeSeqEntropy) {
-    size_t cSizeEstimate = 0;
-    cSizeEstimate += ZSTD_estimateSubBlockSize_literal(literals, litSize,
-                                                         &entropy->huf, &entropyMetadata->hufMetadata,
-                                                         workspace, wkspSize, writeLitEntropy);
-    cSizeEstimate += ZSTD_estimateSubBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable,
+                                        int writeLitEntropy, int writeSeqEntropy)
+{
+    EstimatedBlockSize ebs;
+    ebs.estLitSize = ZSTD_estimateSubBlockSize_literal(literals, litSize,
+                                                        &entropy->huf, &entropyMetadata->hufMetadata,
+                                                        workspace, wkspSize, writeLitEntropy);
+    ebs.estBlockSize = ZSTD_estimateSubBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable,
                                                          nbSeq, &entropy->fse, &entropyMetadata->fseMetadata,
                                                          workspace, wkspSize, writeSeqEntropy);
-    return cSizeEstimate + ZSTD_blockHeaderSize;
+    ebs.estBlockSize += ebs.estLitSize + ZSTD_blockHeaderSize;
+    return ebs;
 }
 
 static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMetadata)
@@ -419,14 +426,57 @@ static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMe
     return 0;
 }
 
+static size_t countLiterals(SeqStore_t const* seqStore, const SeqDef* sp, size_t seqCount)
+{
+    size_t n, total = 0;
+    assert(sp != NULL);
+    for (n=0; n<seqCount; n++) {
+        total += ZSTD_getSequenceLength(seqStore, sp+n).litLength;
+    }
+    DEBUGLOG(6, "countLiterals for %zu sequences from %p => %zu bytes", seqCount, (const void*)sp, total);
+    return total;
+}
+
+#define BYTESCALE 256
+
+static size_t sizeBlockSequences(const SeqDef* sp, size_t nbSeqs,
+                size_t targetBudget, size_t avgLitCost, size_t avgSeqCost,
+                int firstSubBlock)
+{
+    size_t n, budget = 0, inSize=0;
+    /* entropy headers */
+    size_t const headerSize = (size_t)firstSubBlock * 120 * BYTESCALE; /* generous estimate */
+    assert(firstSubBlock==0 || firstSubBlock==1);
+    budget += headerSize;
+
+    /* first sequence => at least one sequence*/
+    budget += sp[0].litLength * avgLitCost + avgSeqCost;
+    if (budget > targetBudget) return 1;
+    inSize = sp[0].litLength + (sp[0].mlBase+MINMATCH);
+
+    /* loop over sequences */
+    for (n=1; n<nbSeqs; n++) {
+        size_t currentCost = sp[n].litLength * avgLitCost + avgSeqCost;
+        budget += currentCost;
+        inSize += sp[n].litLength + (sp[n].mlBase+MINMATCH);
+        /* stop when sub-block budget is reached */
+        if ( (budget > targetBudget)
+            /* though continue to expand until the sub-block is deemed compressible */
+          && (budget < inSize * BYTESCALE) )
+            break;
+    }
+
+    return n;
+}
+
 /** ZSTD_compressSubBlock_multi() :
  *  Breaks super-block into multiple sub-blocks and compresses them.
- *  Entropy will be written to the first block.
- *  The following blocks will use repeat mode to compress.
- *  All sub-blocks are compressed blocks (no raw or rle blocks).
- *  @return : compressed size of the super block (which is multiple ZSTD blocks)
- *            Or 0 if it failed to compress. */
-static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
+ *  Entropy will be written into the first block.
+ *  The following blocks use repeat_mode to compress.
+ *  Sub-blocks are all compressed, except the last one when beneficial.
+ *  @return : compressed size of the super block (which features multiple ZSTD blocks)
+ *            or 0 if it failed to compress. */
+static size_t ZSTD_compressSubBlock_multi(const SeqStore_t* seqStorePtr,
                             const ZSTD_compressedBlockState_t* prevCBlock,
                             ZSTD_compressedBlockState_t* nextCBlock,
                             const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
@@ -436,12 +486,14 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
                             const int bmi2, U32 lastBlock,
                             void* workspace, size_t wkspSize)
 {
-    const seqDef* const sstart = seqStorePtr->sequencesStart;
-    const seqDef* const send = seqStorePtr->sequences;
-    const seqDef* sp = sstart;
+    const SeqDef* const sstart = seqStorePtr->sequencesStart;
+    const SeqDef* const send = seqStorePtr->sequences;
+    const SeqDef* sp = sstart; /* tracks progresses within seqStorePtr->sequences */
+    size_t const nbSeqs = (size_t)(send - sstart);
     const BYTE* const lstart = seqStorePtr->litStart;
     const BYTE* const lend = seqStorePtr->lit;
     const BYTE* lp = lstart;
+    size_t const nbLiterals = (size_t)(lend - lstart);
     BYTE const* ip = (BYTE const*)src;
     BYTE const* const iend = ip + srcSize;
     BYTE* const ostart = (BYTE*)dst;
@@ -450,97 +502,153 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
     const BYTE* llCodePtr = seqStorePtr->llCode;
     const BYTE* mlCodePtr = seqStorePtr->mlCode;
     const BYTE* ofCodePtr = seqStorePtr->ofCode;
-    size_t targetCBlockSize = cctxParams->targetCBlockSize;
-    size_t litSize, seqCount;
-    int writeLitEntropy = entropyMetadata->hufMetadata.hType == set_compressed;
+    size_t const minTarget = ZSTD_TARGETCBLOCKSIZE_MIN; /* enforce minimum size, to reduce undesirable side effects */
+    size_t const targetCBlockSize = MAX(minTarget, cctxParams->targetCBlockSize);
+    int writeLitEntropy = (entropyMetadata->hufMetadata.hType == set_compressed);
     int writeSeqEntropy = 1;
-    int lastSequence = 0;
-
-    DEBUGLOG(5, "ZSTD_compressSubBlock_multi (litSize=%u, nbSeq=%u)",
-                (unsigned)(lend-lp), (unsigned)(send-sstart));
-
-    litSize = 0;
-    seqCount = 0;
-    do {
-        size_t cBlockSizeEstimate = 0;
-        if (sstart == send) {
-            lastSequence = 1;
-        } else {
-            const seqDef* const sequence = sp + seqCount;
-            lastSequence = sequence == send - 1;
-            litSize += ZSTD_getSequenceLength(seqStorePtr, sequence).litLength;
-            seqCount++;
-        }
-        if (lastSequence) {
-            assert(lp <= lend);
-            assert(litSize <= (size_t)(lend - lp));
-            litSize = (size_t)(lend - lp);
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_multi (srcSize=%u, litSize=%u, nbSeq=%u)",
+               (unsigned)srcSize, (unsigned)(lend-lstart), (unsigned)(send-sstart));
+
+        /* let's start by a general estimation for the full block */
+    if (nbSeqs > 0) {
+        EstimatedBlockSize const ebs =
+                ZSTD_estimateSubBlockSize(lp, nbLiterals,
+                                        ofCodePtr, llCodePtr, mlCodePtr, nbSeqs,
+                                        &nextCBlock->entropy, entropyMetadata,
+                                        workspace, wkspSize,
+                                        writeLitEntropy, writeSeqEntropy);
+        /* quick estimation */
+        size_t const avgLitCost = nbLiterals ? (ebs.estLitSize * BYTESCALE) / nbLiterals : BYTESCALE;
+        size_t const avgSeqCost = ((ebs.estBlockSize - ebs.estLitSize) * BYTESCALE) / nbSeqs;
+        const size_t nbSubBlocks = MAX((ebs.estBlockSize + (targetCBlockSize/2)) / targetCBlockSize, 1);
+        size_t n, avgBlockBudget, blockBudgetSupp=0;
+        avgBlockBudget = (ebs.estBlockSize * BYTESCALE) / nbSubBlocks;
+        DEBUGLOG(5, "estimated fullblock size=%u bytes ; avgLitCost=%.2f ; avgSeqCost=%.2f ; targetCBlockSize=%u, nbSubBlocks=%u ; avgBlockBudget=%.0f bytes",
+                    (unsigned)ebs.estBlockSize, (double)avgLitCost/BYTESCALE, (double)avgSeqCost/BYTESCALE,
+                    (unsigned)targetCBlockSize, (unsigned)nbSubBlocks, (double)avgBlockBudget/BYTESCALE);
+        /* simplification: if estimates states that the full superblock doesn't compress, just bail out immediately
+         * this will result in the production of a single uncompressed block covering @srcSize.*/
+        if (ebs.estBlockSize > srcSize) return 0;
+
+        /* compress and write sub-blocks */
+        assert(nbSubBlocks>0);
+        for (n=0; n < nbSubBlocks-1; n++) {
+            /* determine nb of sequences for current sub-block + nbLiterals from next sequence */
+            size_t const seqCount = sizeBlockSequences(sp, (size_t)(send-sp),
+                                        avgBlockBudget + blockBudgetSupp, avgLitCost, avgSeqCost, n==0);
+            /* if reached last sequence : break to last sub-block (simplification) */
+            assert(seqCount <= (size_t)(send-sp));
+            if (sp + seqCount == send) break;
+            assert(seqCount > 0);
+            /* compress sub-block */
+            {   int litEntropyWritten = 0;
+                int seqEntropyWritten = 0;
+                size_t litSize = countLiterals(seqStorePtr, sp, seqCount);
+                const size_t decompressedSize =
+                        ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, 0);
+                size_t const cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata,
+                                                sp, seqCount,
+                                                lp, litSize,
+                                                llCodePtr, mlCodePtr, ofCodePtr,
+                                                cctxParams,
+                                                op, (size_t)(oend-op),
+                                                bmi2, writeLitEntropy, writeSeqEntropy,
+                                                &litEntropyWritten, &seqEntropyWritten,
+                                                0);
+                FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed");
+
+                /* check compressibility, update state components */
+                if (cSize > 0 && cSize < decompressedSize) {
+                    DEBUGLOG(5, "Committed sub-block compressing %u bytes => %u bytes",
+                                (unsigned)decompressedSize, (unsigned)cSize);
+                    assert(ip + decompressedSize <= iend);
+                    ip += decompressedSize;
+                    lp += litSize;
+                    op += cSize;
+                    llCodePtr += seqCount;
+                    mlCodePtr += seqCount;
+                    ofCodePtr += seqCount;
+                    /* Entropy only needs to be written once */
+                    if (litEntropyWritten) {
+                        writeLitEntropy = 0;
+                    }
+                    if (seqEntropyWritten) {
+                        writeSeqEntropy = 0;
+                    }
+                    sp += seqCount;
+                    blockBudgetSupp = 0;
+            }   }
+            /* otherwise : do not compress yet, coalesce current sub-block with following one */
         }
-        /* I think there is an optimization opportunity here.
-         * Calling ZSTD_estimateSubBlockSize for every sequence can be wasteful
-         * since it recalculates estimate from scratch.
-         * For example, it would recount literal distribution and symbol codes every time.
-         */
-        cBlockSizeEstimate = ZSTD_estimateSubBlockSize(lp, litSize, ofCodePtr, llCodePtr, mlCodePtr, seqCount,
-                                                       &nextCBlock->entropy, entropyMetadata,
-                                                       workspace, wkspSize, writeLitEntropy, writeSeqEntropy);
-        if (cBlockSizeEstimate > targetCBlockSize || lastSequence) {
-            int litEntropyWritten = 0;
-            int seqEntropyWritten = 0;
-            const size_t decompressedSize = ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, lastSequence);
-            const size_t cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata,
-                                                       sp, seqCount,
-                                                       lp, litSize,
-                                                       llCodePtr, mlCodePtr, ofCodePtr,
-                                                       cctxParams,
-                                                       op, oend-op,
-                                                       bmi2, writeLitEntropy, writeSeqEntropy,
-                                                       &litEntropyWritten, &seqEntropyWritten,
-                                                       lastBlock && lastSequence);
-            FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed");
-            if (cSize > 0 && cSize < decompressedSize) {
-                DEBUGLOG(5, "Committed the sub-block");
-                assert(ip + decompressedSize <= iend);
-                ip += decompressedSize;
-                sp += seqCount;
-                lp += litSize;
-                op += cSize;
-                llCodePtr += seqCount;
-                mlCodePtr += seqCount;
-                ofCodePtr += seqCount;
-                litSize = 0;
-                seqCount = 0;
-                /* Entropy only needs to be written once */
-                if (litEntropyWritten) {
-                    writeLitEntropy = 0;
-                }
-                if (seqEntropyWritten) {
-                    writeSeqEntropy = 0;
-                }
+    } /* if (nbSeqs > 0) */
+
+    /* write last block */
+    DEBUGLOG(5, "Generate last sub-block: %u sequences remaining", (unsigned)(send - sp));
+    {   int litEntropyWritten = 0;
+        int seqEntropyWritten = 0;
+        size_t litSize = (size_t)(lend - lp);
+        size_t seqCount = (size_t)(send - sp);
+        const size_t decompressedSize =
+                ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, 1);
+        size_t const cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata,
+                                            sp, seqCount,
+                                            lp, litSize,
+                                            llCodePtr, mlCodePtr, ofCodePtr,
+                                            cctxParams,
+                                            op, (size_t)(oend-op),
+                                            bmi2, writeLitEntropy, writeSeqEntropy,
+                                            &litEntropyWritten, &seqEntropyWritten,
+                                            lastBlock);
+        FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed");
+
+        /* update pointers, the nb of literals borrowed from next sequence must be preserved */
+        if (cSize > 0 && cSize < decompressedSize) {
+            DEBUGLOG(5, "Last sub-block compressed %u bytes => %u bytes",
+                        (unsigned)decompressedSize, (unsigned)cSize);
+            assert(ip + decompressedSize <= iend);
+            ip += decompressedSize;
+            lp += litSize;
+            op += cSize;
+            llCodePtr += seqCount;
+            mlCodePtr += seqCount;
+            ofCodePtr += seqCount;
+            /* Entropy only needs to be written once */
+            if (litEntropyWritten) {
+                writeLitEntropy = 0;
+            }
+            if (seqEntropyWritten) {
+                writeSeqEntropy = 0;
             }
+            sp += seqCount;
         }
-    } while (!lastSequence);
+    }
+
+
     if (writeLitEntropy) {
-        DEBUGLOG(5, "ZSTD_compressSubBlock_multi has literal entropy tables unwritten");
+        DEBUGLOG(5, "Literal entropy tables were never written");
         ZSTD_memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf));
     }
     if (writeSeqEntropy && ZSTD_needSequenceEntropyTables(&entropyMetadata->fseMetadata)) {
         /* If we haven't written our entropy tables, then we've violated our contract and
          * must emit an uncompressed block.
          */
-        DEBUGLOG(5, "ZSTD_compressSubBlock_multi has sequence entropy tables unwritten");
+        DEBUGLOG(5, "Sequence entropy tables were never written => cancel, emit an uncompressed block");
         return 0;
     }
+
     if (ip < iend) {
-        size_t const cSize = ZSTD_noCompressBlock(op, oend - op, ip, iend - ip, lastBlock);
-        DEBUGLOG(5, "ZSTD_compressSubBlock_multi last sub-block uncompressed, %zu bytes", (size_t)(iend - ip));
+        /* some data left : last part of the block sent uncompressed */
+        size_t const rSize = (size_t)((iend - ip));
+        size_t const cSize = ZSTD_noCompressBlock(op, (size_t)(oend - op), ip, rSize, lastBlock);
+        DEBUGLOG(5, "Generate last uncompressed sub-block of %u bytes", (unsigned)(rSize));
         FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed");
         assert(cSize != 0);
         op += cSize;
         /* We have to regenerate the repcodes because we've skipped some sequences */
         if (sp < send) {
-            seqDef const* seq;
-            repcodes_t rep;
+            const SeqDef* seq;
+            Repcodes_t rep;
             ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep));
             for (seq = sstart; seq < sp; ++seq) {
                 ZSTD_updateRep(rep.rep, seq->offBase, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0);
@@ -548,14 +656,17 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
             ZSTD_memcpy(nextCBlock->rep, &rep, sizeof(rep));
         }
     }
-    DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed");
-    return op-ostart;
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed all subBlocks: total compressed size = %u",
+                (unsigned)(op-ostart));
+    return (size_t)(op-ostart);
 }
 
 size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
                                void* dst, size_t dstCapacity,
-                               void const* src, size_t srcSize,
-                               unsigned lastBlock) {
+                               const void* src, size_t srcSize,
+                               unsigned lastBlock)
+{
     ZSTD_entropyCTablesMetadata_t entropyMetadata;
 
     FORWARD_IF_ERROR(ZSTD_buildBlockEntropyStats(&zc->seqStore,
@@ -563,7 +674,7 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
           &zc->blockState.nextCBlock->entropy,
           &zc->appliedParams,
           &entropyMetadata,
-          zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), "");
+          zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */), "");
 
     return ZSTD_compressSubBlock_multi(&zc->seqStore,
             zc->blockState.prevCBlock,
@@ -573,5 +684,5 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
             dst, dstCapacity,
             src, srcSize,
             zc->bmi2, lastBlock,
-            zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */);
+            zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */);
 }