diff --git a/CHANGELOG b/CHANGELOG
new file mode 100644
index 000000000000..bf04a8a131c0
--- /dev/null
+++ b/CHANGELOG
@@ -0,0 +1,461 @@
+v1.4.0
+perf: Improve level 1 compression speed in most scenarios by 6% by @gbtucker and @terrelln
+api: Move the advanced API, including all functions in the staging section, to the stable section
+api: Make ZSTD_e_flush and ZSTD_e_end block for maximum forward progress
+api: Rename ZSTD_CCtxParam_getParameter to ZSTD_CCtxParams_getParameter
+api: Rename ZSTD_CCtxParam_setParameter to ZSTD_CCtxParams_setParameter
+api: Don't export ZSTDMT functions from the shared library by default
+api: Require ZSTD_MULTITHREAD to be defined to use ZSTDMT
+api: Add ZSTD_decompressBound() to provide an upper bound on decompressed size by @shakeelrao
+api: Fix ZSTD_decompressDCtx() corner cases with a dictionary
+api: Move ZSTD_getDictID_*() functions to the stable section
+api: Add ZSTD_c_literalCompressionMode flag to enable or disable literal compression by @terrelln
+api: Allow compression parameters to be set when a dictionary is used
+api: Allow setting parameters before or after ZSTD_CCtx_loadDictionary() is called
+api: Fix ZSTD_estimateCStreamSize_usingCCtxParams()
+api: Setting ZSTD_d_maxWindowLog to 0 means use the default
+cli: Ensure that a dictionary is not used to compress itself by @shakeelrao
+cli: Add --[no-]compress-literals flag to enable or disable literal compression
+doc: Update the examples to use the advanced API
+doc: Explain how to transition from old streaming functions to the advanced API in the header
+build: Improve the Windows release packages
+build: Improve CMake build by @hjmjohnson
+build: Build fixes for FreeBSD by @lwhsu
+build: Remove redundant warnings by @thatsafunnyname
+build: Fix tests on OpenBSD by @bket
+build: Extend fuzzer build system to work with the new clang engine
+build: CMake now creates the libzstd.so.1 symlink
+build: Improve Menson build by @lzutao
+misc: Fix symbolic link detection on FreeBSD
+misc: Use physical core count for -T0 on FreeBSD by @cemeyer
+misc: Fix zstd --list on truncated files by @kostmo
+misc: Improve logging in debug mode by @felixhandte
+misc: Add CirrusCI tests by @lwhsu
+misc: Optimize dictionary memory usage in corner cases
+misc: Improve the dictionary builder on small or homogeneous data
+misc: Fix spelling across the repo by @jsoref
+
+v1.3.8
+perf: better decompression speed on large files (+7%) and cold dictionaries (+15%)
+perf: slightly better compression ratio at high compression modes
+api : finalized advanced API, last stage before "stable" status
+api : new --rsyncable mode, by @terrelln
+api : support decompression of empty frames into NULL (used to be an error) (#1385)
+build: new set of macros to build a minimal size decoder, by @felixhandte
+build: fix compilation on MIPS32, reported by @clbr (#1441)
+build: fix compilation with multiple -arch flags, by @ryandesign
+build: highly upgraded meson build, by @lzutao
+build: improved buck support, by @obelisk
+build: fix cmake script : can create debug build, by @pitrou
+build: Makefile : grep works on both colored consoles and systems without color support
+build: fixed zstd-pgo, by @bmwiedemann
+cli : support ZSTD_CLEVEL environment variable, by @yijinfb (#1423)
+cli : --no-progress flag, preserving final summary (#1371), by @terrelln
+cli : ensure destination file is not source file (#1422)
+cli : clearer error messages, especially when input file not present
+doc : clarified zstd_compression_format.md, by @ulikunitz
+misc: fixed zstdgrep, returns 1 on failure, by @lzutao
+misc: NEWS renamed as CHANGELOG, in accordance with fboss
+
+v1.3.7
+perf: slightly better decompression speed on clang (depending on hardware target)
+fix : performance of dictionary compression for small input < 4 KB at levels 9 and 10
+build: no longer build backtrace by default in release mode; restrict further automatic mode
+build: control backtrace support through build macro BACKTRACE
+misc: added man pages for zstdless and zstdgrep, by @samrussell
+
+v1.3.6
+perf: much faster dictionary builder, by @jenniferliu
+perf: faster dictionary compression on small data when using multiple contexts, by @felixhandte
+perf: faster dictionary decompression when using a very large number of dictionaries simultaneously
+cli : fix : does no longer overwrite destination when source does not exist (#1082)
+cli : new command --adapt, for automatic compression level adaptation
+api : fix : block api can be streamed with > 4 GB, reported by @catid
+api : reduced ZSTD_DDict size by 2 KB
+api : minimum negative compression level is defined, and can be queried using ZSTD_minCLevel().
+build: support Haiku target, by @korli
+build: Read Legacy format is limited to v0.5+ by default. Can be changed at compile time with macro ZSTD_LEGACY_SUPPORT.
+doc : zstd_compression_format.md updated to match wording in IETF RFC 8478
+misc: tests/paramgrill, a parameter optimizer, by @GeorgeLu97
+
+v1.3.5
+perf: much faster dictionary compression, by @felixhandte
+perf: small quality improvement for dictionary generation, by @terrelln
+perf: slightly improved high compression levels (notably level 19)
+mem : automatic memory release for long duration contexts
+cli : fix : overlapLog can be manually set
+cli : fix : decoding invalid lz4 frames
+api : fix : performance degradation for dictionary compression when using advanced API, by @terrelln
+api : change : clarify ZSTD_CCtx_reset() vs ZSTD_CCtx_resetParameters(), by @terrelln
+build: select custom libzstd scope through control macros, by @GeorgeLu97
+build: OpenBSD patch, by @bket
+build: make and make all are compatible with -j
+doc : clarify zstd_compression_format.md, updated for IETF RFC process
+misc: pzstd compatible with reproducible compilation, by @lamby
+
+v1.3.4
+perf: faster speed (especially decoding speed) on recent cpus (haswell+)
+perf: much better performance associating --long with multi-threading, by @terrelln
+perf: better compression at levels 13-15
+cli : asynchronous compression by default, for faster experience (use --single-thread for former behavior)
+cli : smoother status report in multi-threading mode
+cli : added command --fast=#, for faster compression modes
+cli : fix crash when not overwriting existing files, by Pádraig Brady (@pixelb)
+api : `nbThreads` becomes `nbWorkers` : 1 triggers asynchronous mode
+api : compression levels can be negative, for even more speed
+api : ZSTD_getFrameProgression() : get precise progress status of ZSTDMT anytime
+api : ZSTDMT can accept new compression parameters during compression
+api : implemented all advanced dictionary decompression prototypes
+build: improved meson recipe, by Shawn Landden (@shawnl)
+build: VS2017 scripts, by @HaydnTrigg
+misc: all /contrib projects fixed
+misc: added /contrib/docker script by @gyscos
+
+v1.3.3
+perf: faster zstd_opt strategy (levels 16-19)
+fix : bug #944 : multithreading with shared ditionary 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
+api : fix : support large skippable frames, by @terrelln
+api : fix : streaming interface was adding a useless 3-bytes null block to small frames
+api : change : when setting `pledgedSrcSize`, use `ZSTD_CONTENTSIZE_UNKNOWN` macro value to mean "unknown"
+build: fix : compilation under rhel6 and centos6, reported by @pixelb
+build: added `check` target
+
+v1.3.2
+new : long range mode, using --long command, by Stella Lau (@stellamplau)
+new : ability to generate and decode magicless frames (#591)
+changed : maximum nb of threads reduced to 200, to avoid address space exhaustion in 32-bits mode
+fix : multi-threading compression works with custom allocators
+fix : ZSTD_sizeof_CStream() was over-evaluating memory usage
+fix : a rare compression bug when compression generates very large distances and bunch of other conditions (only possible at --ultra -22)
+fix : 32-bits build can now decode large offsets (levels 21+)
+cli : added LZ4 frame support by default, by Felix Handte (@felixhandte)
+cli : improved --list output
+cli : new : can split input file for dictionary training, using command -B#
+cli : new : clean operation artefact on Ctrl-C interruption
+cli : fix : do not change /dev/null permissions when using command -t with root access, reported by @mike155 (#851)
+cli : fix : write file size in header in multiple-files mode
+api : added macro ZSTD_COMPRESSBOUND() for static allocation
+api : experimental : new advanced decompression API
+api : fix : sizeof_CCtx() used to over-estimate
+build: fix : no-multithread variant compiles without pool.c dependency, reported by Mitchell Blank Jr (@mitchblank) (#819)
+build: better compatibility with reproducible builds, by Bernhard M. Wiedemann (@bmwiedemann) (#818)
+example : added streaming_memory_usage
+license : changed /examples license to BSD + GPLv2
+license : fix a few header files to reflect new license (#825)
+
+v1.3.1
+New license : BSD + GPLv2
+perf: substantially decreased memory usage in Multi-threading mode, thanks to reports by Tino Reichardt (@mcmilk)
+perf: Multi-threading supports up to 256 threads. Cap at 256 when more are requested (#760)
+cli : improved and fixed --list command, by @ib (#772)
+cli : command -vV to list supported formats, by @ib (#771)
+build : fixed binary variants, reported by @svenha (#788)
+build : fix Visual compilation for non x86/x64 targets, reported by Greg Slazinski (@GregSlazinski) (#718)
+API exp : breaking change : ZSTD_getframeHeader() provides more information
+API exp : breaking change : pinned down values of error codes
+doc : fixed huffman example, by Ulrich Kunitz (@ulikunitz)
+new : contrib/adaptive-compression, I/O driven compression strength, by Paul Cruz (@paulcruz74)
+new : contrib/long_distance_matching, statistics by Stella Lau (@stellamplau)
+updated : contrib/linux-kernel, by Nick Terrell (@terrelln)
+
+v1.3.0
+cli : new : `--list` command, by Paul Cruz
+cli : changed : xz/lzma support enabled by default
+cli : changed : `-t *` continue processing list after a decompression error
+API : added : ZSTD_versionString()
+API : promoted to stable status : ZSTD_getFrameContentSize(), by Sean Purcell
+API exp : new advanced API : ZSTD_compress_generic(), ZSTD_CCtx_setParameter()
+API exp : new : API for static or external allocation : ZSTD_initStatic?Ctx()
+API exp : added : ZSTD_decompressBegin_usingDDict(), requested by Guy Riddle (#700)
+API exp : clarified memory estimation / measurement functions.
+API exp : changed : strongest strategy renamed ZSTD_btultra, fastest strategy ZSTD_fast set to 1
+tools : decodecorpus can generate random dictionary-compressed samples, by Paul Cruz
+new : contrib/seekable_format, demo and API, by Sean Purcell
+changed : contrib/linux-kernel, updated version and license, by Nick Terrell
+
+v1.2.0
+cli : changed : Multithreading enabled by default (use target zstd-nomt or HAVE_THREAD=0 to disable)
+cli : new : command -T0 means "detect and use nb of cores", by Sean Purcell
+cli : new : zstdmt symlink hardwired to `zstd -T0`
+cli : new : command --threads=# (#671)
+cli : changed : cover dictionary builder by default, for improved quality, by Nick Terrell
+cli : new : commands --train-cover and --train-legacy, to select dictionary algorithm and parameters
+cli : experimental targets `zstd4` and `xzstd4`, with support for lz4 format, by Sean Purcell
+cli : fix : does not output compressed data on console
+cli : fix : ignore symbolic links unless --force specified,
+API : breaking change : ZSTD_createCDict_advanced(), only use compressionParameters as argument
+API : added : prototypes ZSTD_*_usingCDict_advanced(), for direct control over frameParameters.
+API : improved: ZSTDMT_compressCCtx() reduced memory usage
+API : fix : ZSTDMT_compressCCtx() now provides srcSize in header (#634)
+API : fix : src size stored in frame header is controlled at end of frame
+API : fix : enforced consistent rules for pledgedSrcSize==0 (#641)
+API : fix : error code "GENERIC" replaced by "dstSizeTooSmall" when appropriate
+build: improved cmake script, by @Majlen
+build: enabled Multi-threading support for *BSD, by Baptiste Daroussin
+tools: updated Paramgrill. Command -O# provides best parameters for sample and speed target.
+new : contrib/linux-kernel version, by Nick Terrell
+
+v1.1.4
+cli : new : can compress in *.gz format, using --format=gzip command, by Przemyslaw Skibinski
+cli : new : advanced benchmark command --priority=rt
+cli : fix : write on sparse-enabled file systems in 32-bits mode, by @ds77
+cli : fix : --rm remains silent when input is stdin
+cli : experimental : xzstd, with support for xz/lzma decoding, by Przemyslaw Skibinski
+speed : improved decompression speed in streaming mode for single shot scenarios (+5%)
+memory: DDict (decompression dictionary) memory usage down from 150 KB to 20 KB
+arch: 32-bits variant able to generate and decode very long matches (>32 MB), by Sean Purcell
+API : new : ZSTD_findFrameCompressedSize(), ZSTD_getFrameContentSize(), ZSTD_findDecompressedSize()
+API : changed : dropped support of legacy versions <= v0.3 (can be changed by modifying ZSTD_LEGACY_SUPPORT value)
+build : new: meson build system in contrib/meson, by Dima Krasner
+build : improved cmake script, by @Majlen
+build : added -Wformat-security flag, as recommended by Padraig Brady
+doc : new : educational decoder, by Sean Purcell
+
+v1.1.3
+cli : zstd can decompress .gz files (can be disabled with `make zstd-nogz` or `make HAVE_ZLIB=0`)
+cli : new : experimental target `make zstdmt`, with multi-threading support
+cli : new : improved dictionary builder "cover" (experimental), by Nick Terrell, based on prior work by Giuseppe Ottaviano.
+cli : new : advanced commands for detailed parameters, by Przemyslaw Skibinski
+cli : fix zstdless on Mac OS-X, by Andrew Janke
+cli : fix #232 "compress non-files"
+dictBuilder : improved dictionary generation quality, thanks to Nick Terrell
+API : new : lib/compress/ZSTDMT_compress.h multithreading API (experimental)
+API : new : ZSTD_create?Dict_byReference(), requested by Bartosz Taudul
+API : new : ZDICT_finalizeDictionary()
+API : fix : ZSTD_initCStream_usingCDict() properly writes dictID into frame header, by Gregory Szorc (#511)
+API : fix : all symbols properly exposed in libzstd, by Nick Terrell
+build : support for Solaris target, by Przemyslaw Skibinski
+doc : clarified specification, by Sean Purcell
+
+v1.1.2
+API : streaming : decompression : changed : automatic implicit reset when chain-decoding new frames without init
+API : experimental : added : dictID retrieval functions, and ZSTD_initCStream_srcSize()
+API : zbuff : changed : prototypes now generate deprecation warnings
+lib : improved : faster decompression speed at ultra compression settings and 32-bits mode
+lib : changed : only public ZSTD_ symbols are now exposed
+lib : changed : reduced usage of stack memory
+lib : fixed : several corner case bugs, by Nick Terrell
+cli : new : gzstd, experimental version able to decode .gz files, by Przemyslaw Skibinski
+cli : new : preserve file attributes
+cli : new : added zstdless and zstdgrep tools
+cli : fixed : status displays total amount decoded, even for file consisting of multiple frames (like pzstd)
+cli : fixed : zstdcat
+zlib_wrapper : added support for gz* functions, by Przemyslaw Skibinski
+install : better compatibility with FreeBSD, by Dimitry Andric
+source tree : changed : zbuff source files moved to lib/deprecated
+
+v1.1.1
+New : command -M#, --memory=, --memlimit=, --memlimit-decompress= to limit allowed memory consumption
+New : doc/zstd_manual.html, by Przemyslaw Skibinski
+Improved : slightly better compression ratio at --ultra levels (>= 20)
+Improved : better memory usage when using streaming compression API, thanks to @Rogier-5 report
+Added : API : ZSTD_initCStream_usingCDict(), ZSTD_initDStream_usingDDict() (experimental section)
+Added : example/multiple_streaming_compression.c
+Changed : zstd_errors.h is now installed within /include (and replaces errors_public.h)
+Updated man page
+Fixed : zstd-small, zstd-compress and zstd-decompress compilation targets
+
+v1.1.0
+New : contrib/pzstd, parallel version of zstd, by Nick Terrell
+added : NetBSD install target (#338)
+Improved : speed for batches of small files
+Improved : speed of zlib wrapper, by Przemyslaw Skibinski
+Changed : libzstd on Windows supports legacy formats, by Christophe Chevalier
+Fixed : CLI -d output to stdout by default when input is stdin (#322)
+Fixed : CLI correctly detects console on Mac OS-X
+Fixed : CLI supports recursive mode `-r` on Mac OS-X
+Fixed : Legacy decoders use unified error codes, reported by benrg (#341), fixed by Przemyslaw Skibinski
+Fixed : compatibility with OpenBSD, reported by Juan Francisco Cantero Hurtado (#319)
+Fixed : compatibility with Hurd, by Przemyslaw Skibinski (#365)
+Fixed : zstd-pgo, reported by octoploid (#329)
+
+v1.0.0
+Change Licensing, all project is now BSD, Copyright Facebook
+Small decompression speed improvement
+API : Streaming API supports legacy format
+API : ZDICT_getDictID(), ZSTD_sizeof_{CCtx, DCtx, CStream, DStream}(), ZSTD_setDStreamParameter()
+CLI supports legacy formats v0.4+
+Fixed : compression fails on certain huge files, reported by Jesse McGrew
+Enhanced documentation, by Przemyslaw Skibinski
+
+v0.8.1
+New streaming API
+Changed : --ultra now enables levels beyond 19
+Changed : -i# now selects benchmark time in second
+Fixed : ZSTD_compress* can now compress > 4 GB in a single pass, reported by Nick Terrell
+Fixed : speed regression on specific patterns (#272)
+Fixed : support for Z_SYNC_FLUSH, by Dmitry Krot (#291)
+Fixed : ICC compilation, by Przemyslaw Skibinski
+
+v0.8.0
+Improved : better speed on clang and gcc -O2, thanks to Eric Biggers
+New : Build on FreeBSD and DragonFly, thanks to JrMarino
+Changed : modified API : ZSTD_compressEnd()
+Fixed : legacy mode with ZSTD_HEAPMODE=0, by Christopher Bergqvist
+Fixed : premature end of frame when zero-sized raw block, reported by Eric Biggers
+Fixed : large dictionaries (> 384 KB), reported by Ilona Papava
+Fixed : checksum correctly checked in single-pass mode
+Fixed : combined --test amd --rm, reported by Andreas M. Nilsson
+Modified : minor compression level adaptations
+Updated : compression format specification to v0.2.0
+changed : zstd.h moved to /lib directory
+
+v0.7.5
+Transition version, supporting decoding of v0.8.x
+
+v0.7.4
+Added : homebrew for Mac, by Daniel Cade
+Added : more examples
+Fixed : segfault when using small dictionaries, reported by Felix Handte
+Modified : default compression level for CLI is now 3
+Updated : specification, to v0.1.1
+
+v0.7.3
+New : compression format specification
+New : `--` separator, stating that all following arguments are file names. Suggested by Chip Turner.
+New : `ZSTD_getDecompressedSize()`
+New : OpenBSD target, by Juan Francisco Cantero Hurtado
+New : `examples` directory
+fixed : dictBuilder using HC levels, reported by Bartosz Taudul
+fixed : legacy support from ZSTD_decompress_usingDDict(), reported by Felix Handte
+fixed : multi-blocks decoding with intermediate uncompressed blocks, reported by Greg Slazinski
+modified : removed "mem.h" and "error_public.h" dependencies from "zstd.h" (experimental section)
+modified : legacy functions no longer need magic number
+
+v0.7.2
+fixed : ZSTD_decompressBlock() using multiple consecutive blocks. Reported by Greg Slazinski.
+fixed : potential segfault on very large files (many gigabytes). Reported by Chip Turner.
+fixed : CLI displays system error message when destination file cannot be created (#231). Reported by Chip Turner.
+
+v0.7.1
+fixed : ZBUFF_compressEnd() called multiple times with too small `dst` buffer, reported by Christophe Chevalier
+fixed : dictBuilder fails if first sample is too small, reported by Руслан Ковалёв
+fixed : corruption issue, reported by cj
+modified : checksum enabled by default in command line mode
+
+v0.7.0
+New : Support for directory compression, using `-r`, thanks to Przemyslaw Skibinski
+New : Command `--rm`, to remove source file after successful de/compression
+New : Visual build scripts, by Christophe Chevalier
+New : Support for Sparse File-systems (do not use space for zero-filled sectors)
+New : Frame checksum support
+New : Support pass-through mode (when using `-df`)
+API : more efficient Dictionary API : `ZSTD_compress_usingCDict()`, `ZSTD_decompress_usingDDict()`
+API : create dictionary files from custom content, by Giuseppe Ottaviano
+API : support for custom malloc/free functions
+New : controllable Dictionary ID
+New : Support for skippable frames
+
+v0.6.1
+New : zlib wrapper API, thanks to Przemyslaw Skibinski
+New : Ability to compile compressor / decompressor separately
+Changed : new lib directory structure
+Fixed : Legacy codec v0.5 compatible with dictionary decompression
+Fixed : Decoder corruption error (#173)
+Fixed : null-string roundtrip (#176)
+New : benchmark mode can select directory as input
+Experimental : midipix support, VMS support
+
+v0.6.0
+Stronger high compression modes, thanks to Przemyslaw Skibinski
+API : ZSTD_getFrameParams() provides size of decompressed content
+New : highest compression modes require `--ultra` command to fully unleash their capacity
+Fixed : zstd cli return error code > 0 and removes dst file artifact when decompression fails, thanks to Chip Turner
+
+v0.5.1
+New : Optimal parsing => Very high compression modes, thanks to Przemyslaw Skibinski
+Changed : Dictionary builder integrated into libzstd and zstd cli
+Changed (!) : zstd cli now uses "multiple input files" as default mode. See `zstd -h`.
+Fix : high compression modes for big-endian platforms
+New : zstd cli : `-t` | `--test` command
+
+v0.5.0
+New : dictionary builder utility
+Changed : streaming & dictionary API
+Improved : better compression of small data
+
+v0.4.7
+Improved : small compression speed improvement in HC mode
+Changed : `zstd_decompress.c` has ZSTD_LEGACY_SUPPORT to 0 by default
+fix : bt search bug
+
+v0.4.6
+fix : fast compression mode on Windows
+New : cmake configuration file, thanks to Artyom Dymchenko
+Improved : high compression mode on repetitive data
+New : block-level API
+New : ZSTD_duplicateCCtx()
+
+v0.4.5
+new : -m/--multiple : compress/decompress multiple files
+
+v0.4.4
+Fixed : high compression modes for Windows 32 bits
+new : external dictionary API extended to buffered mode and accessible through command line
+new : windows DLL project, thanks to Christophe Chevalier
+
+v0.4.3 :
+new : external dictionary API
+new : zstd-frugal
+
+v0.4.2 :
+Generic minor improvements for small blocks
+Fixed : big-endian compatibility, by Peter Harris (#85)
+
+v0.4.1
+Fixed : ZSTD_LEGACY_SUPPORT=0 build mode (reported by Luben)
+removed `zstd.c`
+
+v0.4.0
+Command line utility compatible with high compression levels
+Removed zstdhc => merged into zstd
+Added : ZBUFF API (see zstd_buffered.h)
+Rolling buffer support
+
+v0.3.6
+small blocks params
+
+v0.3.5
+minor generic compression improvements
+
+v0.3.4
+Faster fast cLevels
+
+v0.3.3
+Small compression ratio improvement
+
+v0.3.2
+Fixed Visual Studio
+
+v0.3.1 :
+Small compression ratio improvement
+
+v0.3
+HC mode : compression levels 2-26
+
+v0.2.2
+Fix : Visual Studio 2013 & 2015 release compilation, by Christophe Chevalier
+
+v0.2.1
+Fix : Read errors, advanced fuzzer tests, by Hanno Böck
+
+v0.2.0
+**Breaking format change**
+Faster decompression speed
+Can still decode v0.1 format
+
+v0.1.3
+fix uninitialization warning, reported by Evan Nemerson
+
+v0.1.2
+frame concatenation support
+
+v0.1.1
+fix compression bug
+detects write-flush errors
+
+v0.1.0
+first release
diff --git a/Makefile b/Makefile
index ed78d1956135..f2ec8c9b1074 100644
--- a/Makefile
+++ b/Makefile
@@ -156,7 +156,7 @@ list:
done \
} | column -t -s $$'\t'
-.PHONY: install clangtest armtest usan asan uasan
+.PHONY: install armtest usan asan uasan
install:
@$(MAKE) -C $(ZSTDDIR) $@
@$(MAKE) -C $(PRGDIR) $@
@@ -188,7 +188,7 @@ gcc7build: clean
.PHONY: clangbuild
clangbuild: clean
clang -v
- CXX=clang++ CC=clang $(MAKE) all MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
+ CXX=clang++ CC=clang CFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation" $(MAKE) all
m32build: clean
gcc -v
@@ -232,10 +232,6 @@ gcc6test: clean
gcc-6 -v
$(MAKE) all CC=gcc-6 MOREFLAGS="-Werror"
-clangtest: clean
- clang -v
- $(MAKE) all CXX=clang++ CC=clang MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion -Wdocumentation"
-
armtest: clean
$(MAKE) -C $(TESTDIR) datagen # use native, faster
$(MAKE) -C $(TESTDIR) test CC=arm-linux-gnueabi-gcc QEMU_SYS=qemu-arm-static ZSTDRTTEST= MOREFLAGS="-Werror -static" FUZZER_FLAGS=--no-big-tests
diff --git a/README.md b/README.md
index 4b6d19e7e72d..290341cc78e7 100644
--- a/README.md
+++ b/README.md
@@ -14,6 +14,7 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
[![Build Status][travisDevBadge]][travisLink]
[![Build status][AppveyorDevBadge]][AppveyorLink]
[![Build status][CircleDevBadge]][CircleLink]
+[![Build status][CirrusDevBadge]][CirrusLink]
[travisDevBadge]: https://travis-ci.org/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
[travisLink]: https://travis-ci.org/facebook/zstd
@@ -21,14 +22,16 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
[CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
[CircleLink]: https://circleci.com/gh/facebook/zstd
+[CirrusDevBadge]: https://api.cirrus-ci.com/github/facebook/zstd.svg?branch=dev
+[CirrusLink]: https://cirrus-ci.com/github/facebook/zstd
## Benchmarks
For reference, several fast compression algorithms were tested and compared
-on a server running Linux Debian (`Linux version 4.14.0-3-amd64`),
-with a Core i7-6700K CPU @ 4.0GHz,
+on a server running Arch Linux (`Linux version 5.0.5-arch1-1`),
+with a Core i9-9900K CPU @ 5.0GHz,
using [lzbench], an open-source in-memory benchmark by @inikep
-compiled with [gcc] 7.3.0,
+compiled with [gcc] 8.2.1,
on the [Silesia compression corpus].
[lzbench]: https://github.com/inikep/lzbench
@@ -37,14 +40,14 @@ on the [Silesia compression corpus].
| Compressor name | Ratio | Compression| Decompress.|
| --------------- | ------| -----------| ---------- |
-| **zstd 1.3.4 -1** | 2.877 | 470 MB/s | 1380 MB/s |
-| zlib 1.2.11 -1 | 2.743 | 110 MB/s | 400 MB/s |
-| brotli 1.0.2 -0 | 2.701 | 410 MB/s | 430 MB/s |
-| quicklz 1.5.0 -1 | 2.238 | 550 MB/s | 710 MB/s |
-| lzo1x 2.09 -1 | 2.108 | 650 MB/s | 830 MB/s |
-| lz4 1.8.1 | 2.101 | 750 MB/s | 3700 MB/s |
-| snappy 1.1.4 | 2.091 | 530 MB/s | 1800 MB/s |
-| lzf 3.6 -1 | 2.077 | 400 MB/s | 860 MB/s |
+| **zstd 1.4.0 -1** | 2.884 | 530 MB/s | 1360 MB/s |
+| zlib 1.2.11 -1 | 2.743 | 110 MB/s | 440 MB/s |
+| brotli 1.0.7 -0 | 2.701 | 430 MB/s | 470 MB/s |
+| quicklz 1.5.0 -1 | 2.238 | 600 MB/s | 800 MB/s |
+| lzo1x 2.09 -1 | 2.106 | 680 MB/s | 950 MB/s |
+| lz4 1.8.3 | 2.101 | 800 MB/s | 4220 MB/s |
+| snappy 1.1.4 | 2.073 | 580 MB/s | 2020 MB/s |
+| lzf 3.6 -1 | 2.077 | 440 MB/s | 930 MB/s |
[zlib]: http://www.zlib.net/
[LZ4]: http://www.lz4.org/
diff --git a/contrib/adaptive-compression/Makefile b/contrib/adaptive-compression/Makefile
index c26efcd2815b..2718e9d6e1be 100644
--- a/contrib/adaptive-compression/Makefile
+++ b/contrib/adaptive-compression/Makefile
@@ -13,7 +13,7 @@ CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
CFLAGS ?= -O3
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
- -Wstrict-prototypes -Wundef -Wformat-security \
+ -Wstrict-prototypes -Wundef \
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
-Wredundant-decls
CFLAGS += $(DEBUGFLAGS)
@@ -22,10 +22,10 @@ FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) $(MULTITHREAD_LDFLAGS)
all: adapt datagen
-adapt: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
+adapt: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
$(CC) $(FLAGS) $^ -o $@
-adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c adapt.c
+adapt-debug: $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c adapt.c
$(CC) $(FLAGS) -DDEBUG_MODE=2 $^ -o adapt
datagen : $(PRGDIR)/datagen.c datagencli.c
diff --git a/contrib/adaptive-compression/adapt.c b/contrib/adaptive-compression/adapt.c
index 524d1378a80f..8fb4047e996b 100644
--- a/contrib/adaptive-compression/adapt.c
+++ b/contrib/adaptive-compression/adapt.c
@@ -13,6 +13,7 @@
#include zstd 1.3.8 Manual
+zstd 1.4.0 Manual
Contents
Introduction
@@ -71,7 +80,9 @@
Default constant
-Simple API
+Constants
+
+Simple API
size_t ZSTD_compress( void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
@@ -126,13 +137,22 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
@return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise.
size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); +`src` should point to the start of a ZSTD frame or skippable frame. + `srcSize` must be >= first frame size + @return : the compressed size of the first frame starting at `src`, + suitable to pass as `srcSize` to `ZSTD_decompress` or similar, + or an error code if input is invalid +
#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11)/* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ +int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ int ZSTD_maxCLevel(void); /*!< maximum compression level available */
When compressing many times, it is recommended to allocate a context just once, and re-use it for each successive compression operation. @@ -169,228 +189,7 @@ size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, - int compressionLevel); -Compression at an explicit compression level using a Dictionary. - A dictionary can be any arbitrary data segment (also called a prefix), - or a buffer with specified information (see dictBuilder/zdict.h). - Note : This function loads the dictionary, resulting in significant startup delay. - It's intended for a dictionary used only once. - Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. -
size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize); -Decompression using a known Dictionary. - Dictionary must be identical to the one used during compression. - Note : This function loads the dictionary, resulting in significant startup delay. - It's intended for a dictionary used only once. - Note : When `dict == NULL || dictSize < 8` no dictionary is used. -
ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, - int compressionLevel); -When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once. - ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost. - ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. - `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict. - Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content. - Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. -
size_t ZSTD_freeCDict(ZSTD_CDict* CDict); -Function frees memory allocated by ZSTD_createCDict(). -
size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict); -Compression using a digested Dictionary. - Recommended when same dictionary is used multiple times. - Note : compression level is _decided at dictionary creation time_, - and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) -
ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); -Create a digested dictionary, ready to start decompression operation without startup delay. - dictBuffer can be released after DDict creation, as its content is copied inside DDict. -
size_t ZSTD_freeDDict(ZSTD_DDict* ddict); -Function frees memory allocated with ZSTD_createDDict() -
size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_DDict* ddict); -Decompression using a digested Dictionary. - Recommended when same dictionary is used multiple times. -
typedef struct ZSTD_inBuffer_s { - const void* src; /**< start of input buffer */ - size_t size; /**< size of input buffer */ - size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_inBuffer; -
typedef struct ZSTD_outBuffer_s { - void* dst; /**< start of output buffer */ - size_t size; /**< size of output buffer */ - size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_outBuffer; -
- A ZSTD_CStream object is required to track streaming operation. - Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. - ZSTD_CStream objects can be reused multiple times on consecutive compression operations. - It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. - - For parallel execution, use one separate ZSTD_CStream per thread. - - note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. - - Parameters are sticky : when starting a new compression on the same context, - it will re-use the same sticky parameters as previous compression session. - When in doubt, it's recommended to fully initialize the context before usage. - Use ZSTD_initCStream() to set the parameter to a selected compression level. - Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters. - - Use ZSTD_compressStream() as many times as necessary to consume input stream. - The function will automatically update both `pos` fields within `input` and `output`. - Note that the function may not consume the entire input, - for example, because the output buffer is already full, - in which case `input.pos < input.size`. - The caller must check if input has been entirely consumed. - If not, the caller must make some room to receive more compressed data, - and then present again remaining input data. - @return : a size hint, preferred nb of bytes to use as input for next function call - or an error code, which can be tested using ZSTD_isError(). - Note 1 : it's just a hint, to help latency a little, any value will work fine. - Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize() - - At any moment, it's possible to flush whatever data might remain stuck within internal buffer, - using ZSTD_flushStream(). `output->pos` will be updated. - Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0). - In which case, make some room to receive more compressed data, and call again ZSTD_flushStream(). - @return : 0 if internal buffers are entirely flushed, - >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), - or an error code, which can be tested using ZSTD_isError(). - - ZSTD_endStream() instructs to finish a frame. - It will perform a flush and write frame epilogue. - The epilogue is required for decoders to consider a frame completed. - flush() operation is the same, and follows same rules as ZSTD_flushStream(). - @return : 0 if frame fully completed and fully flushed, - >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), - or an error code, which can be tested using ZSTD_isError(). - - -- -
typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ -
ZSTD_CStream* ZSTD_createCStream(void); -size_t ZSTD_freeCStream(ZSTD_CStream* zcs); -
size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); -size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -
size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -
size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ -
- A ZSTD_DStream object is required to track streaming operations. - Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. - ZSTD_DStream objects can be re-used multiple times. - - Use ZSTD_initDStream() to start a new decompression operation. - @return : recommended first input size - Alternatively, use advanced API to set specific properties. - - Use ZSTD_decompressStream() repetitively to consume your input. - The function will update both `pos` fields. - If `input.pos < input.size`, some input has not been consumed. - It's up to the caller to present again remaining data. - The function tries to flush all data decoded immediately, respecting output buffer size. - If `output.pos < output.size`, decoder has flushed everything it could. - But if `output.pos == output.size`, there might be some data left within internal buffers., - In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. - Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. - @return : 0 when a frame is completely decoded and fully flushed, - or an error code, which can be tested using ZSTD_isError(), - or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : - the return value is a suggested next input size (just a hint for better latency) - that will never request more than the remaining frame size. - -- -
typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ -
ZSTD_DStream* ZSTD_createDStream(void); -size_t ZSTD_freeDStream(ZSTD_DStream* zds); -
size_t ZSTD_initDStream(ZSTD_DStream* zds); -size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -
size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ -
size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ -
- The definitions in the following section are considered experimental. - They are provided for advanced scenarios. - They should never be used with a dynamic library, as prototypes may change in the future. - Use them only in association with static linking. - -- -
- The following symbols and constants form the "staging area" : - they are considered to join "stable API" by v1.4.0. - The proposal is written so that it can be made stable "as is", - though it's still possible to suggest improvements. - Staging is in fact last chance for changes, - the API is locked once reaching "stable" status. - -- -
int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ -
size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); -`src` should point to the start of a ZSTD frame or skippable frame. - `srcSize` must be >= first frame size - @return : the compressed size of the first frame starting at `src`, - suitable to pass as `srcSize` to `ZSTD_decompress` or similar, - or an error code if input is invalid -
size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); -size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); -size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); -size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); -size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); -size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); -These functions give the _current_ memory usage of selected object. - Note that object memory usage can evolve (increase or decrease) over time. -
typedef enum { ZSTD_fast=1, ZSTD_dfast=2, @@ -407,7 +206,10 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
typedef enum { - /* compression parameters */ + /* compression parameters + * Note: When compressing with a ZSTD_CDict these parameters are superseded + * by the parameters used to construct the ZSTD_CDict. See ZSTD_CCtx_refCDict() + * for more info (superseded-by-cdict). */ ZSTD_c_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table * Default level is ZSTD_CLEVEL_DEFAULT==3. * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT. @@ -529,6 +331,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); * ZSTD_c_format * ZSTD_c_forceMaxWindow * ZSTD_c_forceAttachDict + * ZSTD_c_literalCompressionMode * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. * note : never ever use experimentalParam? names directly; * also, the enums values themselves are unstable and can still change. @@ -536,7 +339,8 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); ZSTD_c_experimentalParam1=500, ZSTD_c_experimentalParam2=10, ZSTD_c_experimentalParam3=1000, - ZSTD_c_experimentalParam4=1001 + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, } ZSTD_cParameter;
typedef struct { @@ -580,62 +384,10 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); Note 3 : Whenever all input data is provided and consumed in a single round, for example with ZSTD_compress2(), or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end), - this value is automatically overriden by srcSize instead. + this value is automatically overridden by srcSize instead.
size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); -Create an internal CDict from `dict` buffer. - Decompression will have to use same dictionary. - @result : 0, or an error code (which can be tested with ZSTD_isError()). - Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, - meaning "return to no-dictionary mode". - Note 1 : Dictionary is sticky, it will be used for all future compressed frames. - To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). - Note 2 : Loading a dictionary involves building tables. - It's also a CPU consuming operation, with non-negligible impact on latency. - Tables are dependent on compression parameters, and for this reason, - compression parameters can no longer be changed after loading a dictionary. - Note 3 :`dict` content will be copied internally. - Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead. - In such a case, dictionary buffer must outlive its users. - Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() - to precisely select how dictionary content must be interpreted. -
size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); -Reference a prepared dictionary, to be used for all next compressed frames. - Note that compression parameters are enforced from within CDict, - and supercede any compression parameter previously set within CCtx. - The dictionary will remain valid for future compressed frames using same CCtx. - @result : 0, or an error code (which can be tested with ZSTD_isError()). - Special : Referencing a NULL CDict means "return to no-dictionary mode". - Note 1 : Currently, only one dictionary can be managed. - Referencing a new dictionary effectively "discards" any previous one. - Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. -
size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, - const void* prefix, size_t prefixSize); -Reference a prefix (single-usage dictionary) for next compressed frame. - A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end). - Decompression will need same prefix to properly regenerate data. - Compressing with a prefix is similar in outcome as performing a diff and compressing it, - but performs much faster, especially during decompression (compression speed is tunable with compression level). - @result : 0, or an error code (which can be tested with ZSTD_isError()). - Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary - Note 1 : Prefix buffer is referenced. It **must** outlive compression. - Its content must remain unmodified during compression. - Note 2 : If the intention is to diff some large src data blob with some prior version of itself, - ensure that the window size is large enough to contain the entire source. - See ZSTD_c_windowLog. - Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters. - It's a CPU consuming operation, with non-negligible impact on latency. - If there is a need to use the same prefix multiple times, consider loadDictionary instead. - Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent). - Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. -
typedef enum { ZSTD_reset_session_only = 1, ZSTD_reset_parameters = 2, @@ -672,42 +424,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
typedef enum { - ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ - ZSTD_e_flush=1, /* flush any data provided so far, - * it creates (at least) one new block, that can be decoded immediately on reception; - * frame will continue: any future data can still reference previously compressed data, improving compression. */ - ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. - * note that frame is only closed after compressed data is fully flushed (return value == 0). - * After that point, any additional data starts a new frame. - * note : each frame is independent (does not reference any content from previous frame). */ -} ZSTD_EndDirective; -
size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective endOp); -Behaves about the same as ZSTD_compressStream, with additional control on end directive. - - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() - - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) - - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize - - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. - - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. - - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, - and then immediately returns, just indicating that there is some data remaining to be flushed. - The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. - - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. - - @return provides a minimum amount of data remaining to be flushed from internal buffers - or an error code, which can be tested using ZSTD_isError(). - if @return != 0, flush is not fully completed, there is still some data left within internal buffers. - This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. - For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. - - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), - only ZSTD_e_end or ZSTD_e_flush operations are allowed. - Before starting a new compression job, or changing compression parameters, - it is required to fully flush internal buffers. - -
typedef enum { @@ -715,7 +432,8 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); * the streaming API will refuse to allocate memory buffer * in order to protect the host from unreasonable memory requirements. * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. - * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) */ + * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT). + * Special: value 0 means "use default maximum windowLog". */ /* note : additional experimental parameters are also available * within the experimental section of the API. @@ -746,6 +464,352 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); +Return a DCtx to clean state. + Session and parameters can be reset jointly or separately. + Parameters can only be reset when no active frame is being decompressed. + @return : 0, or an error code, which can be tested with ZSTD_isError() + +
typedef struct ZSTD_inBuffer_s { + const void* src; /**< start of input buffer */ + size_t size; /**< size of input buffer */ + size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_inBuffer; +
typedef struct ZSTD_outBuffer_s { + void* dst; /**< start of output buffer */ + size_t size; /**< size of output buffer */ + size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_outBuffer; +
+ A ZSTD_CStream object is required to track streaming operation. + Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. + ZSTD_CStream objects can be reused multiple times on consecutive compression operations. + It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. + + For parallel execution, use one separate ZSTD_CStream per thread. + + note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. + + Parameters are sticky : when starting a new compression on the same context, + it will re-use the same sticky parameters as previous compression session. + When in doubt, it's recommended to fully initialize the context before usage. + Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), + ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to + set more specific parameters, the pledged source size, or load a dictionary. + + Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to + consume input stream. The function will automatically update both `pos` + fields within `input` and `output`. + Note that the function may not consume the entire input, for example, because + the output buffer is already full, in which case `input.pos < input.size`. + The caller must check if input has been entirely consumed. + If not, the caller must make some room to receive more compressed data, + and then present again remaining input data. + note: ZSTD_e_continue is guaranteed to make some forward progress when called, + but doesn't guarantee maximal forward progress. This is especially relevant + when compressing with multiple threads. The call won't block if it can + consume some input, but if it can't it will wait for some, but not all, + output to be flushed. + @return : provides a minimum amount of data remaining to be flushed from internal buffers + or an error code, which can be tested using ZSTD_isError(). + + At any moment, it's possible to flush whatever data might remain stuck within internal buffer, + using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated. + Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0). + In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush. + You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the + operation. + note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will + block until the flush is complete or the output buffer is full. + @return : 0 if internal buffers are entirely flushed, + >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), + or an error code, which can be tested using ZSTD_isError(). + + Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. + It will perform a flush and write frame epilogue. + The epilogue is required for decoders to consider a frame completed. + flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush. + You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to + start a new frame. + note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will + block until the flush is complete or the output buffer is full. + @return : 0 if frame fully completed and fully flushed, + >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), + or an error code, which can be tested using ZSTD_isError(). + + ++ +
typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ +
ZSTD_CStream* ZSTD_createCStream(void); +size_t ZSTD_freeCStream(ZSTD_CStream* zcs); +
typedef enum { + ZSTD_e_continue=0,/* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. + * note : multithreaded compression will block to flush as much output as possible. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * note that frame is only closed after compressed data is fully flushed (return value == 0). + * After that point, any additional data starts a new frame. + * note : each frame is independent (does not reference any content from previous frame). + : note : multithreaded compression will block to flush as much output as possible. */ +} ZSTD_EndDirective; +
size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); +Behaves about the same as ZSTD_compressStream, with additional control on end directive. + - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) + - output->pos must be <= dstCapacity, input->pos must be <= srcSize + - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, + and then immediately returns, just indicating that there is some data remaining to be flushed. + The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + - @return provides a minimum amount of data remaining to be flushed from internal buffers + or an error code, which can be tested using ZSTD_isError(). + if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + only ZSTD_e_end or ZSTD_e_flush operations are allowed. + Before starting a new compression job, or changing compression parameters, + it is required to fully flush internal buffers. + +
size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ +
size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ +
ZSTD_compressStream2(). It is redundent, but is still fully supported. + Advanced parameters and dictionary compression can only be used through the + new API. ++ +
+ ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + ++ +
NOTE: The return value is different. ZSTD_compressStream() returns a hint for + the next read size (if non-zero and not an error). ZSTD_compressStream2() + returns the number of bytes left to flush (if non-zero and not an error). + ++ +
+ A ZSTD_DStream object is required to track streaming operations. + Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. + ZSTD_DStream objects can be re-used multiple times. + + Use ZSTD_initDStream() to start a new decompression operation. + @return : recommended first input size + Alternatively, use advanced API to set specific properties. + + Use ZSTD_decompressStream() repetitively to consume your input. + The function will update both `pos` fields. + If `input.pos < input.size`, some input has not been consumed. + It's up to the caller to present again remaining data. + The function tries to flush all data decoded immediately, respecting output buffer size. + If `output.pos < output.size`, decoder has flushed everything it could. + But if `output.pos == output.size`, there might be some data left within internal buffers., + In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. + Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. + @return : 0 when a frame is completely decoded and fully flushed, + or an error code, which can be tested using ZSTD_isError(), + or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : + the return value is a suggested next input size (just a hint for better latency) + that will never request more than the remaining frame size. + ++ +
typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ +
ZSTD_DStream* ZSTD_createDStream(void); +size_t ZSTD_freeDStream(ZSTD_DStream* zds); +
size_t ZSTD_initDStream(ZSTD_DStream* zds); +size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +
size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ +
size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ +
size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + int compressionLevel); +Compression at an explicit compression level using a Dictionary. + A dictionary can be any arbitrary data segment (also called a prefix), + or a buffer with specified information (see dictBuilder/zdict.h). + Note : This function loads the dictionary, resulting in significant startup delay. + It's intended for a dictionary used only once. + Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. +
size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize); +Decompression using a known Dictionary. + Dictionary must be identical to the one used during compression. + Note : This function loads the dictionary, resulting in significant startup delay. + It's intended for a dictionary used only once. + Note : When `dict == NULL || dictSize < 8` no dictionary is used. +
ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, + int compressionLevel); +When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once. + ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost. + ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict. + Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content. + Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. +
size_t ZSTD_freeCDict(ZSTD_CDict* CDict); +Function frees memory allocated by ZSTD_createCDict(). +
size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict); +Compression using a digested Dictionary. + Recommended when same dictionary is used multiple times. + Note : compression level is _decided at dictionary creation time_, + and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) +
ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); +Create a digested dictionary, ready to start decompression operation without startup delay. + dictBuffer can be released after DDict creation, as its content is copied inside DDict. +
size_t ZSTD_freeDDict(ZSTD_DDict* ddict); +Function frees memory allocated with ZSTD_createDDict() +
size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict); +Decompression using a digested Dictionary. + Recommended when same dictionary is used multiple times. +
unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); +Provides the dictID stored within dictionary. + if @return == 0, the dictionary is not conformant with Zstandard specification. + It can still be loaded, but as a content-only dictionary. +
unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); +Provides the dictID of the dictionary loaded into `ddict`. + If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + Non-conformant dictionaries can still be loaded, but as content-only dictionaries. +
unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); +Provides the dictID required to decompressed the frame stored within `src`. + If @return == 0, the dictID could not be decoded. + This could for one of the following reasons : + - The frame does not require a dictionary to be decoded (most common case). + - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. + Note : this use case also happens when using a non-conformant dictionary. + - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). + - This is not a Zstandard frame. + When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. +
+ This API allows dictionaries to be used with ZSTD_compress2(), + ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and + only reset with the context is reset with ZSTD_reset_parameters or + ZSTD_reset_session_and_parameters. Prefixes are single-use. ++ +
size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); +Create an internal CDict from `dict` buffer. + Decompression will have to use same dictionary. + @result : 0, or an error code (which can be tested with ZSTD_isError()). + Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, + meaning "return to no-dictionary mode". + Note 1 : Dictionary is sticky, it will be used for all future compressed frames. + To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). + Note 2 : Loading a dictionary involves building tables. + It's also a CPU consuming operation, with non-negligible impact on latency. + Tables are dependent on compression parameters, and for this reason, + compression parameters can no longer be changed after loading a dictionary. + Note 3 :`dict` content will be copied internally. + Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead. + In such a case, dictionary buffer must outlive its users. + Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() + to precisely select how dictionary content must be interpreted. +
size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); +Reference a prepared dictionary, to be used for all next compressed frames. + Note that compression parameters are enforced from within CDict, + and supersede any compression parameter previously set within CCtx. + The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. + The ignored parameters will be used again if the CCtx is returned to no-dictionary mode. + The dictionary will remain valid for future compressed frames using same CCtx. + @result : 0, or an error code (which can be tested with ZSTD_isError()). + Special : Referencing a NULL CDict means "return to no-dictionary mode". + Note 1 : Currently, only one dictionary can be managed. + Referencing a new dictionary effectively "discards" any previous one. + Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. +
size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, + const void* prefix, size_t prefixSize); +Reference a prefix (single-usage dictionary) for next compressed frame. + A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end). + Decompression will need same prefix to properly regenerate data. + Compressing with a prefix is similar in outcome as performing a diff and compressing it, + but performs much faster, especially during decompression (compression speed is tunable with compression level). + @result : 0, or an error code (which can be tested with ZSTD_isError()). + Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary + Note 1 : Prefix buffer is referenced. It **must** outlive compression. + Its content must remain unmodified during compression. + Note 2 : If the intention is to diff some large src data blob with some prior version of itself, + ensure that the window size is large enough to contain the entire source. + See ZSTD_c_windowLog. + Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters. + It's a CPU consuming operation, with non-negligible impact on latency. + If there is a need to use the same prefix multiple times, consider loadDictionary instead. + Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent). + Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. +
size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);Create an internal DDict from dict buffer, to be used to decompress next frames. @@ -793,15 +857,25 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); -Return a DCtx to clean state. - Session and parameters can be reset jointly or separately. - Parameters can only be reset when no active frame is being decompressed. - @return : 0, or an error code, which can be tested with ZSTD_isError() - +
size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); +size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); +size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); +size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); +These functions give the _current_ memory usage of selected object. + Note that object memory usage can evolve (increase or decrease) over time.
-experimental API (static linking only)
+ADVANCED AND EXPERIMENTAL FUNCTIONS
+ The definitions in the following section are considered experimental. + They are provided for advanced scenarios. + They should never be used with a dynamic library, as prototypes may change in the future. + Use them only in association with static linking. + ++ +experimental API (static linking only)
The following symbols and constants are not planned to join "stable API" status in the near future. They can still change in future versions. @@ -890,12 +964,21 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); ZSTD_dictForceCopy = 2, /* Always copy the dictionary. */ } ZSTD_dictAttachPref_e;
-Frame size functions
+typedef enum { + ZSTD_lcm_auto = 0, /**< Automatically determine the compression mode based on the compression level. + * Negative compression levels will be uncompressed, and positive compression + * levels will be compressed. */ + ZSTD_lcm_huffman = 1, /**< Always attempt Huffman compression. Uncompressed literals will still be + * emitted if Huffman compression is not profitable. */ + ZSTD_lcm_uncompressed = 2, /**< Always emit uncompressed literals. */ +} ZSTD_literalCompressionMode_e; +
+Frame size functions
unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); -`src` should point the start of a series of ZSTD encoded and/or skippable frames +
`src` should point to the start of a series of ZSTD encoded and/or skippable frames `srcSize` must be the _exact_ size of this series - (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`) + (i.e. there should be a frame boundary at `src + srcSize`) @return : - decompressed size of all data in all successive frames - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN - if an error occurred: ZSTD_CONTENTSIZE_ERROR @@ -915,13 +998,27 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); however it does mean that all frame data must be present and valid.
+ZSTD_decompressBound() :
`src` should point to the start of a series of ZSTD encoded and/or skippable frames + `srcSize` must be the _exact_ size of this series + (i.e. there should be a frame boundary at `src + srcSize`) + @return : - upper-bound for the decompressed size of all data in all successive frames + - if an error occured: ZSTD_CONTENTSIZE_ERROR + + note 1 : an error can occur if `src` contains an invalid or incorrectly formatted frame. + note 2 : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`. + in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value. + note 3 : when the decompressed size field isn't available, the upper-bound for that frame is calculated by: + upper-bound = # blocks * min(128 KB, Window_Size) + ++size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. @return : size of the Frame Header, or an error code (if srcSize is too small)
-Memory management
+Memory management
size_t ZSTD_estimateCCtxSize(int compressionLevel); size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); @@ -933,7 +1030,7 @@ size_t ZSTD_estimateDCtxSize(void); It will also consider src size to be arbitrarily "large", which is worst case. If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation. ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. Note : CCtx size estimation is only correct for single-threaded compression.
@@ -946,7 +1043,7 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); It will also consider src size to be arbitrarily "large", which is worst case. If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. Note : CStream size estimation is only correct for single-threaded compression. ZSTD_DStream memory budget depends on window Size. This information can be passed manually, using ZSTD_estimateDStreamSize, @@ -1001,7 +1098,7 @@ static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /**< t
-Advanced compression functions
+Advanced compression functions
ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);Create a digested dictionary for compression @@ -1011,22 +1108,26 @@ static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /**< t
ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); -@return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. - `estimatedSrcSize` value is optional, select 0 if not known +
@return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. + `estimatedSrcSize` value is optional, select 0 if not known
ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); -same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. - All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 +
same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. + All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0
size_t ZSTD_checkCParams(ZSTD_compressionParameters params); -Ensure param values remain within authorized range +
Ensure param values remain within authorized range. + @return 0 on success, or an error code (can be checked with ZSTD_isError())
ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);optimize params for a given `srcSize` and `dictSize`. - both values are optional, select `0` if unknown. + `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. + `dictSize` must be `0` when there is no dictionary. + cPar can be invalid : all parameters will be clamped within valid range in the @return struct. + This function never fails (wide contract)
size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, @@ -1072,10 +1173,10 @@ static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /**< t size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);Quick howto : - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure - - ZSTD_CCtxParam_setParameter() : Push parameters one by one into - an existing ZSTD_CCtx_params structure. - This is similar to - ZSTD_CCtx_setParameter(). + - ZSTD_CCtxParams_setParameter() : Push parameters one by one into + an existing ZSTD_CCtx_params structure. + This is similar to + ZSTD_CCtx_setParameter(). - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to an existing CCtx. These parameters will be applied to @@ -1105,7 +1206,7 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
-size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); +size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);Similar to ZSTD_CCtx_setParameter. Set one compression parameter, selected by enum ZSTD_cParameter. Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams(). @@ -1113,7 +1214,7 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
-size_t ZSTD_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); +size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);Similar to ZSTD_CCtx_getParameter. Get the requested value of one compression parameter, selected by enum ZSTD_cParameter. @result : 0, or an error code (which can be tested with ZSTD_isError()). @@ -1142,7 +1243,7 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
-Advanced decompression functions
+Advanced decompression functions
unsigned ZSTD_isFrame(const void* buffer, size_t size);Tells if the content of `buffer` starts with a valid Frame Identifier. @@ -1158,30 +1259,6 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params); it must remain read accessible throughout the lifetime of DDict
-unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); -Provides the dictID stored within dictionary. - if @return == 0, the dictionary is not conformant with Zstandard specification. - It can still be loaded, but as a content-only dictionary. -
- -unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); -Provides the dictID of the dictionary loaded into `ddict`. - If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. - Non-conformant dictionaries can still be loaded, but as content-only dictionaries. -
- -unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); -Provides the dictID required to decompressed the frame stored within `src`. - If @return == 0, the dictID could not be decoded. - This could for one of the following reasons : - - The frame does not require a dictionary to be decoded (most common case). - - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. - Note : this use case also happens when using a non-conformant dictionary. - - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). - - This is not a Zstandard frame. - When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. -
-size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);Same as ZSTD_DCtx_loadDictionary(), but references `dict` content instead of copying it into `dctx`. @@ -1228,20 +1305,74 @@ size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);
-Advanced streaming functions
Warning : most of these functions are now redundant with the Advanced API. +Advanced streaming functions
Warning : most of these functions are now redundant with the Advanced API. Once Advanced API reaches "stable" status, redundant functions will be deprecated, and then at some point removed.-Advanced Streaming compression functions
size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);/**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */ -size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/ +Advanced Streaming compression functions
/**! ZSTD_initCStream_srcSize() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * pledgedSrcSize must be correct. If it is not known at init time, use + * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, + * "0" also disables frame content size field. It may be enabled in the future. + */ +size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); +/**! ZSTD_initCStream_usingDict() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * Creates of an internal CDict (incompatible with static CCtx), except if + * dict == NULL or dictSize < 8, in which case no dict is used. + * Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if + * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy. + */ +size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); +/**! ZSTD_initCStream_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setZstdParams(zcs, params); // Set the zstd params and leave the rest as-is + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. + */ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, - ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */ -size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ -size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */ + ZSTD_parameters params, unsigned long long pledgedSrcSize); +/**! ZSTD_initCStream_usingCDict() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * note : cdict will just be referenced, and must outlive compression session + */ +size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); +/**! ZSTD_initCStream_usingCDict_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setZstdFrameParams(zcs, fParams); // Set the zstd frame params and leave the rest as-is + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters. + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. + */ +size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);
size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); -start a new frame, using same parameters from previous frame. +
This function is deprecated, and is equivalent to: + ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + + start a new frame, using same parameters from previous frame. This is typically useful to skip dictionary loading stage, since it will re-use it in-place. Note that zcs must be init at least once before using ZSTD_resetCStream(). If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. @@ -1280,14 +1411,14 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict is referenced, it must outlive decompression session */ size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */
-Buffer-less and synchronous inner streaming functions
+Buffer-less and synchronous inner streaming functions
This is an advanced API, giving full control over buffer management, for users which need direct control over memory. But it's also a complex one, with several restrictions, documented below. Prefer normal streaming API for an easier experience.-Buffer-less streaming compression (synchronous mode)
+Buffer-less streaming compression (synchronous mode)
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. @@ -1323,7 +1454,7 @@ size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */ size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */
-Buffer-less streaming decompression (synchronous mode)
+Buffer-less streaming decompression (synchronous mode)
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. @@ -1405,7 +1536,7 @@ typedef struct { unsigned checksumFlag; } ZSTD_frameHeader;
-ZSTD_getFrameHeader() :
decode Frame Header, or requires larger `srcSize`. +ZSTD_getFrameHeader() :
decode Frame Header, or requires larger `srcSize`. @return : 0, `zfhPtr` is correctly filled, >0, `srcSize` is too small, value is wanted `srcSize` amount, or an error code, which can be tested using ZSTD_isError() @@ -1421,7 +1552,7 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned longtypedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
-Block level API
+Block level API
Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes). User will have to take in charge required information to regenerate data, such as compressed and content sizes. diff --git a/examples/.gitignore b/examples/.gitignore new file mode 100644 index 000000000000..d682cae38a8d --- /dev/null +++ b/examples/.gitignore @@ -0,0 +1,15 @@ +#build +simple_compression +simple_decompression +multiple_simple_compression +dictionary_compression +dictionary_decompression +streaming_compression +streaming_decompression +multiple_streaming_compression +streaming_memory_usage + +#test artefact +tmp* +test* +*.zst diff --git a/examples/Makefile b/examples/Makefile new file mode 100644 index 000000000000..cd995f2f8b48 --- /dev/null +++ b/examples/Makefile @@ -0,0 +1,90 @@ +# ################################################################ +# Copyright (c) 2016-present, Yann Collet, Facebook, Inc. +# All rights reserved. +# +# This source code is licensed under both the BSD-style license (found in the +# LICENSE file in the root directory of this source tree) and the GPLv2 (found +# in the COPYING file in the root directory of this source tree). +# ################################################################ + +# This Makefile presumes libzstd is installed, using `sudo make install` + +CPPFLAGS += -I../lib +LIB = ../lib/libzstd.a + +.PHONY: default all clean test + +default: all + +all: simple_compression simple_decompression \ + multiple_simple_compression\ + dictionary_compression dictionary_decompression \ + streaming_compression streaming_decompression \ + multiple_streaming_compression streaming_memory_usage + +$(LIB) : + $(MAKE) -C ../lib libzstd.a + +simple_compression : simple_compression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +simple_decompression : simple_decompression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +multiple_simple_compression : multiple_simple_compression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +dictionary_compression : dictionary_compression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +dictionary_decompression : dictionary_decompression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +streaming_compression : streaming_compression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +multiple_streaming_compression : multiple_streaming_compression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +streaming_decompression : streaming_decompression.c common.h $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +streaming_memory_usage : streaming_memory_usage.c $(LIB) + $(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@ + +clean: + @rm -f core *.o tmp* result* *.zst \ + simple_compression simple_decompression \ + multiple_simple_compression \ + dictionary_compression dictionary_decompression \ + streaming_compression streaming_decompression \ + multiple_streaming_compression streaming_memory_usage + @echo Cleaning completed + +test: all + cp README.md tmp + cp Makefile tmp2 + @echo -- Simple compression tests + ./simple_compression tmp + ./simple_decompression tmp.zst + ./multiple_simple_compression *.c + ./streaming_decompression tmp.zst > /dev/null + @echo -- Streaming memory usage + ./streaming_memory_usage + @echo -- Streaming compression tests + ./streaming_compression tmp + ./streaming_decompression tmp.zst > /dev/null + @echo -- Edge cases detection + ! ./streaming_decompression tmp # invalid input, must fail + ! ./simple_decompression tmp # invalid input, must fail + ! ./simple_decompression tmp.zst # unknown input size, must fail + touch tmpNull # create 0-size file + ./simple_compression tmpNull + ./simple_decompression tmpNull.zst # 0-size frame : must work + @echo -- Multiple streaming tests + ./multiple_streaming_compression *.c + @echo -- Dictionary compression tests + ./dictionary_compression tmp2 tmp README.md + ./dictionary_decompression tmp2.zst tmp.zst README.md + $(RM) tmp* *.zst + @echo tests completed diff --git a/examples/README.md b/examples/README.md new file mode 100644 index 000000000000..0bff7ac19a29 --- /dev/null +++ b/examples/README.md @@ -0,0 +1,46 @@ +Zstandard library : usage examples +================================== + +- [Simple compression](simple_compression.c) : + Compress a single file. + Introduces usage of : `ZSTD_compress()` + +- [Simple decompression](simple_decompression.c) : + Decompress a single file. + Only compatible with simple compression. + Result remains in memory. + Introduces usage of : `ZSTD_decompress()` + +- [Multiple simple compression](multiple_simple_compression.c) : + Compress multiple files (in simple mode) in a single command line. + Demonstrates memory preservation technique that + minimizes malloc()/free() calls by re-using existing resources. + Introduces usage of : `ZSTD_compressCCtx()` + +- [Streaming memory usage](streaming_memory_usage.c) : + Provides amount of memory used by streaming context. + Introduces usage of : `ZSTD_sizeof_CStream()` + +- [Streaming compression](streaming_compression.c) : + Compress a single file. + Introduces usage of : `ZSTD_compressStream()` + +- [Multiple Streaming compression](multiple_streaming_compression.c) : + Compress multiple files (in streaming mode) in a single command line. + Introduces memory usage preservation technique, + reducing impact of malloc()/free() and memset() by re-using existing resources. + +- [Streaming decompression](streaming_decompression.c) : + Decompress a single file compressed by zstd. + Compatible with both simple and streaming compression. + Result is sent to stdout. + Introduces usage of : `ZSTD_decompressStream()` + +- [Dictionary compression](dictionary_compression.c) : + Compress multiple files using the same dictionary. + Introduces usage of : `ZSTD_createCDict()` and `ZSTD_compress_usingCDict()` + +- [Dictionary decompression](dictionary_decompression.c) : + Decompress multiple files using the same dictionary. + Result remains in memory. + Introduces usage of : `ZSTD_createDDict()` and `ZSTD_decompress_usingDDict()` diff --git a/examples/common.h b/examples/common.h new file mode 100644 index 000000000000..a714cbb72c36 --- /dev/null +++ b/examples/common.h @@ -0,0 +1,234 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* + * This header file has common utility functions used in examples. + */ +#ifndef COMMON_H +#define COMMON_H + +#include
// malloc, free, exit +#include // fprintf, perror, fopen, etc. +#include // strerror +#include // errno +#include // stat +#include + +/* + * Define the returned error code from utility functions. + */ +typedef enum { + ERROR_fsize = 1, + ERROR_fopen = 2, + ERROR_fclose = 3, + ERROR_fread = 4, + ERROR_fwrite = 5, + ERROR_loadFile = 6, + ERROR_saveFile = 7, + ERROR_malloc = 8, + ERROR_largeFile = 9, +} COMMON_ErrorCode; + +/*! CHECK + * Check that the condition holds. If it doesn't print a message and die. + */ +#define CHECK(cond, ...) \ + do { \ + if (!(cond)) { \ + fprintf(stderr, \ + "%s:%d CHECK(%s) failed: ", \ + __FILE__, \ + __LINE__, \ + #cond); \ + fprintf(stderr, "" __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + exit(1); \ + } \ + } while (0) + +/*! CHECK_ZSTD + * Check the zstd error code and die if an error occurred after printing a + * message. + */ +#define CHECK_ZSTD(fn, ...) \ + do { \ + size_t const err = (fn); \ + CHECK(!ZSTD_isError(err), "%s", ZSTD_getErrorName(err)); \ + } while (0) + +/*! fsize_orDie() : + * Get the size of a given file path. + * + * @return The size of a given file path. + */ +static size_t fsize_orDie(const char *filename) +{ + struct stat st; + if (stat(filename, &st) != 0) { + /* error */ + perror(filename); + exit(ERROR_fsize); + } + + off_t const fileSize = st.st_size; + size_t const size = (size_t)fileSize; + /* 1. fileSize should be non-negative, + * 2. if off_t -> size_t type conversion results in discrepancy, + * the file size is too large for type size_t. + */ + if ((fileSize < 0) || (fileSize != (off_t)size)) { + fprintf(stderr, "%s : filesize too large \n", filename); + exit(ERROR_largeFile); + } + return size; +} + +/*! fopen_orDie() : + * Open a file using given file path and open option. + * + * @return If successful this function will return a FILE pointer to an + * opened file otherwise it sends an error to stderr and exits. + */ +static FILE* fopen_orDie(const char *filename, const char *instruction) +{ + FILE* const inFile = fopen(filename, instruction); + if (inFile) return inFile; + /* error */ + perror(filename); + exit(ERROR_fopen); +} + +/*! fclose_orDie() : + * Close an opened file using given FILE pointer. + */ +static void fclose_orDie(FILE* file) +{ + if (!fclose(file)) { return; }; + /* error */ + perror("fclose"); + exit(ERROR_fclose); +} + +/*! fread_orDie() : + * + * Read sizeToRead bytes from a given file, storing them at the + * location given by buffer. + * + * @return The number of bytes read. + */ +static size_t fread_orDie(void* buffer, size_t sizeToRead, FILE* file) +{ + size_t const readSize = fread(buffer, 1, sizeToRead, file); + if (readSize == sizeToRead) return readSize; /* good */ + if (feof(file)) return readSize; /* good, reached end of file */ + /* error */ + perror("fread"); + exit(ERROR_fread); +} + +/*! fwrite_orDie() : + * + * Write sizeToWrite bytes to a file pointed to by file, obtaining + * them from a location given by buffer. + * + * Note: This function will send an error to stderr and exit if it + * cannot write data to the given file pointer. + * + * @return The number of bytes written. + */ +static size_t fwrite_orDie(const void* buffer, size_t sizeToWrite, FILE* file) +{ + size_t const writtenSize = fwrite(buffer, 1, sizeToWrite, file); + if (writtenSize == sizeToWrite) return sizeToWrite; /* good */ + /* error */ + perror("fwrite"); + exit(ERROR_fwrite); +} + +/*! malloc_orDie() : + * Allocate memory. + * + * @return If successful this function returns a pointer to allo- + * cated memory. If there is an error, this function will send that + * error to stderr and exit. + */ +static void* malloc_orDie(size_t size) +{ + void* const buff = malloc(size); + if (buff) return buff; + /* error */ + perror("malloc"); + exit(ERROR_malloc); +} + +/*! loadFile_orDie() : + * load file into buffer (memory). + * + * Note: This function will send an error to stderr and exit if it + * cannot read data from the given file path. + * + * @return If successful this function will load file into buffer and + * return file size, otherwise it will printout an error to stderr and exit. + */ +static size_t loadFile_orDie(const char* fileName, void* buffer, size_t bufferSize) +{ + size_t const fileSize = fsize_orDie(fileName); + CHECK(fileSize <= bufferSize, "File too large!"); + + FILE* const inFile = fopen_orDie(fileName, "rb"); + size_t const readSize = fread(buffer, 1, fileSize, inFile); + if (readSize != (size_t)fileSize) { + fprintf(stderr, "fread: %s : %s \n", fileName, strerror(errno)); + exit(ERROR_fread); + } + fclose(inFile); /* can't fail, read only */ + return fileSize; +} + +/*! mallocAndLoadFile_orDie() : + * allocate memory buffer and then load file into it. + * + * Note: This function will send an error to stderr and exit if memory allocation + * fails or it cannot read data from the given file path. + * + * @return If successful this function will return buffer and bufferSize(=fileSize), + * otherwise it will printout an error to stderr and exit. + */ +static void* mallocAndLoadFile_orDie(const char* fileName, size_t* bufferSize) { + size_t const fileSize = fsize_orDie(fileName); + *bufferSize = fileSize; + void* const buffer = malloc_orDie(*bufferSize); + loadFile_orDie(fileName, buffer, *bufferSize); + return buffer; +} + +/*! saveFile_orDie() : + * + * Save buffSize bytes to a given file path, obtaining them from a location pointed + * to by buff. + * + * Note: This function will send an error to stderr and exit if it + * cannot write to a given file. + */ +static void saveFile_orDie(const char* fileName, const void* buff, size_t buffSize) +{ + FILE* const oFile = fopen_orDie(fileName, "wb"); + size_t const wSize = fwrite(buff, 1, buffSize, oFile); + if (wSize != (size_t)buffSize) { + fprintf(stderr, "fwrite: %s : %s \n", fileName, strerror(errno)); + exit(ERROR_fwrite); + } + if (fclose(oFile)) { + perror(fileName); + exit(ERROR_fclose); + } +} + +#endif diff --git a/examples/dictionary_compression.c b/examples/dictionary_compression.c new file mode 100644 index 000000000000..9efdb785c112 --- /dev/null +++ b/examples/dictionary_compression.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ +#include // printf +#include // free +#include // memset, strcat +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +/* createDict() : + `dictFileName` is supposed to have been created using `zstd --train` */ +static ZSTD_CDict* createCDict_orDie(const char* dictFileName, int cLevel) +{ + size_t dictSize; + printf("loading dictionary %s \n", dictFileName); + void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize); + ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, cLevel); + CHECK(cdict != NULL, "ZSTD_createCDict() failed!"); + free(dictBuffer); + return cdict; +} + + +static void compress(const char* fname, const char* oname, const ZSTD_CDict* cdict) +{ + size_t fSize; + void* const fBuff = mallocAndLoadFile_orDie(fname, &fSize); + size_t const cBuffSize = ZSTD_compressBound(fSize); + void* const cBuff = malloc_orDie(cBuffSize); + + /* Compress using the dictionary. + * This function writes the dictionary id, and content size into the header. + * But, it doesn't use a checksum. You can control these options using the + * advanced API: ZSTD_CCtx_setParameter(), ZSTD_CCtx_refCDict(), + * and ZSTD_compress2(). + */ + ZSTD_CCtx* const cctx = ZSTD_createCCtx(); + CHECK(cctx != NULL, "ZSTD_createCCtx() failed!"); + size_t const cSize = ZSTD_compress_usingCDict(cctx, cBuff, cBuffSize, fBuff, fSize, cdict); + CHECK_ZSTD(cSize); + + saveFile_orDie(oname, cBuff, cSize); + + /* success */ + printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname); + + ZSTD_freeCCtx(cctx); /* never fails */ + free(fBuff); + free(cBuff); +} + + +static char* createOutFilename_orDie(const char* filename) +{ + size_t const inL = strlen(filename); + size_t const outL = inL + 5; + void* outSpace = malloc_orDie(outL); + memset(outSpace, 0, outL); + strcat(outSpace, filename); + strcat(outSpace, ".zst"); + return (char*)outSpace; +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + int const cLevel = 3; + + if (argc<3) { + fprintf(stderr, "wrong arguments\n"); + fprintf(stderr, "usage:\n"); + fprintf(stderr, "%s [FILES] dictionary\n", exeName); + return 1; + } + + /* load dictionary only once */ + const char* const dictName = argv[argc-1]; + ZSTD_CDict* const dictPtr = createCDict_orDie(dictName, cLevel); + + int u; + for (u=1; u // printf +#include // free +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +/* createDict() : + `dictFileName` is supposed to have been created using `zstd --train` */ +static ZSTD_DDict* createDict_orDie(const char* dictFileName) +{ + size_t dictSize; + printf("loading dictionary %s \n", dictFileName); + void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize); + ZSTD_DDict* const ddict = ZSTD_createDDict(dictBuffer, dictSize); + CHECK(ddict != NULL, "ZSTD_createDDict() failed!"); + free(dictBuffer); + return ddict; +} + +static void decompress(const char* fname, const ZSTD_DDict* ddict) +{ + size_t cSize; + void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize); + /* Read the content size from the frame header. For simplicity we require + * that it is always present. By default, zstd will write the content size + * in the header when it is known. If you can't guarantee that the frame + * content size is always written into the header, either use streaming + * decompression, or ZSTD_decompressBound(). + */ + unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize); + CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname); + CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname); + void* const rBuff = malloc_orDie((size_t)rSize); + + /* Check that the dictionary ID matches. + * If a non-zstd dictionary is used, then both will be zero. + * By default zstd always writes the dictionary ID into the frame. + * Zstd will check if there is a dictionary ID mismatch as well. + */ + unsigned const expectedDictID = ZSTD_getDictID_fromDDict(ddict); + unsigned const actualDictID = ZSTD_getDictID_fromFrame(cBuff, cSize); + CHECK(actualDictID == expectedDictID, + "DictID mismatch: expected %u got %u", + expectedDictID, + actualDictID); + + /* Decompress using the dictionary. + * If you need to control the decompression parameters, then use the + * advanced API: ZSTD_DCtx_setParameter(), ZSTD_DCtx_refDDict(), and + * ZSTD_decompressDCtx(). + */ + ZSTD_DCtx* const dctx = ZSTD_createDCtx(); + CHECK(dctx != NULL, "ZSTD_createDCtx() failed!"); + size_t const dSize = ZSTD_decompress_usingDDict(dctx, rBuff, rSize, cBuff, cSize, ddict); + CHECK_ZSTD(dSize); + /* When zstd knows the content size, it will error if it doesn't match. */ + CHECK(dSize == rSize, "Impossible because zstd will check this condition!"); + + /* success */ + printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize); + + ZSTD_freeDCtx(dctx); + free(rBuff); + free(cBuff); +} + + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc<3) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s [FILES] dictionary\n", exeName); + return 1; + } + + /* load dictionary only once */ + const char* const dictName = argv[argc-1]; + ZSTD_DDict* const dictPtr = createDict_orDie(dictName); + + int u; + for (u=1; u // printf +#include // free +#include // memcpy, strlen +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +typedef struct { + void* fBuffer; + void* cBuffer; + size_t fBufferSize; + size_t cBufferSize; + ZSTD_CCtx* cctx; +} resources; + +/* + * allocate memory for buffers big enough to compress all files + * as well as memory for output file name (ofn) + */ +static resources createResources_orDie(int argc, const char** argv, char **ofn, size_t* ofnBufferLen) +{ + size_t maxFilenameLength=0; + size_t maxFileSize = 0; + + int argNb; + for (argNb = 1; argNb < argc; argNb++) { + const char* const filename = argv[argNb]; + size_t const filenameLength = strlen(filename); + size_t const fileSize = fsize_orDie(filename); + + if (filenameLength > maxFilenameLength) maxFilenameLength = filenameLength; + if (fileSize > maxFileSize) maxFileSize = fileSize; + } + + resources ress; + ress.fBufferSize = maxFileSize; + ress.cBufferSize = ZSTD_compressBound(maxFileSize); + + *ofnBufferLen = maxFilenameLength + 5; + *ofn = (char*)malloc_orDie(*ofnBufferLen); + ress.fBuffer = malloc_orDie(ress.fBufferSize); + ress.cBuffer = malloc_orDie(ress.cBufferSize); + ress.cctx = ZSTD_createCCtx(); + CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!"); + return ress; +} + +static void freeResources(resources ress, char *outFilename) +{ + free(ress.fBuffer); + free(ress.cBuffer); + ZSTD_freeCCtx(ress.cctx); /* never fails */ + free(outFilename); +} + +/* compress with pre-allocated context (ZSTD_CCtx) and input/output buffers*/ +static void compressFile_orDie(resources ress, const char* fname, const char* oname) +{ + size_t fSize = loadFile_orDie(fname, ress.fBuffer, ress.fBufferSize); + + /* Compress using the context. + * If you need more control over parameters, use the advanced API: + * ZSTD_CCtx_setParameter(), and ZSTD_compress2(). + */ + size_t const cSize = ZSTD_compressCCtx(ress.cctx, ress.cBuffer, ress.cBufferSize, ress.fBuffer, fSize, 1); + CHECK_ZSTD(cSize); + + saveFile_orDie(oname, ress.cBuffer, cSize); + + /* success */ + printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname); +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc<2) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s FILE(s)\n", exeName); + return 1; + } + + /* memory allocation for outFilename and resources */ + char* outFilename; + size_t outFilenameBufferLen; + resources const ress = createResources_orDie(argc, argv, &outFilename, &outFilenameBufferLen); + + /* compress files with shared context, input and output buffers */ + int argNb; + for (argNb = 1; argNb < argc; argNb++) { + const char* const inFilename = argv[argNb]; + size_t const inFilenameLen = strlen(inFilename); + CHECK(inFilenameLen + 5 <= outFilenameBufferLen, "File name too long!"); + memcpy(outFilename, inFilename, inFilenameLen); + memcpy(outFilename+inFilenameLen, ".zst", 5); + compressFile_orDie(ress, inFilename, outFilename); + } + + /* free memory */ + freeResources(ress,outFilename); + + printf("compressed %i files \n", argc-1); + + return 0; +} diff --git a/examples/multiple_streaming_compression.c b/examples/multiple_streaming_compression.c new file mode 100644 index 000000000000..ad98b1bd1b09 --- /dev/null +++ b/examples/multiple_streaming_compression.c @@ -0,0 +1,133 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +/* The objective of this example is to show of to compress multiple successive files +* while preserving memory management. +* All structures and buffers will be created only once, +* and shared across all compression operations */ + +#include // printf +#include // free +#include // memset, strcat +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +typedef struct { + void* buffIn; + void* buffOut; + size_t buffInSize; + size_t buffOutSize; + ZSTD_CCtx* cctx; +} resources; + +static resources createResources_orDie(int cLevel) +{ + resources ress; + ress.buffInSize = ZSTD_CStreamInSize(); /* can always read one full block */ + ress.buffOutSize= ZSTD_CStreamOutSize(); /* can always flush a full block */ + ress.buffIn = malloc_orDie(ress.buffInSize); + ress.buffOut= malloc_orDie(ress.buffOutSize); + ress.cctx = ZSTD_createCCtx(); + CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!"); + + /* Set any compression parameters you want here. + * They will persist for every compression operation. + * Here we set the compression level, and enable the checksum. + */ + CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, cLevel) ); + CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, 1) ); + return ress; +} + +static void freeResources(resources ress) +{ + ZSTD_freeCCtx(ress.cctx); + free(ress.buffIn); + free(ress.buffOut); +} + +static void compressFile_orDie(resources ress, const char* fname, const char* outName) +{ + // Open the input and output files. + FILE* const fin = fopen_orDie(fname, "rb"); + FILE* const fout = fopen_orDie(outName, "wb"); + + /* Reset the context to a clean state to start a new compression operation. + * The parameters are sticky, so we keep the compression level and extra + * parameters that we set in createResources_orDie(). + */ + CHECK_ZSTD( ZSTD_CCtx_reset(ress.cctx, ZSTD_reset_session_only) ); + + size_t const toRead = ress.buffInSize; + size_t read; + while ( (read = fread_orDie(ress.buffIn, toRead, fin)) ) { + /* This loop is the same as streaming_compression.c. + * See that file for detailed comments. + */ + int const lastChunk = (read < toRead); + ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue; + + ZSTD_inBuffer input = { ress.buffIn, read, 0 }; + int finished; + do { + ZSTD_outBuffer output = { ress.buffOut, ress.buffOutSize, 0 }; + size_t const remaining = ZSTD_compressStream2(ress.cctx, &output, &input, mode); + CHECK_ZSTD(remaining); + fwrite_orDie(ress.buffOut, output.pos, fout); + finished = lastChunk ? (remaining == 0) : (input.pos == input.size); + } while (!finished); + CHECK(input.pos == input.size, + "Impossible: zstd only returns 0 when the input is completely consumed!"); + } + + fclose_orDie(fout); + fclose_orDie(fin); +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc<2) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s FILE(s)\n", exeName); + return 1; + } + + int const cLevel = 7; + resources const ress = createResources_orDie(cLevel); + void* ofnBuffer = NULL; + size_t ofnbSize = 0; + + int argNb; + for (argNb = 1; argNb < argc; argNb++) { + const char* const ifn = argv[argNb]; + size_t const ifnSize = strlen(ifn); + size_t const ofnSize = ifnSize + 5; + if (ofnbSize <= ofnSize) { + ofnbSize = ofnSize + 16; + free(ofnBuffer); + ofnBuffer = malloc_orDie(ofnbSize); + } + memset(ofnBuffer, 0, ofnSize); + strcat(ofnBuffer, ifn); + strcat(ofnBuffer, ".zst"); + compressFile_orDie(ress, ifn, ofnBuffer); + } + + freeResources(ress); + free(ofnBuffer); + + printf("compressed %i files \n", argc-1); + + return 0; +} diff --git a/examples/simple_compression.c b/examples/simple_compression.c new file mode 100644 index 000000000000..019a143d4c85 --- /dev/null +++ b/examples/simple_compression.c @@ -0,0 +1,68 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include // printf +#include // free +#include // strlen, strcat, memset +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +static void compress_orDie(const char* fname, const char* oname) +{ + size_t fSize; + void* const fBuff = mallocAndLoadFile_orDie(fname, &fSize); + size_t const cBuffSize = ZSTD_compressBound(fSize); + void* const cBuff = malloc_orDie(cBuffSize); + + /* Compress. + * If you are doing many compressions, you may want to reuse the context. + * See the multiple_simple_compression.c example. + */ + size_t const cSize = ZSTD_compress(cBuff, cBuffSize, fBuff, fSize, 1); + CHECK_ZSTD(cSize); + + saveFile_orDie(oname, cBuff, cSize); + + /* success */ + printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname); + + free(fBuff); + free(cBuff); +} + +static char* createOutFilename_orDie(const char* filename) +{ + size_t const inL = strlen(filename); + size_t const outL = inL + 5; + void* const outSpace = malloc_orDie(outL); + memset(outSpace, 0, outL); + strcat(outSpace, filename); + strcat(outSpace, ".zst"); + return (char*)outSpace; +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc!=2) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s FILE\n", exeName); + return 1; + } + + const char* const inFilename = argv[1]; + + char* const outFilename = createOutFilename_orDie(inFilename); + compress_orDie(inFilename, outFilename); + free(outFilename); + return 0; +} diff --git a/examples/simple_decompression.c b/examples/simple_decompression.c new file mode 100644 index 000000000000..1aa57c7b0934 --- /dev/null +++ b/examples/simple_decompression.c @@ -0,0 +1,65 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include // printf +#include // free +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +static void decompress(const char* fname) +{ + size_t cSize; + void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize); + /* Read the content size from the frame header. For simplicity we require + * that it is always present. By default, zstd will write the content size + * in the header when it is known. If you can't guarantee that the frame + * content size is always written into the header, either use streaming + * decompression, or ZSTD_decompressBound(). + */ + unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize); + CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname); + CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname); + + void* const rBuff = malloc_orDie((size_t)rSize); + + /* Decompress. + * If you are doing many decompressions, you may want to reuse the context + * and use ZSTD_decompressDCtx(). If you want to set advanced parameters, + * use ZSTD_DCtx_setParameter(). + */ + size_t const dSize = ZSTD_decompress(rBuff, rSize, cBuff, cSize); + CHECK_ZSTD(dSize); + /* When zstd knows the content size, it will error if it doesn't match. */ + CHECK(dSize == rSize, "Impossible because zstd will check this condition!"); + + /* success */ + printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize); + + free(rBuff); + free(cBuff); +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc!=2) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s FILE\n", exeName); + return 1; + } + + decompress(argv[1]); + + printf("%s correctly decoded (in memory). \n", argv[1]); + + return 0; +} diff --git a/examples/streaming_compression.c b/examples/streaming_compression.c new file mode 100644 index 000000000000..d1353a684a62 --- /dev/null +++ b/examples/streaming_compression.c @@ -0,0 +1,119 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +#include // printf +#include // free +#include // memset, strcat, strlen +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + + +static void compressFile_orDie(const char* fname, const char* outName, int cLevel) +{ + /* Open the input and output files. */ + FILE* const fin = fopen_orDie(fname, "rb"); + FILE* const fout = fopen_orDie(outName, "wb"); + /* Create the input and output buffers. + * They may be any size, but we recommend using these functions to size them. + * Performance will only suffer significantly for very tiny buffers. + */ + size_t const buffInSize = ZSTD_CStreamInSize(); + void* const buffIn = malloc_orDie(buffInSize); + size_t const buffOutSize = ZSTD_CStreamOutSize(); + void* const buffOut = malloc_orDie(buffOutSize); + + /* Create the context. */ + ZSTD_CCtx* const cctx = ZSTD_createCCtx(); + CHECK(cctx != NULL, "ZSTD_createCCtx() failed!"); + + /* Set any parameters you want. + * Here we set the compression level, and enable the checksum. + */ + CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, cLevel) ); + CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1) ); + + /* This loop read from the input file, compresses that entire chunk, + * and writes all output produced to the output file. + */ + size_t const toRead = buffInSize; + size_t read; + while ((read = fread_orDie(buffIn, toRead, fin))) { + /* Select the flush mode. + * If the read may not be finished (read == toRead) we use + * ZSTD_e_continue. If this is the last chunk, we use ZSTD_e_end. + * Zstd optimizes the case where the first flush mode is ZSTD_e_end, + * since it knows it is compressing the entire source in one pass. + */ + int const lastChunk = (read < toRead); + ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue; + /* Set the input buffer to what we just read. + * We compress until the input buffer is empty, each time flushing the + * output. + */ + ZSTD_inBuffer input = { buffIn, read, 0 }; + int finished; + do { + /* Compress into the output buffer and write all of the output to + * the file so we can reuse the buffer next iteration. + */ + ZSTD_outBuffer output = { buffOut, buffOutSize, 0 }; + size_t const remaining = ZSTD_compressStream2(cctx, &output , &input, mode); + CHECK_ZSTD(remaining); + fwrite_orDie(buffOut, output.pos, fout); + /* If we're on the last chunk we're finished when zstd returns 0, + * which means its consumed all the input AND finished the frame. + * Otherwise, we're finished when we've consumed all the input. + */ + finished = lastChunk ? (remaining == 0) : (input.pos == input.size); + } while (!finished); + CHECK(input.pos == input.size, + "Impossible: zstd only returns 0 when the input is completely consumed!"); + } + + ZSTD_freeCCtx(cctx); + fclose_orDie(fout); + fclose_orDie(fin); + free(buffIn); + free(buffOut); +} + + +static char* createOutFilename_orDie(const char* filename) +{ + size_t const inL = strlen(filename); + size_t const outL = inL + 5; + void* const outSpace = malloc_orDie(outL); + memset(outSpace, 0, outL); + strcat(outSpace, filename); + strcat(outSpace, ".zst"); + return (char*)outSpace; +} + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc!=2) { + printf("wrong arguments\n"); + printf("usage:\n"); + printf("%s FILE\n", exeName); + return 1; + } + + const char* const inFilename = argv[1]; + + char* const outFilename = createOutFilename_orDie(inFilename); + compressFile_orDie(inFilename, outFilename, 1); + + free(outFilename); /* not strictly required, since program execution stops there, + * but some static analyzer main complain otherwise */ + return 0; +} diff --git a/examples/streaming_decompression.c b/examples/streaming_decompression.c new file mode 100644 index 000000000000..bcd861b756c1 --- /dev/null +++ b/examples/streaming_decompression.c @@ -0,0 +1,82 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +#include // fprintf +#include // free +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + +static void decompressFile_orDie(const char* fname) +{ + FILE* const fin = fopen_orDie(fname, "rb"); + size_t const buffInSize = ZSTD_DStreamInSize(); + void* const buffIn = malloc_orDie(buffInSize); + FILE* const fout = stdout; + size_t const buffOutSize = ZSTD_DStreamOutSize(); /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */ + void* const buffOut = malloc_orDie(buffOutSize); + + ZSTD_DCtx* const dctx = ZSTD_createDCtx(); + CHECK(dctx != NULL, "ZSTD_createDCtx() failed!"); + + /* This loop assumes that the input file is one or more concatenated zstd + * streams. This example won't work if there is trailing non-zstd data at + * the end, but streaming decompression in general handles this case. + * ZSTD_decompressStream() returns 0 exactly when the frame is completed, + * and doesn't consume input after the frame. + */ + size_t const toRead = buffInSize; + size_t read; + while ( (read = fread_orDie(buffIn, toRead, fin)) ) { + ZSTD_inBuffer input = { buffIn, read, 0 }; + /* Given a valid frame, zstd won't consume the last byte of the frame + * until it has flushed all of the decompressed data of the frame. + * Therefore, instead of checking if the return code is 0, we can + * decompress just check if input.pos < input.size. + */ + while (input.pos < input.size) { + ZSTD_outBuffer output = { buffOut, buffOutSize, 0 }; + /* The return code is zero if the frame is complete, but there may + * be multiple frames concatenated together. Zstd will automatically + * reset the context when a frame is complete. Still, calling + * ZSTD_DCtx_reset() can be useful to reset the context to a clean + * state, for instance if the last decompression call returned an + * error. + */ + size_t const ret = ZSTD_decompressStream(dctx, &output , &input); + CHECK_ZSTD(ret); + fwrite_orDie(buffOut, output.pos, fout); + } + } + + ZSTD_freeDCtx(dctx); + fclose_orDie(fin); + fclose_orDie(fout); + free(buffIn); + free(buffOut); +} + + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc!=2) { + fprintf(stderr, "wrong arguments\n"); + fprintf(stderr, "usage:\n"); + fprintf(stderr, "%s FILE\n", exeName); + return 1; + } + + const char* const inFilename = argv[1]; + + decompressFile_orDie(inFilename); + return 0; +} diff --git a/examples/streaming_memory_usage.c b/examples/streaming_memory_usage.c new file mode 100644 index 000000000000..26835788abed --- /dev/null +++ b/examples/streaming_memory_usage.c @@ -0,0 +1,137 @@ +/* + * Copyright (c) 2017-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +/*=== Tuning parameter ===*/ +#ifndef MAX_TESTED_LEVEL +#define MAX_TESTED_LEVEL 12 +#endif + + +/*=== Dependencies ===*/ +#include // printf +#define ZSTD_STATIC_LINKING_ONLY +#include // presumes zstd library is installed +#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD() + + +/*=== functions ===*/ + +/*! readU32FromChar() : + @return : unsigned integer value read from input in `char` format + allows and interprets K, KB, KiB, M, MB and MiB suffix. + Will also modify `*stringPtr`, advancing it to position where it stopped reading. + Note : function result can overflow if digit string > MAX_UINT */ +static unsigned readU32FromChar(const char** stringPtr) +{ + unsigned result = 0; + while ((**stringPtr >='0') && (**stringPtr <='9')) + result *= 10, result += **stringPtr - '0', (*stringPtr)++ ; + if ((**stringPtr=='K') || (**stringPtr=='M')) { + result <<= 10; + if (**stringPtr=='M') result <<= 10; + (*stringPtr)++ ; + if (**stringPtr=='i') (*stringPtr)++; + if (**stringPtr=='B') (*stringPtr)++; + } + return result; +} + + +int main(int argc, char const *argv[]) { + + printf("\n Zstandard (v%s) memory usage for streaming : \n\n", ZSTD_versionString()); + + unsigned wLog = 0; + if (argc > 1) { + const char* valStr = argv[1]; + wLog = readU32FromChar(&valStr); + } + + int compressionLevel; + for (compressionLevel = 1; compressionLevel <= MAX_TESTED_LEVEL; compressionLevel++) { +#define INPUT_SIZE 5 +#define COMPRESSED_SIZE 128 + char const dataToCompress[INPUT_SIZE] = "abcde"; + char compressedData[COMPRESSED_SIZE]; + char decompressedData[INPUT_SIZE]; + /* the ZSTD_CCtx_params structure is a way to save parameters and use + * them across multiple contexts. We use them here so we can call the + * function ZSTD_estimateCStreamSize_usingCCtxParams(). + */ + ZSTD_CCtx_params* const cctxParams = ZSTD_createCCtxParams(); + CHECK(cctxParams != NULL, "ZSTD_createCCtxParams() failed!"); + + /* Set the compression level. */ + CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, compressionLevel) ); + /* Set the window log. + * The value 0 means use the default window log, which is equivalent to + * not setting it. + */ + CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_windowLog, wLog) ); + + /* Force the compressor to allocate the maximum memory size for a given + * level by not providing the pledged source size, or calling + * ZSTD_compressStream2() with ZSTD_e_end. + */ + ZSTD_CCtx* const cctx = ZSTD_createCCtx(); + CHECK(cctx != NULL, "ZSTD_createCCtx() failed!"); + CHECK_ZSTD( ZSTD_CCtx_setParametersUsingCCtxParams(cctx, cctxParams) ); + size_t compressedSize; + { + ZSTD_inBuffer inBuff = { dataToCompress, sizeof(dataToCompress), 0 }; + ZSTD_outBuffer outBuff = { compressedData, sizeof(compressedData), 0 }; + CHECK_ZSTD( ZSTD_compressStream(cctx, &outBuff, &inBuff) ); + size_t const remaining = ZSTD_endStream(cctx, &outBuff); + CHECK_ZSTD(remaining); + CHECK(remaining == 0, "Frame not flushed!"); + compressedSize = outBuff.pos; + } + + ZSTD_DCtx* const dctx = ZSTD_createDCtx(); + CHECK(dctx != NULL, "ZSTD_createDCtx() failed!"); + /* Set the maximum allowed window log. + * The value 0 means use the default window log, which is equivalent to + * not setting it. + */ + CHECK_ZSTD( ZSTD_DCtx_setParameter(dctx, ZSTD_d_windowLogMax, wLog) ); + /* forces decompressor to use maximum memory size, since the + * decompressed size is not stored in the frame header. + */ + { ZSTD_inBuffer inBuff = { compressedData, compressedSize, 0 }; + ZSTD_outBuffer outBuff = { decompressedData, sizeof(decompressedData), 0 }; + size_t const remaining = ZSTD_decompressStream(dctx, &outBuff, &inBuff); + CHECK_ZSTD(remaining); + CHECK(remaining == 0, "Frame not complete!"); + CHECK(outBuff.pos == sizeof(dataToCompress), "Bad decompression!"); + } + + size_t const cstreamSize = ZSTD_sizeof_CStream(cctx); + size_t const cstreamEstimatedSize = ZSTD_estimateCStreamSize_usingCCtxParams(cctxParams); + size_t const dstreamSize = ZSTD_sizeof_DStream(dctx); + size_t const dstreamEstimatedSize = ZSTD_estimateDStreamSize_fromFrame(compressedData, compressedSize); + + CHECK(cstreamSize <= cstreamEstimatedSize, "Compression mem (%u) > estimated (%u)", + (unsigned)cstreamSize, (unsigned)cstreamEstimatedSize); + CHECK(dstreamSize <= dstreamEstimatedSize, "Decompression mem (%u) > estimated (%u)", + (unsigned)dstreamSize, (unsigned)dstreamEstimatedSize); + + printf("Level %2i : Compression Mem = %5u KB (estimated : %5u KB) ; Decompression Mem = %4u KB (estimated : %5u KB)\n", + compressionLevel, + (unsigned)(cstreamSize>>10), (unsigned)(cstreamEstimatedSize>>10), + (unsigned)(dstreamSize>>10), (unsigned)(dstreamEstimatedSize>>10)); + + ZSTD_freeDCtx(dctx); + ZSTD_freeCCtx(cctx); + ZSTD_freeCCtxParams(cctxParams); + if (wLog) break; /* single test */ + } + return 0; +} diff --git a/lib/Makefile b/lib/Makefile index 386583e728b9..404f5b692101 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -25,7 +25,7 @@ endif CFLAGS ?= -O3 DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \ - -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \ + -Wstrict-prototypes -Wundef -Wpointer-arith \ -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \ -Wredundant-decls -Wmissing-prototypes -Wc++-compat CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS) @@ -56,6 +56,7 @@ ZSTD_FORCE_DECOMPRESS_SHORT ?= 0 ZSTD_FORCE_DECOMPRESS_LONG ?= 0 ZSTD_NO_INLINE ?= 0 ZSTD_STRIP_ERROR_STRINGS ?= 0 +ZSTD_LEGACY_MULTITHREADED_API ?= 0 ifeq ($(ZSTD_LIB_COMPRESSION), 0) ZSTD_LIB_DICTBUILDER = 0 @@ -107,6 +108,10 @@ ifneq ($(ZSTD_STRIP_ERROR_STRINGS), 0) CFLAGS += -DZSTD_STRIP_ERROR_STRINGS endif +ifneq ($(ZSTD_LEGACY_MULTITHREADED_API), 0) + CFLAGS += -DZSTD_LEGACY_MULTITHREADED_API +endif + ifneq ($(ZSTD_LEGACY_SUPPORT), 0) ifeq ($(shell test $(ZSTD_LEGACY_SUPPORT) -lt 8; echo $$?), 0) ZSTD_FILES += $(shell ls legacy/*.c | $(GREP) 'v0[$(ZSTD_LEGACY_SUPPORT)-7]') @@ -151,8 +156,7 @@ ifneq (,$(filter Windows%,$(OS))) LIBZSTD = dll\libzstd.dll $(LIBZSTD): $(ZSTD_FILES) @echo compiling dynamic library $(LIBVER) - @$(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -shared $^ -o $@ - dlltool -D $@ -d dll\libzstd.def -l dll\libzstd.lib + $(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -Wl,--out-implib,dll\libzstd.lib -shared $^ -o $@ else diff --git a/lib/README.md b/lib/README.md index 0c9cd6d58f3f..792729b1f9ba 100644 --- a/lib/README.md +++ b/lib/README.md @@ -31,8 +31,6 @@ note that it's necessary to request the `-pthread` flag during link stage. Multithreading capabilities are exposed via the [advanced API defined in `lib/zstd.h`](https://github.com/facebook/zstd/blob/v1.3.8/lib/zstd.h#L592). -This API is still labelled experimental, -but is expected to become "stable" in the near future. #### API @@ -110,6 +108,10 @@ The file structure is designed to make this selection manually achievable for an which removes the error messages that are otherwise returned by `ZSTD_getErrorName`. +- While invoking `make libzstd`, the build macro `ZSTD_LEGACY_MULTITHREADED_API=1` + will expose the deprecated `ZSTDMT` API exposed by `zstdmt_compress.h` in + the shared library, which is now hidden by default. + #### Windows : using MinGW+MSYS to create DLL diff --git a/lib/common/compiler.h b/lib/common/compiler.h index 7f561282ca35..0836e3ed27a3 100644 --- a/lib/common/compiler.h +++ b/lib/common/compiler.h @@ -40,7 +40,7 @@ /** * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant - * parameters. They must be inlined for the compiler to elimininate the constant + * parameters. They must be inlined for the compiler to eliminate the constant * branches. */ #define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR diff --git a/lib/common/fse.h b/lib/common/fse.h index f72c519b259d..811c670bddc3 100644 --- a/lib/common/fse.h +++ b/lib/common/fse.h @@ -358,7 +358,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size typedef enum { FSE_repeat_none, /**< Cannot use the previous table */ FSE_repeat_check, /**< Can use the previous table but it must be checked */ - FSE_repeat_valid /**< Can use the previous table and it is asumed to be valid */ + FSE_repeat_valid /**< Can use the previous table and it is assumed to be valid */ } FSE_repeat; /* ***************************************** diff --git a/lib/common/threading.c b/lib/common/threading.c index 8be8c8da948a..f3d4fa841843 100644 --- a/lib/common/threading.c +++ b/lib/common/threading.c @@ -14,8 +14,8 @@ * This file will hold wrapper for systems, which do not support pthreads */ -/* create fake symbol to avoid empty trnaslation unit warning */ -int g_ZSTD_threading_useles_symbol; +/* create fake symbol to avoid empty translation unit warning */ +int g_ZSTD_threading_useless_symbol; #if defined(ZSTD_MULTITHREAD) && defined(_WIN32) diff --git a/lib/common/xxhash.c b/lib/common/xxhash.c index 532b8161929d..30599aaae41f 100644 --- a/lib/common/xxhash.c +++ b/lib/common/xxhash.c @@ -66,10 +66,10 @@ /* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */ /*!XXH_FORCE_NATIVE_FORMAT : - * By default, xxHash library provides endian-independant Hash values, based on little-endian convention. + * By default, xxHash library provides endian-independent Hash values, based on little-endian convention. * Results are therefore identical for little-endian and big-endian CPU. * This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format. - * Should endian-independance be of no importance for your application, you may set the #define below to 1, + * Should endian-independence be of no importance for your application, you may set the #define below to 1, * to improve speed for Big-endian CPU. * This option has no impact on Little_Endian CPU. */ diff --git a/lib/common/zstd_internal.h b/lib/common/zstd_internal.h index edeb74b9c3a2..31f756ab5812 100644 --- a/lib/common/zstd_internal.h +++ b/lib/common/zstd_internal.h @@ -53,8 +53,50 @@ extern "C" { #undef MAX #define MIN(a,b) ((a)<(b) ? (a) : (b)) #define MAX(a,b) ((a)>(b) ? (a) : (b)) -#define CHECK_F(f) { size_t const errcod = f; if (ERR_isError(errcod)) return errcod; } /* check and Forward error code */ -#define CHECK_E(f, e) { size_t const errcod = f; if (ERR_isError(errcod)) return ERROR(e); } /* check and send Error code */ + +/** + * Return the specified error if the condition evaluates to true. + * + * In debug modes, prints additional information. In order to do that + * (particularly, printing the conditional that failed), this can't just wrap + * RETURN_ERROR(). + */ +#define RETURN_ERROR_IF(cond, err, ...) \ + if (cond) { \ + RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return ERROR(err); \ + } + +/** + * Unconditionally return the specified error. + * + * In debug modes, prints additional information. + */ +#define RETURN_ERROR(err, ...) \ + do { \ + RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return ERROR(err); \ + } while(0); + +/** + * If the provided expression evaluates to an error code, returns that error code. + * + * In debug modes, prints additional information. + */ +#define FORWARD_IF_ERROR(err, ...) \ + do { \ + size_t const err_code = (err); \ + if (ERR_isError(err_code)) { \ + RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return err_code; \ + } \ + } while(0); /*-************************************* @@ -200,6 +242,17 @@ typedef struct { U32 longLengthPos; } seqStore_t; +/** + * Contains the compressed frame size and an upper-bound for the decompressed frame size. + * Note: before using `compressedSize`, check for errors using ZSTD_isError(). + * similarly, before using `decompressedBound`, check for errors using: + * `decompressedBound != ZSTD_CONTENTSIZE_ERROR` + */ +typedef struct { + size_t compressedSize; + unsigned long long decompressedBound; +} ZSTD_frameSizeInfo; /* decompress & legacy */ + const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */ diff --git a/lib/compress/fse_compress.c b/lib/compress/fse_compress.c index 60f357bbd24e..68b47e109351 100644 --- a/lib/compress/fse_compress.c +++ b/lib/compress/fse_compress.c @@ -129,9 +129,9 @@ size_t FSE_buildCTable_wksp(FSE_CTable* ct, { U32 position = 0; U32 symbol; for (symbol=0; symbol<=maxSymbolValue; symbol++) { - int nbOccurences; + int nbOccurrences; int const freq = normalizedCounter[symbol]; - for (nbOccurences=0; nbOccurences highThreshold) diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c index c2c9d3bc553d..2e163c8bf3d4 100644 --- a/lib/compress/zstd_compress.c +++ b/lib/compress/zstd_compress.c @@ -103,12 +103,31 @@ ZSTD_CCtx* ZSTD_initStaticCCtx(void *workspace, size_t workspaceSize) return cctx; } +/** + * Clears and frees all of the dictionaries in the CCtx. + */ +static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx) +{ + ZSTD_free(cctx->localDict.dictBuffer, cctx->customMem); + ZSTD_freeCDict(cctx->localDict.cdict); + memset(&cctx->localDict, 0, sizeof(cctx->localDict)); + memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); + cctx->cdict = NULL; +} + +static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict) +{ + size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0; + size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict); + return bufferSize + cdictSize; +} + static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx) { assert(cctx != NULL); assert(cctx->staticSize == 0); ZSTD_free(cctx->workSpace, cctx->customMem); cctx->workSpace = NULL; - ZSTD_freeCDict(cctx->cdictLocal); cctx->cdictLocal = NULL; + ZSTD_clearAllDicts(cctx); #ifdef ZSTD_MULTITHREAD ZSTDMT_freeCCtx(cctx->mtctx); cctx->mtctx = NULL; #endif @@ -117,7 +136,8 @@ static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx) size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx) { if (cctx==NULL) return 0; /* support free on NULL */ - if (cctx->staticSize) return ERROR(memory_allocation); /* not compatible with static CCtx */ + RETURN_ERROR_IF(cctx->staticSize, memory_allocation, + "not compatible with static CCtx"); ZSTD_freeCCtxContent(cctx); ZSTD_free(cctx, cctx->customMem); return 0; @@ -139,7 +159,7 @@ size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx) { if (cctx==NULL) return 0; /* support sizeof on NULL */ return sizeof(*cctx) + cctx->workSpaceSize - + ZSTD_sizeof_CDict(cctx->cdictLocal) + + ZSTD_sizeof_localDict(cctx->localDict) + ZSTD_sizeof_mtctx(cctx); } @@ -195,7 +215,7 @@ size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params) } size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) { - if (!cctxParams) { return ERROR(GENERIC); } + RETURN_ERROR_IF(!cctxParams, GENERIC); memset(cctxParams, 0, sizeof(*cctxParams)); cctxParams->compressionLevel = compressionLevel; cctxParams->fParams.contentSizeFlag = 1; @@ -204,8 +224,8 @@ size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params) { - if (!cctxParams) { return ERROR(GENERIC); } - CHECK_F( ZSTD_checkCParams(params.cParams) ); + RETURN_ERROR_IF(!cctxParams, GENERIC); + FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) ); memset(cctxParams, 0, sizeof(*cctxParams)); cctxParams->cParams = params.cParams; cctxParams->fParams = params.fParams; @@ -359,6 +379,12 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param) bounds.upperBound = ZSTD_dictForceCopy; /* note : how to ensure at compile time that this is the highest value enum ? */ return bounds; + case ZSTD_c_literalCompressionMode: + ZSTD_STATIC_ASSERT(ZSTD_lcm_auto < ZSTD_lcm_huffman && ZSTD_lcm_huffman < ZSTD_lcm_uncompressed); + bounds.lowerBound = ZSTD_lcm_auto; + bounds.upperBound = ZSTD_lcm_uncompressed; + return bounds; + default: { ZSTD_bounds const boundError = { ERROR(parameter_unsupported), 0, 0 }; return boundError; @@ -378,10 +404,22 @@ static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value) return 1; } -#define BOUNDCHECK(cParam, val) { \ - if (!ZSTD_cParam_withinBounds(cParam,val)) { \ - return ERROR(parameter_outOfBound); \ -} } +/* ZSTD_cParam_clampBounds: + * Clamps the value into the bounded range. + */ +static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value) +{ + ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); + if (ZSTD_isError(bounds.error)) return bounds.error; + if (*value < bounds.lowerBound) *value = bounds.lowerBound; + if (*value > bounds.upperBound) *value = bounds.upperBound; + return 0; +} + +#define BOUNDCHECK(cParam, val) { \ + RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \ + parameter_outOfBound); \ +} static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) @@ -413,6 +451,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) case ZSTD_c_ldmBucketSizeLog: case ZSTD_c_ldmHashRateLog: case ZSTD_c_forceAttachDict: + case ZSTD_c_literalCompressionMode: default: return 0; } @@ -425,18 +464,17 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) if (ZSTD_isUpdateAuthorized(param)) { cctx->cParamsChanged = 1; } else { - return ERROR(stage_wrong); + RETURN_ERROR(stage_wrong); } } switch(param) { - case ZSTD_c_format : - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); + case ZSTD_c_nbWorkers: + RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported, + "MT not compatible with static alloc"); + break; case ZSTD_c_compressionLevel: - if (cctx->cdict) return ERROR(stage_wrong); - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - case ZSTD_c_windowLog: case ZSTD_c_hashLog: case ZSTD_c_chainLog: @@ -444,49 +482,32 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) case ZSTD_c_minMatch: case ZSTD_c_targetLength: case ZSTD_c_strategy: - if (cctx->cdict) return ERROR(stage_wrong); - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - + case ZSTD_c_ldmHashRateLog: + case ZSTD_c_format: case ZSTD_c_contentSizeFlag: case ZSTD_c_checksumFlag: case ZSTD_c_dictIDFlag: - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - - case ZSTD_c_forceMaxWindow : /* Force back-references to remain < windowSize, - * even when referencing into Dictionary content. - * default : 0 when using a CDict, 1 when using a Prefix */ - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - + case ZSTD_c_forceMaxWindow: case ZSTD_c_forceAttachDict: - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - - case ZSTD_c_nbWorkers: - if ((value!=0) && cctx->staticSize) { - return ERROR(parameter_unsupported); /* MT not compatible with static alloc */ - } - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - + case ZSTD_c_literalCompressionMode: case ZSTD_c_jobSize: case ZSTD_c_overlapLog: case ZSTD_c_rsyncable: - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); - case ZSTD_c_enableLongDistanceMatching: case ZSTD_c_ldmHashLog: case ZSTD_c_ldmMinMatch: case ZSTD_c_ldmBucketSizeLog: - case ZSTD_c_ldmHashRateLog: - if (cctx->cdict) return ERROR(stage_wrong); - return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value); + break; - default: return ERROR(parameter_unsupported); + default: RETURN_ERROR(parameter_unsupported); } + return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value); } -size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams, - ZSTD_cParameter param, int value) +size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, + ZSTD_cParameter param, int value) { - DEBUGLOG(4, "ZSTD_CCtxParam_setParameter (%i, %i)", (int)param, value); + DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value); switch(param) { case ZSTD_c_format : @@ -495,11 +516,9 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams, return (size_t)CCtxParams->format; case ZSTD_c_compressionLevel : { - int cLevel = value; - if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel(); - if (cLevel < ZSTD_minCLevel()) cLevel = ZSTD_minCLevel(); - if (cLevel) { /* 0 : does not change current level */ - CCtxParams->compressionLevel = cLevel; + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value)); + if (value) { /* 0 : does not change current level */ + CCtxParams->compressionLevel = value; } if (CCtxParams->compressionLevel >= 0) return CCtxParams->compressionLevel; return 0; /* return type (size_t) cannot represent negative values */ @@ -573,33 +592,55 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams, return CCtxParams->attachDictPref; } + case ZSTD_c_literalCompressionMode : { + const ZSTD_literalCompressionMode_e lcm = (ZSTD_literalCompressionMode_e)value; + BOUNDCHECK(ZSTD_c_literalCompressionMode, lcm); + CCtxParams->literalCompressionMode = lcm; + return CCtxParams->literalCompressionMode; + } + case ZSTD_c_nbWorkers : #ifndef ZSTD_MULTITHREAD - if (value!=0) return ERROR(parameter_unsupported); + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; #else - return ZSTDMT_CCtxParam_setNbWorkers(CCtxParams, value); + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value)); + CCtxParams->nbWorkers = value; + return CCtxParams->nbWorkers; #endif case ZSTD_c_jobSize : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; #else - return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_jobSize, value); + /* Adjust to the minimum non-default value. */ + if (value != 0 && value < ZSTDMT_JOBSIZE_MIN) + value = ZSTDMT_JOBSIZE_MIN; + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value)); + assert(value >= 0); + CCtxParams->jobSize = value; + return CCtxParams->jobSize; #endif case ZSTD_c_overlapLog : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; #else - return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_overlapLog, value); + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value)); + CCtxParams->overlapLog = value; + return CCtxParams->overlapLog; #endif case ZSTD_c_rsyncable : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; #else - return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_rsyncable, value); + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value)); + CCtxParams->rsyncable = value; + return CCtxParams->rsyncable; #endif case ZSTD_c_enableLongDistanceMatching : @@ -625,21 +666,21 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams, return CCtxParams->ldmParams.bucketSizeLog; case ZSTD_c_ldmHashRateLog : - if (value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN) - return ERROR(parameter_outOfBound); + RETURN_ERROR_IF(value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN, + parameter_outOfBound); CCtxParams->ldmParams.hashRateLog = value; return CCtxParams->ldmParams.hashRateLog; - default: return ERROR(parameter_unsupported); + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); } } size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value) { - return ZSTD_CCtxParam_getParameter(&cctx->requestedParams, param, value); + return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value); } -size_t ZSTD_CCtxParam_getParameter( +size_t ZSTD_CCtxParams_getParameter( ZSTD_CCtx_params* CCtxParams, ZSTD_cParameter param, int* value) { switch(param) @@ -686,6 +727,9 @@ size_t ZSTD_CCtxParam_getParameter( case ZSTD_c_forceAttachDict : *value = CCtxParams->attachDictPref; break; + case ZSTD_c_literalCompressionMode : + *value = CCtxParams->literalCompressionMode; + break; case ZSTD_c_nbWorkers : #ifndef ZSTD_MULTITHREAD assert(CCtxParams->nbWorkers == 0); @@ -694,7 +738,7 @@ size_t ZSTD_CCtxParam_getParameter( break; case ZSTD_c_jobSize : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); #else assert(CCtxParams->jobSize <= INT_MAX); *value = (int)CCtxParams->jobSize; @@ -702,14 +746,14 @@ size_t ZSTD_CCtxParam_getParameter( #endif case ZSTD_c_overlapLog : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); #else *value = CCtxParams->overlapLog; break; #endif case ZSTD_c_rsyncable : #ifndef ZSTD_MULTITHREAD - return ERROR(parameter_unsupported); + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); #else *value = CCtxParams->rsyncable; break; @@ -729,7 +773,7 @@ size_t ZSTD_CCtxParam_getParameter( case ZSTD_c_ldmHashRateLog : *value = CCtxParams->ldmParams.hashRateLog; break; - default: return ERROR(parameter_unsupported); + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); } return 0; } @@ -745,8 +789,8 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams( ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params) { DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams"); - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); - if (cctx->cdict) return ERROR(stage_wrong); + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); + RETURN_ERROR_IF(cctx->cdict, stage_wrong); cctx->requestedParams = *params; return 0; @@ -755,33 +799,71 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams( ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize) { DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize); - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1; return 0; } +/** + * Initializes the local dict using the requested parameters. + * NOTE: This does not use the pledged src size, because it may be used for more + * than one compression. + */ +static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx) +{ + ZSTD_localDict* const dl = &cctx->localDict; + ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams( + &cctx->requestedParams, 0, dl->dictSize); + if (dl->dict == NULL) { + /* No local dictionary. */ + assert(dl->dictBuffer == NULL); + assert(dl->cdict == NULL); + assert(dl->dictSize == 0); + return 0; + } + if (dl->cdict != NULL) { + assert(cctx->cdict == dl->cdict); + /* Local dictionary already initialized. */ + return 0; + } + assert(dl->dictSize > 0); + assert(cctx->cdict == NULL); + assert(cctx->prefixDict.dict == NULL); + + dl->cdict = ZSTD_createCDict_advanced( + dl->dict, + dl->dictSize, + ZSTD_dlm_byRef, + dl->dictContentType, + cParams, + cctx->customMem); + RETURN_ERROR_IF(!dl->cdict, memory_allocation); + cctx->cdict = dl->cdict; + return 0; +} + size_t ZSTD_CCtx_loadDictionary_advanced( ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) { - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); - if (cctx->staticSize) return ERROR(memory_allocation); /* no malloc for static CCtx */ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); + RETURN_ERROR_IF(cctx->staticSize, memory_allocation, + "no malloc for static CCtx"); DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize); - ZSTD_freeCDict(cctx->cdictLocal); /* in case one already exists */ - if (dict==NULL || dictSize==0) { /* no dictionary mode */ - cctx->cdictLocal = NULL; - cctx->cdict = NULL; + ZSTD_clearAllDicts(cctx); /* in case one already exists */ + if (dict == NULL || dictSize == 0) /* no dictionary mode */ + return 0; + if (dictLoadMethod == ZSTD_dlm_byRef) { + cctx->localDict.dict = dict; } else { - ZSTD_compressionParameters const cParams = - ZSTD_getCParamsFromCCtxParams(&cctx->requestedParams, cctx->pledgedSrcSizePlusOne-1, dictSize); - cctx->cdictLocal = ZSTD_createCDict_advanced( - dict, dictSize, - dictLoadMethod, dictContentType, - cParams, cctx->customMem); - cctx->cdict = cctx->cdictLocal; - if (cctx->cdictLocal == NULL) - return ERROR(memory_allocation); + void* dictBuffer = ZSTD_malloc(dictSize, cctx->customMem); + RETURN_ERROR_IF(!dictBuffer, memory_allocation); + memcpy(dictBuffer, dict, dictSize); + cctx->localDict.dictBuffer = dictBuffer; + cctx->localDict.dict = dictBuffer; } + cctx->localDict.dictSize = dictSize; + cctx->localDict.dictContentType = dictContentType; return 0; } @@ -801,9 +883,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) { - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); + /* Free the existing local cdict (if any) to save memory. */ + ZSTD_clearAllDicts(cctx); cctx->cdict = cdict; - memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); /* exclusive */ return 0; } @@ -815,8 +898,8 @@ size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSiz size_t ZSTD_CCtx_refPrefix_advanced( ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) { - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); - cctx->cdict = NULL; /* prefix discards any prior cdict */ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); + ZSTD_clearAllDicts(cctx); cctx->prefixDict.dict = prefix; cctx->prefixDict.dictSize = prefixSize; cctx->prefixDict.dictContentType = dictContentType; @@ -834,8 +917,8 @@ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset) } if ( (reset == ZSTD_reset_parameters) || (reset == ZSTD_reset_session_and_parameters) ) { - if (cctx->streamStage != zcss_init) return ERROR(stage_wrong); - cctx->cdict = NULL; + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong); + ZSTD_clearAllDicts(cctx); return ZSTD_CCtxParams_reset(&cctx->requestedParams); } return 0; @@ -888,10 +971,11 @@ static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat) } /** ZSTD_adjustCParams_internal() : - optimize `cPar` for a given input (`srcSize` and `dictSize`). - mostly downsizing to reduce memory consumption and initialization latency. - Both `srcSize` and `dictSize` are optional (use 0 if unknown). - Note : cPar is assumed validated. Use ZSTD_checkCParams() to ensure this condition. */ + * optimize `cPar` for a specified input (`srcSize` and `dictSize`). + * mostly downsize to reduce memory consumption and initialization latency. + * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known. + * note : for the time being, `srcSize==0` means "unknown" too, for compatibility with older convention. + * condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */ static ZSTD_compressionParameters ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, unsigned long long srcSize, @@ -901,7 +985,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, static const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1); assert(ZSTD_checkCParams(cPar)==0); - if (dictSize && (srcSize+1<2) /* srcSize unknown */ ) + if (dictSize && (srcSize+1<2) /* ZSTD_CONTENTSIZE_UNKNOWN and 0 mean "unknown" */ ) srcSize = minSrcSize; /* presumed small when there is a dictionary */ else if (srcSize == 0) srcSize = ZSTD_CONTENTSIZE_UNKNOWN; /* 0 == unknown : presumed large */ @@ -922,7 +1006,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, } if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) - cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* required for frame header */ + cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* minimum wlog required for valid frame header */ return cPar; } @@ -932,7 +1016,7 @@ ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize) { - cPar = ZSTD_clampCParams(cPar); + cPar = ZSTD_clampCParams(cPar); /* resulting cPar is necessarily valid (all parameters within range) */ return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize); } @@ -973,8 +1057,7 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams, size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params) { - /* Estimate CCtx size is supported for single-threaded compression only. */ - if (params->nbWorkers > 0) { return ERROR(GENERIC); } + RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); { ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(params, 0, 0); size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog); @@ -1022,10 +1105,12 @@ size_t ZSTD_estimateCCtxSize(int compressionLevel) size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) { - if (params->nbWorkers > 0) { return ERROR(GENERIC); } - { size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params); - size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << params->cParams.windowLog); - size_t const inBuffSize = ((size_t)1 << params->cParams.windowLog) + blockSize; + RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); + { ZSTD_compressionParameters const cParams = + ZSTD_getCParamsFromCCtxParams(params, 0, 0); + size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params); + size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog); + size_t const inBuffSize = ((size_t)1 << cParams.windowLog) + blockSize; size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1; size_t const streamingSize = inBuffSize + outBuffSize; @@ -1367,13 +1452,13 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, DEBUGLOG(4, "Need to resize workSpaceSize from %zuKB to %zuKB", zc->workSpaceSize >> 10, neededSpace >> 10); - /* static cctx : no resize, error out */ - if (zc->staticSize) return ERROR(memory_allocation); + + RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize"); zc->workSpaceSize = 0; ZSTD_free(zc->workSpace, zc->customMem); zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem); - if (zc->workSpace == NULL) return ERROR(memory_allocation); + RETURN_ERROR_IF(zc->workSpace == NULL, memory_allocation); zc->workSpaceSize = neededSpace; zc->workSpaceOversizedDuration = 0; @@ -1644,7 +1729,7 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, ZSTD_buffered_policy_e zbuff) { DEBUGLOG(5, "ZSTD_copyCCtx_internal"); - if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong); + RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong); memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); { ZSTD_CCtx_params params = dstCCtx->requestedParams; @@ -1777,7 +1862,8 @@ static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue) static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize, U32 lastBlock) { U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw)<<1) + (U32)(srcSize << 3); - if (srcSize + ZSTD_blockHeaderSize > dstCapacity) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(srcSize + ZSTD_blockHeaderSize > dstCapacity, + dstSize_tooSmall); MEM_writeLE24(dst, cBlockHeader24); memcpy((BYTE*)dst + ZSTD_blockHeaderSize, src, srcSize); return ZSTD_blockHeaderSize + srcSize; @@ -1788,7 +1874,7 @@ static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void BYTE* const ostart = (BYTE* const)dst; U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); - if (srcSize + flSize > dstCapacity) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall); switch(flSize) { @@ -1878,7 +1964,7 @@ static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf, if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); } - if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall); /* not enough space for compression */ + RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression"); { HUF_repeat repeat = prevHuf->repeatMode; int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; @@ -1960,7 +2046,7 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr) * If x == 0: Return 0 * Else: Return floor(-log2(x / 256) * 256) */ -static unsigned const kInverseProbabiltyLog256[256] = { +static unsigned const kInverseProbabilityLog256[256] = { 0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162, 1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889, 874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734, @@ -1999,7 +2085,7 @@ static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t if (count[s] != 0 && norm == 0) norm = 1; assert(count[s] < total); - cost += count[s] * kInverseProbabiltyLog256[norm]; + cost += count[s] * kInverseProbabilityLog256[norm]; } return cost >> 8; } @@ -2022,7 +2108,7 @@ static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog, unsigned const norm256 = normAcc << shift; assert(norm256 > 0); assert(norm256 < 256); - cost += count[s] * kInverseProbabiltyLog256[norm256]; + cost += count[s] * kInverseProbabilityLog256[norm256]; } return cost >> 8; } @@ -2050,21 +2136,17 @@ static size_t ZSTD_fseBitCost( unsigned s; FSE_CState_t cstate; FSE_initCState(&cstate, ctable); - if (ZSTD_getFSEMaxSymbolValue(ctable) < max) { - DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u", + RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC, + "Repeat FSE_CTable has maxSymbolValue %u < %u", ZSTD_getFSEMaxSymbolValue(ctable), max); - return ERROR(GENERIC); - } for (s = 0; s <= max; ++s) { unsigned const tableLog = cstate.stateLog; unsigned const badCost = (tableLog + 1) << kAccuracyLog; unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog); if (count[s] == 0) continue; - if (bitCost >= badCost) { - DEBUGLOG(5, "Repeat FSE_CTable has Prob[%u] == 0", s); - return ERROR(GENERIC); - } + RETURN_ERROR_IF(bitCost >= badCost, GENERIC, + "Repeat FSE_CTable has Prob[%u] == 0", s); cost += count[s] * bitCost; } return cost >> kAccuracyLog; @@ -2080,7 +2162,7 @@ static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max, BYTE wksp[FSE_NCOUNTBOUND]; S16 norm[MaxSeq + 1]; const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); - CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq, max)); + FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max)); return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog); } @@ -2186,15 +2268,15 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity, switch (type) { case set_rle: - CHECK_F(FSE_buildCTable_rle(nextCTable, (BYTE)max)); - if (dstCapacity==0) return ERROR(dstSize_tooSmall); + FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max)); + RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall); *op = codeTable[0]; return 1; case set_repeat: memcpy(nextCTable, prevCTable, prevCTableSize); return 0; case set_basic: - CHECK_F(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */ + FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */ return 0; case set_compressed: { S16 norm[MaxSeq + 1]; @@ -2205,14 +2287,14 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity, nbSeq_1--; } assert(nbSeq_1 > 1); - CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max)); + FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max)); { size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ - if (FSE_isError(NCountSize)) return NCountSize; - CHECK_F(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize)); + FORWARD_IF_ERROR(NCountSize); + FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize)); return NCountSize; } } - default: return assert(0), ERROR(GENERIC); + default: assert(0); RETURN_ERROR(GENERIC); } } @@ -2229,7 +2311,9 @@ ZSTD_encodeSequences_body( FSE_CState_t stateOffsetBits; FSE_CState_t stateLitLength; - CHECK_E(BIT_initCStream(&blockStream, dst, dstCapacity), dstSize_tooSmall); /* not enough space remaining */ + RETURN_ERROR_IF( + ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)), + dstSize_tooSmall, "not enough space remaining"); DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)", (int)(blockStream.endPtr - blockStream.startPtr), (unsigned)dstCapacity); @@ -2303,7 +2387,7 @@ ZSTD_encodeSequences_body( FSE_flushCState(&blockStream, &stateLitLength); { size_t const streamSize = BIT_closeCStream(&blockStream); - if (streamSize==0) return ERROR(dstSize_tooSmall); /* not enough space */ + RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space"); return streamSize; } } @@ -2368,6 +2452,21 @@ static size_t ZSTD_encodeSequences( sequences, nbSeq, longOffsets); } +static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams) +{ + switch (cctxParams->literalCompressionMode) { + case ZSTD_lcm_huffman: + return 0; + case ZSTD_lcm_uncompressed: + return 1; + default: + assert(0 /* impossible: pre-validated */); + /* fall-through */ + case ZSTD_lcm_auto: + return (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0); + } +} + /* ZSTD_compressSequences_internal(): * actually compresses both literals and sequences */ MEM_STATIC size_t @@ -2403,22 +2502,22 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, /* Compress literals */ { const BYTE* const literals = seqStorePtr->litStart; size_t const litSize = seqStorePtr->lit - literals; - int const disableLiteralCompression = (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0); size_t const cSize = ZSTD_compressLiterals( &prevEntropy->huf, &nextEntropy->huf, - cctxParams->cParams.strategy, disableLiteralCompression, + cctxParams->cParams.strategy, + ZSTD_disableLiteralsCompression(cctxParams), op, dstCapacity, literals, litSize, workspace, wkspSize, bmi2); - if (ZSTD_isError(cSize)) - return cSize; + FORWARD_IF_ERROR(cSize); assert(cSize <= dstCapacity); op += cSize; } /* Sequences Header */ - if ((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, + dstSize_tooSmall); if (nbSeq < 0x7F) *op++ = (BYTE)nbSeq; else if (nbSeq < LONGNBSEQ) @@ -2452,7 +2551,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL, prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable), workspace, wkspSize); - if (ZSTD_isError(countSize)) return countSize; + FORWARD_IF_ERROR(countSize); if (LLtype == set_compressed) lastNCount = op; op += countSize; @@ -2474,7 +2573,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable), workspace, wkspSize); - if (ZSTD_isError(countSize)) return countSize; + FORWARD_IF_ERROR(countSize); if (Offtype == set_compressed) lastNCount = op; op += countSize; @@ -2494,7 +2593,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML, prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable), workspace, wkspSize); - if (ZSTD_isError(countSize)) return countSize; + FORWARD_IF_ERROR(countSize); if (MLtype == set_compressed) lastNCount = op; op += countSize; @@ -2509,10 +2608,10 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, CTable_LitLength, llCodeTable, sequences, nbSeq, longOffsets, bmi2); - if (ZSTD_isError(bitstreamSize)) return bitstreamSize; + FORWARD_IF_ERROR(bitstreamSize); op += bitstreamSize; /* zstd versions <= 1.3.4 mistakenly report corruption when - * FSE_readNCount() recieves a buffer < 4 bytes. + * FSE_readNCount() receives a buffer < 4 bytes. * Fixed by https://github.com/facebook/zstd/pull/1146. * This can happen when the last set_compressed table present is 2 * bytes and the bitstream is only one byte. @@ -2552,7 +2651,7 @@ ZSTD_compressSequences(seqStore_t* seqStorePtr, */ if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity)) return 0; /* block not compressed */ - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); /* Check compressibility */ { size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy); @@ -2641,7 +2740,10 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, goto out; /* don't even attempt compression below a certain srcSize */ } ZSTD_resetSeqStore(&(zc->seqStore)); - ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; /* required for optimal parser to read stats from dictionary */ + /* required for optimal parser to read stats from dictionary */ + ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; + /* tell the optimal parser how we expect to compress literals */ + ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode; /* a gap between an attached dict and the current window is not safe, * they must remain adjacent, @@ -2679,7 +2781,7 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, ldmSeqStore.seq = zc->ldmSequences; ldmSeqStore.capacity = zc->maxNbLdmSequences; /* Updates ldmSeqStore.size */ - CHECK_F(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore, + FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore, &zc->appliedParams.ldmParams, src, srcSize)); /* Updates ldmSeqStore.pos */ @@ -2752,8 +2854,9 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx, ZSTD_matchState_t* const ms = &cctx->blockState.matchState; U32 const lastBlock = lastFrameChunk & (blockSize >= remaining); - if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE) - return ERROR(dstSize_tooSmall); /* not enough space to store compressed block */ + RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE, + dstSize_tooSmall, + "not enough space to store compressed block"); if (remaining < blockSize) blockSize = remaining; if (ZSTD_window_needOverflowCorrection(ms->window, ip + blockSize)) { @@ -2774,11 +2877,11 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx, { size_t cSize = ZSTD_compressBlock_internal(cctx, op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize, ip, blockSize); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); if (cSize == 0) { /* block is not compressible */ cSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); } else { U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3); MEM_writeLE24(op, cBlockHeader24); @@ -2811,11 +2914,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3); U32 const fcsCode = params.fParams.contentSizeFlag ? (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0; /* 0-3 */ - BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) ); + BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) ); size_t pos=0; assert(!(params.fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)); - if (dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall); DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u", !params.fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode); @@ -2823,7 +2926,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, MEM_writeLE32(dst, ZSTD_MAGICNUMBER); pos = 4; } - op[pos++] = frameHeaderDecriptionByte; + op[pos++] = frameHeaderDescriptionByte; if (!singleSegment) op[pos++] = windowLogByte; switch(dictIDSizeCode) { @@ -2847,11 +2950,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, /* ZSTD_writeLastEmptyBlock() : * output an empty Block with end-of-frame mark to complete a frame * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) - * or an error code if `dstCapcity` is too small ( stage != ZSTDcs_init) - return ERROR(stage_wrong); - if (cctx->appliedParams.ldmParams.enableLdm) - return ERROR(parameter_unsupported); + RETURN_ERROR_IF(cctx->stage != ZSTDcs_init, stage_wrong); + RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm, + parameter_unsupported); cctx->externSeqStore.seq = seq; cctx->externSeqStore.size = nbSeq; cctx->externSeqStore.capacity = nbSeq; @@ -2882,12 +2984,13 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u", cctx->stage, (unsigned)srcSize); - if (cctx->stage==ZSTDcs_created) return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */ + RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong, + "missing init (ZSTD_compressBegin)"); if (frame && (cctx->stage==ZSTDcs_init)) { fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, cctx->pledgedSrcSizePlusOne-1, cctx->dictID); - if (ZSTD_isError(fhSize)) return fhSize; + FORWARD_IF_ERROR(fhSize); dstCapacity -= fhSize; dst = (char*)dst + fhSize; cctx->stage = ZSTDcs_ongoing; @@ -2922,17 +3025,18 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, { size_t const cSize = frame ? ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) : ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); cctx->consumedSrcSize += srcSize; cctx->producedCSize += (cSize + fhSize); assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); - if (cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne) { - DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize >= %u", - (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize); - return ERROR(srcSize_wrong); - } + RETURN_ERROR_IF( + cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne, + srcSize_wrong, + "error : pledgedSrcSize = %u, while realSrcSize >= %u", + (unsigned)cctx->pledgedSrcSizePlusOne-1, + (unsigned)cctx->consumedSrcSize); } return cSize + fhSize; } @@ -2957,7 +3061,7 @@ size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx) size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) { size_t const blockSizeMax = ZSTD_getBlockSize(cctx); - if (srcSize > blockSizeMax) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong); return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */); } @@ -3020,9 +3124,9 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms, NOTE: This behavior is not standard and could be improved in the future. */ static size_t ZSTD_checkDictNCount(short* normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue) { U32 s; - if (dictMaxSymbolValue < maxSymbolValue) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(dictMaxSymbolValue < maxSymbolValue, dictionary_corrupted); for (s = 0; s <= maxSymbolValue; ++s) { - if (normalizedCounter[s] == 0) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(normalizedCounter[s] == 0, dictionary_corrupted); } return 0; } @@ -3060,53 +3164,56 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs, { unsigned maxSymbolValue = 255; size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr); - if (HUF_isError(hufHeaderSize)) return ERROR(dictionary_corrupted); - if (maxSymbolValue < 255) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted); dictPtr += hufHeaderSize; } { unsigned offcodeLog; size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted); - if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted); /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */ /* fill all offset symbols to avoid garbage at end of table */ - CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.offcodeCTable, - offcodeNCount, MaxOff, offcodeLog, - workspace, HUF_WORKSPACE_SIZE), - dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.offcodeCTable, + offcodeNCount, MaxOff, offcodeLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted); dictPtr += offcodeHeaderSize; } { short matchlengthNCount[MaxML+1]; unsigned matchlengthMaxValue = MaxML, matchlengthLog; size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted); - if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted); /* Every match length code must have non-zero probability */ - CHECK_F( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML)); - CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.matchlengthCTable, - matchlengthNCount, matchlengthMaxValue, matchlengthLog, - workspace, HUF_WORKSPACE_SIZE), - dictionary_corrupted); + FORWARD_IF_ERROR( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML)); + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.matchlengthCTable, + matchlengthNCount, matchlengthMaxValue, matchlengthLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted); dictPtr += matchlengthHeaderSize; } { short litlengthNCount[MaxLL+1]; unsigned litlengthMaxValue = MaxLL, litlengthLog; size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted); - if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted); /* Every literal length code must have non-zero probability */ - CHECK_F( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL)); - CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.litlengthCTable, - litlengthNCount, litlengthMaxValue, litlengthLog, - workspace, HUF_WORKSPACE_SIZE), - dictionary_corrupted); + FORWARD_IF_ERROR( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL)); + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.litlengthCTable, + litlengthNCount, litlengthMaxValue, litlengthLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted); dictPtr += litlengthHeaderSize; } - if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted); bs->rep[0] = MEM_readLE32(dictPtr+0); bs->rep[1] = MEM_readLE32(dictPtr+4); bs->rep[2] = MEM_readLE32(dictPtr+8); @@ -3119,19 +3226,19 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs, offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */ } /* All offset values <= dictContentSize + 128 KB must be representable */ - CHECK_F (ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff))); + FORWARD_IF_ERROR(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff))); /* All repCodes must be <= dictContentSize and != 0*/ { U32 u; for (u=0; u<3; u++) { - if (bs->rep[u] == 0) return ERROR(dictionary_corrupted); - if (bs->rep[u] > dictContentSize) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(bs->rep[u] == 0, dictionary_corrupted); + RETURN_ERROR_IF(bs->rep[u] > dictContentSize, dictionary_corrupted); } } bs->entropy.huf.repeatMode = HUF_repeat_valid; bs->entropy.fse.offcode_repeatMode = FSE_repeat_valid; bs->entropy.fse.matchlength_repeatMode = FSE_repeat_valid; bs->entropy.fse.litlength_repeatMode = FSE_repeat_valid; - CHECK_F(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm)); + FORWARD_IF_ERROR(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm)); return dictID; } } @@ -3161,8 +3268,7 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs, DEBUGLOG(4, "raw content dictionary detected"); return ZSTD_loadDictionaryContent(ms, params, dict, dictSize, dtlm); } - if (dictContentType == ZSTD_dct_fullDict) - return ERROR(dictionary_wrong); + RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong); assert(0); /* impossible */ } @@ -3189,13 +3295,13 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff); } - CHECK_F( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, + FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, ZSTDcrp_continue, zbuff) ); { size_t const dictID = ZSTD_compress_insertDictionary( cctx->blockState.prevCBlock, &cctx->blockState.matchState, ¶ms, dict, dictSize, dictContentType, dtlm, cctx->entropyWorkspace); - if (ZSTD_isError(dictID)) return dictID; + FORWARD_IF_ERROR(dictID); assert(dictID <= (size_t)(U32)-1); cctx->dictID = (U32)dictID; } @@ -3212,7 +3318,7 @@ size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, { DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params.cParams.windowLog); /* compression parameters verification and optimization */ - CHECK_F( ZSTD_checkCParams(params.cParams) ); + FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) ); return ZSTD_compressBegin_internal(cctx, dict, dictSize, dictContentType, dtlm, cdict, @@ -3260,12 +3366,12 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) size_t fhSize = 0; DEBUGLOG(4, "ZSTD_writeEpilogue"); - if (cctx->stage == ZSTDcs_created) return ERROR(stage_wrong); /* init missing */ + RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing"); /* special case : empty frame */ if (cctx->stage == ZSTDcs_init) { fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, 0, 0); - if (ZSTD_isError(fhSize)) return fhSize; + FORWARD_IF_ERROR(fhSize); dstCapacity -= fhSize; op += fhSize; cctx->stage = ZSTDcs_ongoing; @@ -3274,7 +3380,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) if (cctx->stage != ZSTDcs_ending) { /* write one last empty block, make it the "last" block */ U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1) + 0; - if (dstCapacity<4) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall); MEM_writeLE32(op, cBlockHeader24); op += ZSTD_blockHeaderSize; dstCapacity -= ZSTD_blockHeaderSize; @@ -3282,7 +3388,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) if (cctx->appliedParams.fParams.checksumFlag) { U32 const checksum = (U32) XXH64_digest(&cctx->xxhState); - if (dstCapacity<4) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall); DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum); MEM_writeLE32(op, checksum); op += 4; @@ -3300,18 +3406,20 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx, size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 1 /* last chunk */); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize); - if (ZSTD_isError(endResult)) return endResult; + FORWARD_IF_ERROR(endResult); assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); DEBUGLOG(4, "end of frame : controlling src size"); - if (cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1) { - DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize = %u", - (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize); - return ERROR(srcSize_wrong); - } } + RETURN_ERROR_IF( + cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1, + srcSize_wrong, + "error : pledgedSrcSize = %u, while realSrcSize = %u", + (unsigned)cctx->pledgedSrcSizePlusOne-1, + (unsigned)cctx->consumedSrcSize); + } return cSize + endResult; } @@ -3339,7 +3447,7 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx, ZSTD_parameters params) { DEBUGLOG(4, "ZSTD_compress_advanced"); - CHECK_F(ZSTD_checkCParams(params.cParams)); + FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams)); return ZSTD_compress_internal(cctx, dst, dstCapacity, src, srcSize, @@ -3356,7 +3464,7 @@ size_t ZSTD_compress_advanced_internal( ZSTD_CCtx_params params) { DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize); - CHECK_F( ZSTD_compressBegin_internal(cctx, + FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL, params, srcSize, ZSTDb_not_buffered) ); return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); @@ -3440,7 +3548,7 @@ static size_t ZSTD_initCDict_internal( void* const internalBuffer = ZSTD_malloc(dictSize, cdict->customMem); cdict->dictBuffer = internalBuffer; cdict->dictContent = internalBuffer; - if (!internalBuffer) return ERROR(memory_allocation); + RETURN_ERROR_IF(!internalBuffer, memory_allocation); memcpy(internalBuffer, dictBuffer, dictSize); } cdict->dictContentSize = dictSize; @@ -3466,7 +3574,7 @@ static size_t ZSTD_initCDict_internal( &cdict->cBlockState, &cdict->matchState, ¶ms, cdict->dictContent, cdict->dictContentSize, dictContentType, ZSTD_dtlm_full, cdict->workspace); - if (ZSTD_isError(dictID)) return dictID; + FORWARD_IF_ERROR(dictID); assert(dictID <= (size_t)(U32)-1); cdict->dictID = (U32)dictID; } @@ -3596,7 +3704,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced( ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize) { DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced"); - if (cdict==NULL) return ERROR(dictionary_wrong); + RETURN_ERROR_IF(cdict==NULL, dictionary_wrong); { ZSTD_CCtx_params params = cctx->requestedParams; params.cParams = ZSTD_getCParamsFromCDict(cdict); /* Increase window log to fit the entire dictionary and source if the @@ -3632,7 +3740,7 @@ size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, const void* src, size_t srcSize, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams) { - CHECK_F (ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize)); /* will check if cdict != NULL */ + FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize)); /* will check if cdict != NULL */ return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); } @@ -3700,7 +3808,7 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx, assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); assert(!((dict) && (cdict))); /* either dict or cdict, not both */ - CHECK_F( ZSTD_compressBegin_internal(cctx, + FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx, dict, dictSize, dictContentType, ZSTD_dtlm_fast, cdict, params, pledgedSrcSize, @@ -3718,13 +3826,17 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx, /* ZSTD_resetCStream(): * pledgedSrcSize == 0 means "unknown" */ -size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) +size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss) { - ZSTD_CCtx_params params = zcs->requestedParams; + /* temporary : 0 interpreted as "unknown" during transition period. + * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. + * 0 will be interpreted as "empty" in the future. + */ + U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; DEBUGLOG(4, "ZSTD_resetCStream: pledgedSrcSize = %u", (unsigned)pledgedSrcSize); - if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; - params.fParams.contentSizeFlag = 1; - return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) ); + return 0; } /*! ZSTD_initCStream_internal() : @@ -3736,32 +3848,18 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, ZSTD_CCtx_params params, unsigned long long pledgedSrcSize) { DEBUGLOG(4, "ZSTD_initCStream_internal"); - params.cParams = ZSTD_getCParamsFromCCtxParams(¶ms, pledgedSrcSize, dictSize); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) ); assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); + zcs->requestedParams = params; assert(!((dict) && (cdict))); /* either dict or cdict, not both */ - - if (dict && dictSize >= 8) { - DEBUGLOG(4, "loading dictionary of size %u", (unsigned)dictSize); - if (zcs->staticSize) { /* static CCtx : never uses malloc */ - /* incompatible with internal cdict creation */ - return ERROR(memory_allocation); - } - ZSTD_freeCDict(zcs->cdictLocal); - zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, - ZSTD_dlm_byCopy, ZSTD_dct_auto, - params.cParams, zcs->customMem); - zcs->cdict = zcs->cdictLocal; - if (zcs->cdictLocal == NULL) return ERROR(memory_allocation); + if (dict) { + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) ); } else { - if (cdict) { - params.cParams = ZSTD_getCParamsFromCDict(cdict); /* cParams are enforced from cdict; it includes windowLog */ - } - ZSTD_freeCDict(zcs->cdictLocal); - zcs->cdictLocal = NULL; - zcs->cdict = cdict; + /* Dictionary is cleared if !cdict */ + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) ); } - - return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize); + return 0; } /* ZSTD_initCStream_usingCDict_advanced() : @@ -3772,22 +3870,20 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) { DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced"); - if (!cdict) return ERROR(dictionary_wrong); /* cannot handle NULL cdict (does not know what to do) */ - { ZSTD_CCtx_params params = zcs->requestedParams; - params.cParams = ZSTD_getCParamsFromCDict(cdict); - params.fParams = fParams; - return ZSTD_initCStream_internal(zcs, - NULL, 0, cdict, - params, pledgedSrcSize); - } + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) ); + zcs->requestedParams.fParams = fParams; + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) ); + return 0; } /* note : cdict must outlive compression session */ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict) { - ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */, 0 /* checksum */, 0 /* hideDictID */ }; DEBUGLOG(4, "ZSTD_initCStream_usingCDict"); - return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN); /* note : will check that cdict != NULL */ + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) ); + return 0; } @@ -3797,33 +3893,53 @@ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict) * dict is loaded with default parameters ZSTD_dm_auto and ZSTD_dlm_byCopy. */ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, - ZSTD_parameters params, unsigned long long pledgedSrcSize) + ZSTD_parameters params, unsigned long long pss) { - DEBUGLOG(4, "ZSTD_initCStream_advanced: pledgedSrcSize=%u, flag=%u", - (unsigned)pledgedSrcSize, params.fParams.contentSizeFlag); - CHECK_F( ZSTD_checkCParams(params.cParams) ); - if ((pledgedSrcSize==0) && (params.fParams.contentSizeFlag==0)) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; /* for compatibility with older programs relying on this behavior. Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. This line will be removed in the future. */ + /* for compatibility with older programs relying on this behavior. + * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. + * This line will be removed in the future. + */ + U64 const pledgedSrcSize = (pss==0 && params.fParams.contentSizeFlag==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; + DEBUGLOG(4, "ZSTD_initCStream_advanced"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) ); + FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) ); zcs->requestedParams = ZSTD_assignParamsToCCtxParams(zcs->requestedParams, params); - return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL /*cdict*/, zcs->requestedParams, pledgedSrcSize); + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) ); + return 0; } size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel) { - ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel); - return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, zcs->requestedParams, ZSTD_CONTENTSIZE_UNKNOWN); + DEBUGLOG(4, "ZSTD_initCStream_usingDict"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) ); + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) ); + return 0; } size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss) { - U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; /* temporary : 0 interpreted as "unknown" during transition period. Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. `0` will be interpreted as "empty" in the future */ - ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel); - return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, zcs->requestedParams, pledgedSrcSize); + /* temporary : 0 interpreted as "unknown" during transition period. + * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. + * 0 will be interpreted as "empty" in the future. + */ + U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; + DEBUGLOG(4, "ZSTD_initCStream_srcSize"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) ); + return 0; } size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel) { DEBUGLOG(4, "ZSTD_initCStream"); - return ZSTD_initCStream_srcSize(zcs, compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) ); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) ); + return 0; } /*====== Compression ======*/ @@ -3847,10 +3963,10 @@ static size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, * internal function for all *compressStream*() variants * non-static, because can be called from zstdmt_compress.c * @return : hint size for next input */ -size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective const flushMode) +static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective const flushMode) { const char* const istart = (const char*)input->src; const char* const iend = istart + input->size; @@ -3873,8 +3989,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, switch(zcs->streamStage) { case zcss_init: - /* call ZSTD_initCStream() first ! */ - return ERROR(init_missing); + RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!"); case zcss_load: if ( (flushMode == ZSTD_e_end) @@ -3884,7 +3999,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, size_t const cSize = ZSTD_compressEnd(zcs, op, oend-op, ip, iend-ip); DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); ip = iend; op += cSize; zcs->frameEnded = 1; @@ -3925,7 +4040,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, zcs->inBuff + zcs->inToCompress, iSize) : ZSTD_compressContinue(zcs, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize); - if (ZSTD_isError(cSize)) return cSize; + FORWARD_IF_ERROR(cSize); zcs->frameEnded = lastBlock; /* prepare next block */ zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize; @@ -4001,7 +4116,7 @@ static size_t ZSTD_nextInputSizeHint_MTorST(const ZSTD_CCtx* cctx) size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input) { - CHECK_F( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) ); + FORWARD_IF_ERROR( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) ); return ZSTD_nextInputSizeHint_MTorST(zcs); } @@ -4013,14 +4128,15 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, { DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp); /* check conditions */ - if (output->pos > output->size) return ERROR(GENERIC); - if (input->pos > input->size) return ERROR(GENERIC); + RETURN_ERROR_IF(output->pos > output->size, GENERIC); + RETURN_ERROR_IF(input->pos > input->size, GENERIC); assert(cctx!=NULL); /* transparent initialization stage */ if (cctx->streamStage == zcss_init) { ZSTD_CCtx_params params = cctx->requestedParams; ZSTD_prefixDict const prefixDict = cctx->prefixDict; + FORWARD_IF_ERROR( ZSTD_initLocalDict(cctx) ); /* Init the local dict if present. */ memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); /* single usage */ assert(prefixDict.dict==NULL || cctx->cdict==NULL); /* only one can be set */ DEBUGLOG(4, "ZSTD_compressStream2 : transparent init stage"); @@ -4039,11 +4155,11 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, DEBUGLOG(4, "ZSTD_compressStream2: creating new mtctx for nbWorkers=%u", params.nbWorkers); cctx->mtctx = ZSTDMT_createCCtx_advanced(params.nbWorkers, cctx->customMem); - if (cctx->mtctx == NULL) return ERROR(memory_allocation); + RETURN_ERROR_IF(cctx->mtctx == NULL, memory_allocation); } /* mt compression */ DEBUGLOG(4, "call ZSTDMT_initCStream_internal as nbWorkers=%u", params.nbWorkers); - CHECK_F( ZSTDMT_initCStream_internal( + FORWARD_IF_ERROR( ZSTDMT_initCStream_internal( cctx->mtctx, prefixDict.dict, prefixDict.dictSize, ZSTD_dct_rawContent, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) ); @@ -4051,7 +4167,7 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, cctx->appliedParams.nbWorkers = params.nbWorkers; } else #endif - { CHECK_F( ZSTD_resetCStream_internal(cctx, + { FORWARD_IF_ERROR( ZSTD_resetCStream_internal(cctx, prefixDict.dict, prefixDict.dictSize, prefixDict.dictContentType, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) ); @@ -4063,20 +4179,30 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, /* compression stage */ #ifdef ZSTD_MULTITHREAD if (cctx->appliedParams.nbWorkers > 0) { + int const forceMaxProgress = (endOp == ZSTD_e_flush || endOp == ZSTD_e_end); + size_t flushMin; + assert(forceMaxProgress || endOp == ZSTD_e_continue /* Protection for a new flush type */); if (cctx->cParamsChanged) { ZSTDMT_updateCParams_whileCompressing(cctx->mtctx, &cctx->requestedParams); cctx->cParamsChanged = 0; } - { size_t const flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp); + do { + flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp); if ( ZSTD_isError(flushMin) || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */ ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only); } - DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic"); - return flushMin; - } } + FORWARD_IF_ERROR(flushMin); + } while (forceMaxProgress && flushMin != 0 && output->pos < output->size); + DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic"); + /* Either we don't require maximum forward progress, we've finished the + * flush, or we are out of output space. + */ + assert(!forceMaxProgress || flushMin == 0 || output->pos == output->size); + return flushMin; + } #endif - CHECK_F( ZSTD_compressStream_generic(cctx, output, input, endOp) ); + FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) ); DEBUGLOG(5, "completed ZSTD_compressStream2"); return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */ } @@ -4107,10 +4233,10 @@ size_t ZSTD_compress2(ZSTD_CCtx* cctx, dst, dstCapacity, &oPos, src, srcSize, &iPos, ZSTD_e_end); - if (ZSTD_isError(result)) return result; + FORWARD_IF_ERROR(result); if (result != 0) { /* compression not completed, due to lack of output space */ assert(oPos == dstCapacity); - return ERROR(dstSize_tooSmall); + RETURN_ERROR(dstSize_tooSmall); } assert(iPos == srcSize); /* all input is expected consumed */ return oPos; @@ -4132,7 +4258,7 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output) { ZSTD_inBuffer input = { NULL, 0, 0 }; size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end); - CHECK_F( remainingToFlush ); + FORWARD_IF_ERROR( remainingToFlush ); if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush; /* minimal estimation */ /* single thread mode : attempt to calculate remaining to flush more precisely */ { size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE; @@ -4151,7 +4277,7 @@ int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; } int ZSTD_minCLevel(void) { return (int)-ZSTD_TARGETLENGTH_MAX; } static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = { -{ /* "default" - guarantees a monotonically increasing memory budget */ +{ /* "default" - for any srcSize > 256 KB */ /* W, C, H, S, L, TL, strat */ { 19, 12, 13, 1, 6, 1, ZSTD_fast }, /* base for negative levels */ { 19, 13, 14, 1, 7, 0, ZSTD_fast }, /* level 1 */ @@ -4258,13 +4384,13 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV }; /*! ZSTD_getCParams() : -* @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize. -* Size values are optional, provide 0 if not known or unused */ + * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize. + * Size values are optional, provide 0 if not known or unused */ ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) { size_t const addedSize = srcSizeHint ? 0 : 500; - U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : (U64)-1; - U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); /* intentional underflow for srcSizeHint == 0 */ + U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : ZSTD_CONTENTSIZE_UNKNOWN; /* intentional overflow for srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN */ + U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); int row = compressionLevel; DEBUGLOG(5, "ZSTD_getCParams (cLevel=%i)", compressionLevel); if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ @@ -4272,13 +4398,14 @@ ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long l if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL; { ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row]; if (compressionLevel < 0) cp.targetLength = (unsigned)(-compressionLevel); /* acceleration factor */ - return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize); + return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize); /* refine parameters based on srcSize & dictSize */ } } /*! ZSTD_getParams() : -* same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`). -* All fields of `ZSTD_frameParameters` are set to default (0) */ + * same idea as ZSTD_getCParams() + * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`). + * Fields of `ZSTD_frameParameters` are set to default values */ ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) { ZSTD_parameters params; ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSizeHint, dictSize); diff --git a/lib/compress/zstd_compress_internal.h b/lib/compress/zstd_compress_internal.h index 29bca59859ea..cc3cbb9da9ff 100644 --- a/lib/compress/zstd_compress_internal.h +++ b/lib/compress/zstd_compress_internal.h @@ -36,9 +36,9 @@ extern "C" { #define ZSTD_DUBT_UNSORTED_MARK 1 /* For btlazy2 strategy, index 1 now means "unsorted". It could be confused for a real successor at index "1", if sorted as larger than its predecessor. It's not a big deal though : candidate will just be sorted again. - Additionnally, candidate position 1 will be lost. + Additionally, candidate position 1 will be lost. But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss. - The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be misdhandled after table re-use with a different strategy + The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy Constant required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */ @@ -54,6 +54,14 @@ typedef struct ZSTD_prefixDict_s { ZSTD_dictContentType_e dictContentType; } ZSTD_prefixDict; +typedef struct { + void* dictBuffer; + void const* dict; + size_t dictSize; + ZSTD_dictContentType_e dictContentType; + ZSTD_CDict* cdict; +} ZSTD_localDict; + typedef struct { U32 CTable[HUF_CTABLE_SIZE_U32(255)]; HUF_repeat repeatMode; @@ -107,6 +115,7 @@ typedef struct { U32 offCodeSumBasePrice; /* to compare to log2(offreq) */ ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost structure */ const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */ + ZSTD_literalCompressionMode_e literalCompressionMode; } optState_t; typedef struct { @@ -188,6 +197,7 @@ struct ZSTD_CCtx_params_s { * 1< cParams; + U32* const hashTable = ms->hashTable; + U32 const hlog = cParams->hashLog; + /* support stepSize of 0 */ + size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1; + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + /* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */ + const BYTE* ip0 = istart; + const BYTE* ip1; + const BYTE* anchor = istart; + const U32 prefixStartIndex = ms->window.dictLimit; + const BYTE* const prefixStart = base + prefixStartIndex; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; + U32 offset_1=rep[0], offset_2=rep[1]; + U32 offsetSaved = 0; + + /* init */ + ip0 += (ip0 == prefixStart); + ip1 = ip0 + 1; + { + U32 const maxRep = (U32)(ip0 - prefixStart); + if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0; + if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0; + } + + /* Main Search Loop */ + while (ip1 < ilimit) { /* < instead of <=, because check at ip0+2 */ + size_t mLength; + BYTE const* ip2 = ip0 + 2; + size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls); + U32 const val0 = MEM_read32(ip0); + size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls); + U32 const val1 = MEM_read32(ip1); + U32 const current0 = (U32)(ip0-base); + U32 const current1 = (U32)(ip1-base); + U32 const matchIndex0 = hashTable[h0]; + U32 const matchIndex1 = hashTable[h1]; + BYTE const* repMatch = ip2-offset_1; + const BYTE* match0 = base + matchIndex0; + const BYTE* match1 = base + matchIndex1; + U32 offcode; + hashTable[h0] = current0; /* update hash table */ + hashTable[h1] = current1; /* update hash table */ + + assert(ip0 + 1 == ip1); + + if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) { + mLength = ip2[-1] == repMatch[-1] ? 1 : 0; + ip0 = ip2 - mLength; + match0 = repMatch - mLength; + offcode = 0; + goto _match; + } + if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) { + /* found a regular match */ + goto _offset; + } + if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) { + /* found a regular match after one literal */ + ip0 = ip1; + match0 = match1; + goto _offset; + } + { + size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize; + assert(step >= 2); + ip0 += step; + ip1 += step; + continue; + } +_offset: /* Requires: ip0, match0 */ + /* Compute the offset code */ + offset_2 = offset_1; + offset_1 = (U32)(ip0-match0); + offcode = offset_1 + ZSTD_REP_MOVE; + mLength = 0; + /* Count the backwards match length */ + while (((ip0>anchor) & (match0>prefixStart)) + && (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */ + +_match: /* Requires: ip0, match0, offcode */ + /* Count the forward length */ + mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4; + ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH); + /* match found */ + ip0 += mLength; + anchor = ip0; + ip1 = ip0 + 1; + + if (ip0 <= ilimit) { + /* Fill Table */ + assert(base+current0+2 > istart); /* check base overflow */ + hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */ + hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base); + + while ( (ip0 <= ilimit) + && ( (offset_2>0) + & (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) { + /* store sequence */ + size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4; + U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */ + hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base); + ip0 += rLength; + ip1 = ip0 + 1; + ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH); + anchor = ip0; + continue; /* faster when present (confirmed on gcc-8) ... (?) */ + } + } + } + + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ + return iend - anchor; +} + + +size_t ZSTD_compressBlock_fast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + ZSTD_compressionParameters const* cParams = &ms->cParams; + U32 const mls = cParams->minMatch; + assert(ms->dictMatchState == NULL); + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4); + case 5 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5); + case 6 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6); + case 7 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7); + } +} + +FORCE_INLINE_TEMPLATE +size_t ZSTD_compressBlock_fast_dictMatchState_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, U32 const mls) { const ZSTD_compressionParameters* const cParams = &ms->cParams; U32* const hashTable = ms->hashTable; @@ -64,46 +212,26 @@ size_t ZSTD_compressBlock_fast_generic( U32 offsetSaved = 0; const ZSTD_matchState_t* const dms = ms->dictMatchState; - const ZSTD_compressionParameters* const dictCParams = - dictMode == ZSTD_dictMatchState ? - &dms->cParams : NULL; - const U32* const dictHashTable = dictMode == ZSTD_dictMatchState ? - dms->hashTable : NULL; - const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ? - dms->window.dictLimit : 0; - const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ? - dms->window.base : NULL; - const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ? - dictBase + dictStartIndex : NULL; - const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ? - dms->window.nextSrc : NULL; - const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ? - prefixStartIndex - (U32)(dictEnd - dictBase) : - 0; + const ZSTD_compressionParameters* const dictCParams = &dms->cParams ; + const U32* const dictHashTable = dms->hashTable; + const U32 dictStartIndex = dms->window.dictLimit; + const BYTE* const dictBase = dms->window.base; + const BYTE* const dictStart = dictBase + dictStartIndex; + const BYTE* const dictEnd = dms->window.nextSrc; + const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase); const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart); - const U32 dictHLog = dictMode == ZSTD_dictMatchState ? - dictCParams->hashLog : hlog; - - assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState); + const U32 dictHLog = dictCParams->hashLog; /* otherwise, we would get index underflow when translating a dict index * into a local index */ - assert(dictMode != ZSTD_dictMatchState - || prefixStartIndex >= (U32)(dictEnd - dictBase)); + assert(prefixStartIndex >= (U32)(dictEnd - dictBase)); /* init */ ip += (dictAndPrefixLength == 0); - if (dictMode == ZSTD_noDict) { - U32 const maxRep = (U32)(ip - prefixStart); - if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0; - if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0; - } - if (dictMode == ZSTD_dictMatchState) { - /* dictMatchState repCode checks don't currently handle repCode == 0 - * disabling. */ - assert(offset_1 <= dictAndPrefixLength); - assert(offset_2 <= dictAndPrefixLength); - } + /* dictMatchState repCode checks don't currently handle repCode == 0 + * disabling. */ + assert(offset_1 <= dictAndPrefixLength); + assert(offset_2 <= dictAndPrefixLength); /* Main Search Loop */ while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ @@ -113,50 +241,37 @@ size_t ZSTD_compressBlock_fast_generic( U32 const matchIndex = hashTable[h]; const BYTE* match = base + matchIndex; const U32 repIndex = current + 1 - offset_1; - const BYTE* repMatch = (dictMode == ZSTD_dictMatchState - && repIndex < prefixStartIndex) ? + const BYTE* repMatch = (repIndex < prefixStartIndex) ? dictBase + (repIndex - dictIndexDelta) : base + repIndex; hashTable[h] = current; /* update hash table */ - if ( (dictMode == ZSTD_dictMatchState) - && ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */ + if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */ && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; ip++; ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH); - } else if ( dictMode == ZSTD_noDict - && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) { - mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4; - ip++; - ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH); } else if ( (matchIndex <= prefixStartIndex) ) { - if (dictMode == ZSTD_dictMatchState) { - size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls); - U32 const dictMatchIndex = dictHashTable[dictHash]; - const BYTE* dictMatch = dictBase + dictMatchIndex; - if (dictMatchIndex <= dictStartIndex || - MEM_read32(dictMatch) != MEM_read32(ip)) { - assert(stepSize >= 1); - ip += ((ip-anchor) >> kSearchStrength) + stepSize; - continue; - } else { - /* found a dict match */ - U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta); - mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4; - while (((ip>anchor) & (dictMatch>dictStart)) - && (ip[-1] == dictMatch[-1])) { - ip--; dictMatch--; mLength++; - } /* catch up */ - offset_2 = offset_1; - offset_1 = offset; - ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH); - } - } else { + size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls); + U32 const dictMatchIndex = dictHashTable[dictHash]; + const BYTE* dictMatch = dictBase + dictMatchIndex; + if (dictMatchIndex <= dictStartIndex || + MEM_read32(dictMatch) != MEM_read32(ip)) { assert(stepSize >= 1); ip += ((ip-anchor) >> kSearchStrength) + stepSize; continue; + } else { + /* found a dict match */ + U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta); + mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4; + while (((ip>anchor) & (dictMatch>dictStart)) + && (ip[-1] == dictMatch[-1])) { + ip--; dictMatch--; mLength++; + } /* catch up */ + offset_2 = offset_1; + offset_1 = offset; + ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH); } } else if (MEM_read32(match) != MEM_read32(ip)) { /* it's not a match, and we're not going to check the dictionary */ @@ -185,41 +300,27 @@ size_t ZSTD_compressBlock_fast_generic( hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); /* check immediate repcode */ - if (dictMode == ZSTD_dictMatchState) { - while (ip <= ilimit) { - U32 const current2 = (U32)(ip-base); - U32 const repIndex2 = current2 - offset_2; - const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? - dictBase - dictIndexDelta + repIndex2 : - base + repIndex2; - if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) - && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { - const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; - size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; - U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ - ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH); - hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; - ip += repLength2; - anchor = ip; - continue; - } - break; - } - } - - if (dictMode == ZSTD_noDict) { - while ( (ip <= ilimit) - && ( (offset_2>0) - & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) { - /* store sequence */ - size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4; - U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */ - hashTable[ZSTD_hashPtr(ip, hlog, mls)] = (U32)(ip-base); - ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH); - ip += rLength; + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; + const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? + dictBase - dictIndexDelta + repIndex2 : + base + repIndex2; + if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; + size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; + U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH); + hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; + ip += repLength2; anchor = ip; - continue; /* faster when present ... (?) */ - } } } } + continue; + } + break; + } + } + } /* save reps for next block */ rep[0] = offset_1 ? offset_1 : offsetSaved; @@ -229,28 +330,6 @@ size_t ZSTD_compressBlock_fast_generic( return iend - anchor; } - -size_t ZSTD_compressBlock_fast( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], - void const* src, size_t srcSize) -{ - ZSTD_compressionParameters const* cParams = &ms->cParams; - U32 const mls = cParams->minMatch; - assert(ms->dictMatchState == NULL); - switch(mls) - { - default: /* includes case 3 */ - case 4 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict); - case 5 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict); - case 6 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict); - case 7 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict); - } -} - size_t ZSTD_compressBlock_fast_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) @@ -262,13 +341,13 @@ size_t ZSTD_compressBlock_fast_dictMatchState( { default: /* includes case 3 */ case 4 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState); + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4); case 5 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState); + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5); case 6 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState); + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6); case 7 : - return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState); + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7); } } diff --git a/lib/compress/zstd_lazy.h b/lib/compress/zstd_lazy.h index ef85a6df9c8f..bb1763069f3b 100644 --- a/lib/compress/zstd_lazy.h +++ b/lib/compress/zstd_lazy.h @@ -19,7 +19,7 @@ extern "C" { U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip); -void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). pre-emptively increase value of ZSTD_DUBT_UNSORTED_MARK */ +void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */ size_t ZSTD_compressBlock_btlazy2( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], diff --git a/lib/compress/zstd_ldm.c b/lib/compress/zstd_ldm.c index 58eb2ffe4db3..784d20f3ab71 100644 --- a/lib/compress/zstd_ldm.c +++ b/lib/compress/zstd_ldm.c @@ -429,7 +429,7 @@ size_t ZSTD_ldm_generateSequences( */ assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); /* The input could be very large (in zstdmt), so it must be broken up into - * chunks to enforce the maximmum distance and handle overflow correction. + * chunks to enforce the maximum distance and handle overflow correction. */ assert(sequences->pos <= sequences->size); assert(sequences->size <= sequences->capacity); diff --git a/lib/compress/zstd_opt.c b/lib/compress/zstd_opt.c index 44de6e97fd20..efb69d3267d1 100644 --- a/lib/compress/zstd_opt.c +++ b/lib/compress/zstd_opt.c @@ -64,9 +64,15 @@ MEM_STATIC double ZSTD_fCost(U32 price) } #endif +static int ZSTD_compressedLiterals(optState_t const* const optPtr) +{ + return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed; +} + static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel) { - optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel); + if (ZSTD_compressedLiterals(optPtr)) + optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel); optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel); optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel); optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel); @@ -99,6 +105,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, const BYTE* const src, size_t const srcSize, int const optLevel) { + int const compressedLiterals = ZSTD_compressedLiterals(optPtr); DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize); optPtr->priceType = zop_dynamic; @@ -113,9 +120,10 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, /* huffman table presumed generated by dictionary */ optPtr->priceType = zop_dynamic; - assert(optPtr->litFreq != NULL); - optPtr->litSum = 0; - { unsigned lit; + if (compressedLiterals) { + unsigned lit; + assert(optPtr->litFreq != NULL); + optPtr->litSum = 0; for (lit=0; lit<=MaxLit; lit++) { U32 const scaleLog = 11; /* scale to 2K */ U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit); @@ -163,10 +171,11 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, } else { /* not a dictionary */ assert(optPtr->litFreq != NULL); - { unsigned lit = MaxLit; + if (compressedLiterals) { + unsigned lit = MaxLit; HIST_count_simple(optPtr->litFreq, &lit, src, srcSize); /* use raw first block to init statistics */ + optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); } - optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); { unsigned ll; for (ll=0; ll<=MaxLL; ll++) @@ -190,7 +199,8 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, } else { /* new block : re-use previous statistics, scaled down */ - optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); + if (compressedLiterals) + optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0); optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0); optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0); @@ -207,6 +217,10 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength, int optLevel) { if (litLength == 0) return 0; + + if (!ZSTD_compressedLiterals(optPtr)) + return (litLength << 3) * BITCOST_MULTIPLIER; /* Uncompressed - 8 bytes per literal. */ + if (optPtr->priceType == zop_predef) return (litLength*6) * BITCOST_MULTIPLIER; /* 6 bit per literal - no statistic used */ @@ -310,7 +324,8 @@ static void ZSTD_updateStats(optState_t* const optPtr, U32 offsetCode, U32 matchLength) { /* literals */ - { U32 u; + if (ZSTD_compressedLiterals(optPtr)) { + U32 u; for (u=0; u < litLength; u++) optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD; optPtr->litSum += litLength*ZSTD_LITFREQ_ADD; @@ -870,7 +885,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, /* large match -> immediate encoding */ { U32 const maxML = matches[nbMatches-1].len; U32 const maxOffset = matches[nbMatches-1].off; - DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new serie", + DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series", nbMatches, maxML, maxOffset, (U32)(ip-prefixStart)); if (maxML > sufficient_len) { @@ -1108,7 +1123,8 @@ static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus) /* used in 2-pass strategy */ MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr) { - optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0); + if (ZSTD_compressedLiterals(optPtr)) + optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0); optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0); optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0); optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0); @@ -1117,7 +1133,7 @@ MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr) /* ZSTD_initStats_ultra(): * make a first compression pass, just to seed stats with more accurate starting values. * only works on first block, with no dictionary and no ldm. - * this function cannot error, hence its constract must be respected. + * this function cannot error, hence its contract must be respected. */ static void ZSTD_initStats_ultra(ZSTD_matchState_t* ms, diff --git a/lib/compress/zstdmt_compress.c b/lib/compress/zstdmt_compress.c index 2cbd6ffade38..38fbb907685b 100644 --- a/lib/compress/zstdmt_compress.c +++ b/lib/compress/zstdmt_compress.c @@ -22,6 +22,7 @@ /* ====== Dependencies ====== */ #include /* memcpy, memset */ #include /* INT_MAX, UINT_MAX */ +#include "mem.h" /* MEM_STATIC */ #include "pool.h" /* threadpool */ #include "threading.h" /* mutex */ #include "zstd_compress_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */ @@ -456,7 +457,7 @@ typedef struct { * Must be acquired after the main mutex when acquiring both. */ ZSTD_pthread_mutex_t ldmWindowMutex; - ZSTD_pthread_cond_t ldmWindowCond; /* Signaled when ldmWindow is udpated */ + ZSTD_pthread_cond_t ldmWindowCond; /* Signaled when ldmWindow is updated */ ZSTD_window_t ldmWindow; /* A thread-safe copy of ldmState.window */ } serialState_t; @@ -647,7 +648,7 @@ static void ZSTDMT_compressionJob(void* jobDescription) buffer_t dstBuff = job->dstBuff; size_t lastCBlockSize = 0; - /* ressources */ + /* resources */ if (cctx==NULL) JOB_ERROR(ERROR(memory_allocation)); if (dstBuff.start == NULL) { /* streaming job : doesn't provide a dstBuffer */ dstBuff = ZSTDMT_getBuffer(job->bufPool); @@ -672,7 +673,7 @@ static void ZSTDMT_compressionJob(void* jobDescription) if (ZSTD_isError(initError)) JOB_ERROR(initError); } else { /* srcStart points at reloaded section */ U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size; - { size_t const forceWindowError = ZSTD_CCtxParam_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob); + { size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob); if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError); } { size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, @@ -864,14 +865,10 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) { * Internal use only */ size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers) { - if (nbWorkers > ZSTDMT_NBWORKERS_MAX) nbWorkers = ZSTDMT_NBWORKERS_MAX; - params->nbWorkers = nbWorkers; - params->overlapLog = ZSTDMT_OVERLAPLOG_DEFAULT; - params->jobSize = 0; - return nbWorkers; + return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers); } -ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem) +MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, ZSTD_customMem cMem) { ZSTDMT_CCtx* mtctx; U32 nbJobs = nbWorkers + 2; @@ -906,6 +903,17 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem) return mtctx; } +ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem) +{ +#ifdef ZSTD_MULTITHREAD + return ZSTDMT_createCCtx_advanced_internal(nbWorkers, cMem); +#else + (void)nbWorkers; + (void)cMem; + return NULL; +#endif +} + ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers) { return ZSTDMT_createCCtx_advanced(nbWorkers, ZSTD_defaultCMem); @@ -986,26 +994,13 @@ ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params, { case ZSTDMT_p_jobSize : DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter : set jobSize to %i", value); - if ( value != 0 /* default */ - && value < ZSTDMT_JOBSIZE_MIN) - value = ZSTDMT_JOBSIZE_MIN; - assert(value >= 0); - if (value > ZSTDMT_JOBSIZE_MAX) value = ZSTDMT_JOBSIZE_MAX; - params->jobSize = value; - return value; - + return ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, value); case ZSTDMT_p_overlapLog : DEBUGLOG(4, "ZSTDMT_p_overlapLog : %i", value); - if (value < ZSTD_OVERLAPLOG_MIN) value = ZSTD_OVERLAPLOG_MIN; - if (value > ZSTD_OVERLAPLOG_MAX) value = ZSTD_OVERLAPLOG_MAX; - params->overlapLog = value; - return value; - + return ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, value); case ZSTDMT_p_rsyncable : - value = (value != 0); - params->rsyncable = value; - return value; - + DEBUGLOG(4, "ZSTD_p_rsyncable : %i", value); + return ZSTD_CCtxParams_setParameter(params, ZSTD_c_rsyncable, value); default : return ERROR(parameter_unsupported); } @@ -1021,32 +1016,29 @@ size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, { switch (parameter) { case ZSTDMT_p_jobSize: - assert(mtctx->params.jobSize <= INT_MAX); - *value = (int)(mtctx->params.jobSize); - break; + return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_jobSize, value); case ZSTDMT_p_overlapLog: - *value = mtctx->params.overlapLog; - break; + return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_overlapLog, value); case ZSTDMT_p_rsyncable: - *value = mtctx->params.rsyncable; - break; + return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_rsyncable, value); default: return ERROR(parameter_unsupported); } - return 0; } /* Sets parameters relevant to the compression job, * initializing others to default values. */ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params) { - ZSTD_CCtx_params jobParams; - memset(&jobParams, 0, sizeof(jobParams)); - - jobParams.cParams = params.cParams; - jobParams.fParams = params.fParams; - jobParams.compressionLevel = params.compressionLevel; - + ZSTD_CCtx_params jobParams = params; + /* Clear parameters related to multithreading */ + jobParams.forceWindow = 0; + jobParams.nbWorkers = 0; + jobParams.jobSize = 0; + jobParams.overlapLog = 0; + jobParams.rsyncable = 0; + memset(&jobParams.ldmParams, 0, sizeof(ldmParams_t)); + memset(&jobParams.customMem, 0, sizeof(ZSTD_customMem)); return jobParams; } @@ -1056,7 +1048,7 @@ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params) static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers) { if (POOL_resize(mtctx->factory, nbWorkers)) return ERROR(memory_allocation); - CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbWorkers) ); + FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbWorkers) ); mtctx->bufPool = ZSTDMT_expandBufferPool(mtctx->bufPool, nbWorkers); if (mtctx->bufPool == NULL) return ERROR(memory_allocation); mtctx->cctxPool = ZSTDMT_expandCCtxPool(mtctx->cctxPool, nbWorkers); @@ -1263,7 +1255,7 @@ static size_t ZSTDMT_compress_advanced_internal( if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize)) return ERROR(memory_allocation); - CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbJobs) ); /* only expands if necessary */ + FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) ); /* only expands if necessary */ { unsigned u; for (u=0; u params.nbWorkers) - CHECK_F( ZSTDMT_resize(mtctx, params.nbWorkers) ); + FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) ); if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN; if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX; @@ -1547,7 +1539,7 @@ size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel) { /* ZSTDMT_writeLastEmptyBlock() * Write a single empty block with an end-of-frame to finish a frame. * Job must be created from streaming variant. - * This function is always successfull if expected conditions are fulfilled. + * This function is always successful if expected conditions are fulfilled. */ static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job) { @@ -1987,7 +1979,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, assert(input->pos <= input->size); if (mtctx->singleBlockingThread) { /* delegate to single-thread (synchronous) */ - return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp); + return ZSTD_compressStream2(mtctx->cctxPool->cctx[0], output, input, endOp); } if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) { @@ -2051,7 +2043,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, || ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) { /* must finish the frame with a zero-size block */ size_t const jobSize = mtctx->inBuff.filled; assert(mtctx->inBuff.filled <= mtctx->targetSectionSize); - CHECK_F( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) ); + FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) ); } /* check for potential compressed data ready to be flushed */ @@ -2065,7 +2057,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input) { - CHECK_F( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) ); + FORWARD_IF_ERROR( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) ); /* recommended next input size : fill current input buffer */ return mtctx->targetSectionSize - mtctx->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */ @@ -2082,7 +2074,7 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* ou || ((endFrame==ZSTD_e_end) && !mtctx->frameEnded)) { /* need a last 0-size block to end frame */ DEBUGLOG(5, "ZSTDMT_flushStream_internal : create a new job (%u bytes, end:%u)", (U32)srcSize, (U32)endFrame); - CHECK_F( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) ); + FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) ); } /* check if there is any data available to flush */ diff --git a/lib/compress/zstdmt_compress.h b/lib/compress/zstdmt_compress.h index ee771681fa59..12e6bcb3a338 100644 --- a/lib/compress/zstdmt_compress.h +++ b/lib/compress/zstdmt_compress.h @@ -17,10 +17,25 @@ /* Note : This is an internal API. - * Some methods are still exposed (ZSTDLIB_API), + * These APIs used to be exposed with ZSTDLIB_API, * because it used to be the only way to invoke MT compression. - * Now, it's recommended to use ZSTD_compress_generic() instead. - * These methods will stop being exposed in a future version */ + * Now, it's recommended to use ZSTD_compress2 and ZSTD_compressStream2() + * instead. + * + * If you depend on these APIs and can't switch, then define + * ZSTD_LEGACY_MULTITHREADED_API when making the dynamic library. + * However, we may completely remove these functions in a future + * release, so please switch soon. + * + * This API requires ZSTD_MULTITHREAD to be defined during compilation, + * otherwise ZSTDMT_createCCtx*() will fail. + */ + +#ifdef ZSTD_LEGACY_MULTITHREADED_API +# define ZSTDMT_API ZSTDLIB_API +#else +# define ZSTDMT_API +#endif /* === Dependencies === */ #include /* size_t */ @@ -40,17 +55,19 @@ /* === Memory management === */ typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx; -ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers); -ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, +/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */ +ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers); +/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */ +ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem); -ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx); +ZSTDMT_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx); -ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx); +ZSTDMT_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx); /* === Simple one-pass compression function === */ -ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx, +ZSTDMT_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel); @@ -59,31 +76,31 @@ ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx, /* === Streaming functions === */ -ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel); -ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize); /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */ +ZSTDMT_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel); +ZSTDMT_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize); /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */ -ZSTDLIB_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx); -ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +ZSTDMT_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx); +ZSTDMT_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ -ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ +ZSTDMT_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ +ZSTDMT_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ /* === Advanced functions and parameters === */ -ZSTDLIB_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict, - ZSTD_parameters params, - int overlapLog); +ZSTDMT_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, + ZSTD_parameters params, + int overlapLog); -ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx, +ZSTDMT_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx, const void* dict, size_t dictSize, /* dict can be released after init, a local copy is preserved within zcs */ ZSTD_parameters params, unsigned long long pledgedSrcSize); /* pledgedSrcSize is optional and can be zero == unknown */ -ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx, +ZSTDMT_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx, const ZSTD_CDict* cdict, ZSTD_frameParameters fparams, unsigned long long pledgedSrcSize); /* note : zero means empty */ @@ -92,7 +109,7 @@ ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx, * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */ typedef enum { ZSTDMT_p_jobSize, /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */ - ZSTDMT_p_overlapLog, /* Each job may reload a part of previous job to enhance compressionr ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */ + ZSTDMT_p_overlapLog, /* Each job may reload a part of previous job to enhance compression ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */ ZSTDMT_p_rsyncable /* Enables rsyncable mode. */ } ZSTDMT_parameter; @@ -101,12 +118,12 @@ typedef enum { * The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__ * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions. * @return : 0, or an error code (which can be tested using ZSTD_isError()) */ -ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value); +ZSTDMT_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value); /* ZSTDMT_getMTCtxParameter() : * Query the ZSTDMT_CCtx for a parameter value. * @return : 0, or an error code (which can be tested using ZSTD_isError()) */ -ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value); +ZSTDMT_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value); /*! ZSTDMT_compressStream_generic() : @@ -116,7 +133,7 @@ ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter * 0 if fully flushed * or an error code * note : needs to be init using any ZSTD_initCStream*() variant */ -ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, +ZSTDMT_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input, ZSTD_EndDirective endOp); diff --git a/lib/decompress/zstd_ddict.c b/lib/decompress/zstd_ddict.c index 2ad0440684ca..0af3d23bfe2d 100644 --- a/lib/decompress/zstd_ddict.c +++ b/lib/decompress/zstd_ddict.c @@ -105,9 +105,9 @@ ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict, ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE); /* load entropy tables */ - CHECK_E( ZSTD_loadDEntropy(&ddict->entropy, - ddict->dictContent, ddict->dictSize), - dictionary_corrupted ); + RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy( + &ddict->entropy, ddict->dictContent, ddict->dictSize)), + dictionary_corrupted); ddict->entropyPresent = 1; return 0; } @@ -133,7 +133,7 @@ static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ /* parse dictionary content */ - CHECK_F( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) ); + FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) ); return 0; } diff --git a/lib/decompress/zstd_decompress.c b/lib/decompress/zstd_decompress.c index feef1ef67abd..675596f5aa92 100644 --- a/lib/decompress/zstd_decompress.c +++ b/lib/decompress/zstd_decompress.c @@ -106,6 +106,7 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx) dctx->ddictLocal = NULL; dctx->dictEnd = NULL; dctx->ddictIsCold = 0; + dctx->dictUses = ZSTD_dont_use; dctx->inBuff = NULL; dctx->inBuffSize = 0; dctx->outBuffSize = 0; @@ -147,13 +148,20 @@ ZSTD_DCtx* ZSTD_createDCtx(void) return ZSTD_createDCtx_advanced(ZSTD_defaultCMem); } +static void ZSTD_clearDict(ZSTD_DCtx* dctx) +{ + ZSTD_freeDDict(dctx->ddictLocal); + dctx->ddictLocal = NULL; + dctx->ddict = NULL; + dctx->dictUses = ZSTD_dont_use; +} + size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx) { if (dctx==NULL) return 0; /* support free on NULL */ - if (dctx->staticSize) return ERROR(memory_allocation); /* not compatible with static DCtx */ + RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx"); { ZSTD_customMem const cMem = dctx->customMem; - ZSTD_freeDDict(dctx->ddictLocal); - dctx->ddictLocal = NULL; + ZSTD_clearDict(dctx); ZSTD_free(dctx->inBuff, cMem); dctx->inBuff = NULL; #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) @@ -203,7 +211,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size) static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format) { size_t const minInputSize = ZSTD_startingInputLength(format); - if (srcSize < minInputSize) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong); { BYTE const fhd = ((const BYTE*)src)[minInputSize-1]; U32 const dictID= fhd & 3; @@ -238,7 +246,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s memset(zfhPtr, 0, sizeof(*zfhPtr)); /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */ if (srcSize < minInputSize) return minInputSize; - if (src==NULL) return ERROR(GENERIC); /* invalid parameter */ + RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter"); if ( (format != ZSTD_f_zstd1_magicless) && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) { @@ -251,7 +259,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s zfhPtr->frameType = ZSTD_skippableFrame; return 0; } - return ERROR(prefix_unknown); + RETURN_ERROR(prefix_unknown); } /* ensure there is enough `srcSize` to fully read/decode frame header */ @@ -269,14 +277,13 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s U64 windowSize = 0; U32 dictID = 0; U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN; - if ((fhdByte & 0x08) != 0) - return ERROR(frameParameter_unsupported); /* reserved bits, must be zero */ + RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported, + "reserved bits, must be zero"); if (!singleSegment) { BYTE const wlByte = ip[pos++]; U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN; - if (windowLog > ZSTD_WINDOWLOG_MAX) - return ERROR(frameParameter_windowTooLarge); + RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge); windowSize = (1ULL << windowLog); windowSize += (windowSize >> 3) * (wlByte&7); } @@ -348,12 +355,11 @@ static size_t readSkippableFrameSize(void const* src, size_t srcSize) size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE; U32 sizeU32; - if (srcSize < ZSTD_SKIPPABLEHEADERSIZE) - return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong); sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE); - if ((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32) - return ERROR(frameParameter_unsupported); + RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32, + frameParameter_unsupported); return skippableHeaderSize + sizeU32; } @@ -428,13 +434,89 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he { size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format); if (ZSTD_isError(result)) return result; /* invalid header */ - if (result>0) return ERROR(srcSize_wrong); /* headerSize too small */ - if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID)) - return ERROR(dictionary_wrong); + RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small"); +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + /* Skip the dictID check in fuzzing mode, because it makes the search + * harder. + */ + RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID), + dictionary_wrong); +#endif if (dctx->fParams.checksumFlag) XXH64_reset(&dctx->xxhState, 0); return 0; } +static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret) +{ + ZSTD_frameSizeInfo frameSizeInfo; + frameSizeInfo.compressedSize = ret; + frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR; + return frameSizeInfo; +} + +static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize) +{ + ZSTD_frameSizeInfo frameSizeInfo; + memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo)); + +#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) + if (ZSTD_isLegacy(src, srcSize)) + return ZSTD_findFrameSizeInfoLegacy(src, srcSize); +#endif + + if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE) + && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { + frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize); + return frameSizeInfo; + } else { + const BYTE* ip = (const BYTE*)src; + const BYTE* const ipstart = ip; + size_t remainingSize = srcSize; + size_t nbBlocks = 0; + ZSTD_frameHeader zfh; + + /* Extract Frame Header */ + { size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize); + if (ZSTD_isError(ret)) + return ZSTD_errorFrameSizeInfo(ret); + if (ret > 0) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + } + + ip += zfh.headerSize; + remainingSize -= zfh.headerSize; + + /* Iterate over each block */ + while (1) { + blockProperties_t blockProperties; + size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); + if (ZSTD_isError(cBlockSize)) + return ZSTD_errorFrameSizeInfo(cBlockSize); + + if (ZSTD_blockHeaderSize + cBlockSize > remainingSize) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + + ip += ZSTD_blockHeaderSize + cBlockSize; + remainingSize -= ZSTD_blockHeaderSize + cBlockSize; + nbBlocks++; + + if (blockProperties.lastBlock) break; + } + + /* Final frame content checksum */ + if (zfh.checksumFlag) { + if (remainingSize < 4) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + ip += 4; + } + + frameSizeInfo.compressedSize = ip - ipstart; + frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) + ? zfh.frameContentSize + : nbBlocks * zfh.blockSizeMax; + return frameSizeInfo; + } +} /** ZSTD_findFrameCompressedSize() : * compatible with legacy mode @@ -443,53 +525,34 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he * @return : the compressed size of the frame starting at `src` */ size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize) { -#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) - if (ZSTD_isLegacy(src, srcSize)) - return ZSTD_findFrameCompressedSizeLegacy(src, srcSize); -#endif - if ( (srcSize >= ZSTD_SKIPPABLEHEADERSIZE) - && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START ) { - return readSkippableFrameSize(src, srcSize); - } else { - const BYTE* ip = (const BYTE*)src; - const BYTE* const ipstart = ip; - size_t remainingSize = srcSize; - ZSTD_frameHeader zfh; - - /* Extract Frame Header */ - { size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize); - if (ZSTD_isError(ret)) return ret; - if (ret > 0) return ERROR(srcSize_wrong); - } - - ip += zfh.headerSize; - remainingSize -= zfh.headerSize; - - /* Loop on each block */ - while (1) { - blockProperties_t blockProperties; - size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) return cBlockSize; - - if (ZSTD_blockHeaderSize + cBlockSize > remainingSize) - return ERROR(srcSize_wrong); - - ip += ZSTD_blockHeaderSize + cBlockSize; - remainingSize -= ZSTD_blockHeaderSize + cBlockSize; - - if (blockProperties.lastBlock) break; - } - - if (zfh.checksumFlag) { /* Final frame content checksum */ - if (remainingSize < 4) return ERROR(srcSize_wrong); - ip += 4; - } - - return ip - ipstart; - } + ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize); + return frameSizeInfo.compressedSize; } +/** ZSTD_decompressBound() : + * compatible with legacy mode + * `src` must point to the start of a ZSTD frame or a skippeable frame + * `srcSize` must be at least as large as the frame contained + * @return : the maximum decompressed size of the compressed source + */ +unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize) +{ + unsigned long long bound = 0; + /* Iterate over each frame */ + while (srcSize > 0) { + ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize); + size_t const compressedSize = frameSizeInfo.compressedSize; + unsigned long long const decompressedBound = frameSizeInfo.decompressedBound; + if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR) + return ZSTD_CONTENTSIZE_ERROR; + src = (const BYTE*)src + compressedSize; + srcSize -= compressedSize; + bound += decompressedBound; + } + return bound; +} + /*-************************************************************* * Frame decoding @@ -522,9 +585,9 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity, DEBUGLOG(5, "ZSTD_copyRawBlock"); if (dst == NULL) { if (srcSize == 0) return 0; - return ERROR(dstBuffer_null); + RETURN_ERROR(dstBuffer_null); } - if (srcSize > dstCapacity) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall); memcpy(dst, src, srcSize); return srcSize; } @@ -535,9 +598,9 @@ static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity, { if (dst == NULL) { if (regenSize == 0) return 0; - return ERROR(dstBuffer_null); + RETURN_ERROR(dstBuffer_null); } - if (regenSize > dstCapacity) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall); memset(dst, b, regenSize); return regenSize; } @@ -560,15 +623,16 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr); /* check */ - if (remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize) - return ERROR(srcSize_wrong); + RETURN_ERROR_IF( + remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize, + srcSize_wrong); /* Frame Header */ { size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_FRAMEHEADERSIZE_PREFIX); if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize; - if (remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize) - return ERROR(srcSize_wrong); - CHECK_F( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) ); + RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize, + srcSize_wrong); + FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) ); ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize; } @@ -581,7 +645,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, ip += ZSTD_blockHeaderSize; remainingSrcSize -= ZSTD_blockHeaderSize; - if (cBlockSize > remainingSrcSize) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong); switch(blockProperties.blockType) { @@ -596,7 +660,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, break; case bt_reserved : default: - return ERROR(corruption_detected); + RETURN_ERROR(corruption_detected); } if (ZSTD_isError(decodedSize)) return decodedSize; @@ -609,15 +673,15 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, } if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) { - if ((U64)(op-ostart) != dctx->fParams.frameContentSize) { - return ERROR(corruption_detected); - } } + RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize, + corruption_detected); + } if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */ U32 const checkCalc = (U32)XXH64_digest(&dctx->xxhState); U32 checkRead; - if (remainingSrcSize<4) return ERROR(checksum_wrong); + RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong); checkRead = MEM_readLE32(ip); - if (checkRead != checkCalc) return ERROR(checksum_wrong); + RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong); ip += 4; remainingSrcSize -= 4; } @@ -652,8 +716,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, size_t decodedSize; size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize); if (ZSTD_isError(frameSize)) return frameSize; - /* legacy support is not compatible with static dctx */ - if (dctx->staticSize) return ERROR(memory_allocation); + RETURN_ERROR_IF(dctx->staticSize, memory_allocation, + "legacy support is not compatible with static dctx"); decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize); if (ZSTD_isError(decodedSize)) return decodedSize; @@ -676,7 +740,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, size_t const skippableSize = readSkippableFrameSize(src, srcSize); if (ZSTD_isError(skippableSize)) return skippableSize; - if (srcSize < skippableSize) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize < skippableSize, srcSize_wrong); src = (const BYTE *)src + skippableSize; srcSize -= skippableSize; @@ -685,29 +749,29 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, if (ddict) { /* we were called from ZSTD_decompress_usingDDict */ - CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict)); + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict)); } else { /* this will initialize correctly with no dict if dict == NULL, so * use this in all cases but ddict */ - CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize)); + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize)); } ZSTD_checkContinuity(dctx, dst); { const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, &src, &srcSize); - if ( (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown) - && (moreThan1Frame==1) ) { - /* at least one frame successfully completed, - * but following bytes are garbage : - * it's more likely to be a srcSize error, - * specifying more bytes than compressed size of frame(s). - * This error message replaces ERROR(prefix_unknown), - * which would be confusing, as the first header is actually correct. - * Note that one could be unlucky, it might be a corruption error instead, - * happening right at the place where we expect zstd magic bytes. - * But this is _much_ less likely than a srcSize field error. */ - return ERROR(srcSize_wrong); - } + RETURN_ERROR_IF( + (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown) + && (moreThan1Frame==1), + srcSize_wrong, + "at least one frame successfully completed, but following " + "bytes are garbage: it's more likely to be a srcSize error, " + "specifying more bytes than compressed size of frame(s). This " + "error message replaces ERROR(prefix_unknown), which would be " + "confusing, as the first header is actually correct. Note that " + "one could be unlucky, it might be a corruption error instead, " + "happening right at the place where we expect zstd magic " + "bytes. But this is _much_ less likely than a srcSize field " + "error."); if (ZSTD_isError(res)) return res; assert(res <= dstCapacity); dst = (BYTE*)dst + res; @@ -716,7 +780,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, moreThan1Frame = 1; } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ - if (srcSize) return ERROR(srcSize_wrong); /* input not entirely consumed */ + RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed"); return (BYTE*)dst - (BYTE*)dststart; } @@ -730,9 +794,26 @@ size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, } +static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx) +{ + switch (dctx->dictUses) { + default: + assert(0 /* Impossible */); + /* fall-through */ + case ZSTD_dont_use: + ZSTD_clearDict(dctx); + return NULL; + case ZSTD_use_indefinitely: + return dctx->ddict; + case ZSTD_use_once: + dctx->dictUses = ZSTD_dont_use; + return dctx->ddict; + } +} + size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) { - return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0); + return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, ZSTD_getDDict(dctx)); } @@ -741,7 +822,7 @@ size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t sr #if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1) size_t regenSize; ZSTD_DCtx* const dctx = ZSTD_createDCtx(); - if (dctx==NULL) return ERROR(memory_allocation); + RETURN_ERROR_IF(dctx==NULL, memory_allocation); regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize); ZSTD_freeDCtx(dctx); return regenSize; @@ -791,8 +872,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c { DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize); /* Sanity check */ - if (srcSize != dctx->expected) - return ERROR(srcSize_wrong); /* not allowed */ + RETURN_ERROR_IF(srcSize != dctx->expected, srcSize_wrong, "not allowed"); if (dstCapacity) ZSTD_checkContinuity(dctx, dst); switch (dctx->stage) @@ -817,7 +897,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c case ZSTDds_decodeFrameHeader: assert(src != NULL); memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize); - CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize)); + FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize)); dctx->expected = ZSTD_blockHeaderSize; dctx->stage = ZSTDds_decodeBlockHeader; return 0; @@ -867,7 +947,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c break; case bt_reserved : /* should never happen */ default: - return ERROR(corruption_detected); + RETURN_ERROR(corruption_detected); } if (ZSTD_isError(rSize)) return rSize; DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize); @@ -876,10 +956,10 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */ DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize); - if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) { - if (dctx->decodedSize != dctx->fParams.frameContentSize) { - return ERROR(corruption_detected); - } } + RETURN_ERROR_IF( + dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN + && dctx->decodedSize != dctx->fParams.frameContentSize, + corruption_detected); if (dctx->fParams.checksumFlag) { /* another round for frame checksum */ dctx->expected = 4; dctx->stage = ZSTDds_checkChecksum; @@ -900,7 +980,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c { U32 const h32 = (U32)XXH64_digest(&dctx->xxhState); U32 const check32 = MEM_readLE32(src); DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32); - if (check32 != h32) return ERROR(checksum_wrong); + RETURN_ERROR_IF(check32 != h32, checksum_wrong); dctx->expected = 0; dctx->stage = ZSTDds_getFrameHeaderSize; return 0; @@ -921,7 +1001,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c default: assert(0); /* impossible */ - return ERROR(GENERIC); /* some compiler require default to do something */ + RETURN_ERROR(GENERIC); /* some compiler require default to do something */ } } @@ -945,7 +1025,7 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, const BYTE* dictPtr = (const BYTE*)dict; const BYTE* const dictEnd = dictPtr + dictSize; - if (dictSize <= 8) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted); assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY); /* dict must be valid */ dictPtr += 8; /* skip header = magic + dictID */ @@ -964,16 +1044,16 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, dictPtr, dictEnd - dictPtr, workspace, workspaceSize); #endif - if (HUF_isError(hSize)) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted); dictPtr += hSize; } { short offcodeNCount[MaxOff+1]; unsigned offcodeMaxValue = MaxOff, offcodeLog; size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted); - if (offcodeMaxValue > MaxOff) return ERROR(dictionary_corrupted); - if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted); + RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted); ZSTD_buildFSETable( entropy->OFTable, offcodeNCount, offcodeMaxValue, OF_base, OF_bits, @@ -984,9 +1064,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, { short matchlengthNCount[MaxML+1]; unsigned matchlengthMaxValue = MaxML, matchlengthLog; size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted); - if (matchlengthMaxValue > MaxML) return ERROR(dictionary_corrupted); - if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted); + RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted); ZSTD_buildFSETable( entropy->MLTable, matchlengthNCount, matchlengthMaxValue, ML_base, ML_bits, @@ -997,9 +1077,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, { short litlengthNCount[MaxLL+1]; unsigned litlengthMaxValue = MaxLL, litlengthLog; size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr); - if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted); - if (litlengthMaxValue > MaxLL) return ERROR(dictionary_corrupted); - if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted); + RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted); + RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted); ZSTD_buildFSETable( entropy->LLTable, litlengthNCount, litlengthMaxValue, LL_base, LL_bits, @@ -1007,12 +1087,13 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, dictPtr += litlengthHeaderSize; } - if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted); { int i; size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12)); for (i=0; i<3; i++) { U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4; - if (rep==0 || rep >= dictContentSize) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(rep==0 || rep >= dictContentSize, + dictionary_corrupted); entropy->rep[i] = rep; } } @@ -1030,7 +1111,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict /* load entropy tables */ { size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize); - if (ZSTD_isError(eSize)) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted); dict = (const char*)dict + eSize; dictSize -= eSize; } @@ -1064,9 +1145,11 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx) size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) { - CHECK_F( ZSTD_decompressBegin(dctx) ); + FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) ); if (dict && dictSize) - CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted); + RETURN_ERROR_IF( + ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)), + dictionary_corrupted); return 0; } @@ -1085,7 +1168,7 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) DEBUGLOG(4, "DDict is %s", dctx->ddictIsCold ? "~cold~" : "hot!"); } - CHECK_F( ZSTD_decompressBegin(dctx) ); + FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) ); if (ddict) { /* NULL ddict is equivalent to no dictionary */ ZSTD_copyDDictParameters(dctx, ddict); } @@ -1104,7 +1187,7 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize) } /*! ZSTD_getDictID_fromFrame() : - * Provides the dictID required to decompresse frame stored within `src`. + * Provides the dictID required to decompress frame stored within `src`. * If @return == 0, the dictID could not be decoded. * This could for one of the following reasons : * - The frame does not require a dictionary (most common case). @@ -1176,15 +1259,14 @@ size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) { - if (dctx->streamStage != zdss_init) return ERROR(stage_wrong); - ZSTD_freeDDict(dctx->ddictLocal); + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong); + ZSTD_clearDict(dctx); if (dict && dictSize >= 8) { dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem); - if (dctx->ddictLocal == NULL) return ERROR(memory_allocation); - } else { - dctx->ddictLocal = NULL; + RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation); + dctx->ddict = dctx->ddictLocal; + dctx->dictUses = ZSTD_use_indefinitely; } - dctx->ddict = dctx->ddictLocal; return 0; } @@ -1200,7 +1282,9 @@ size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSi size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) { - return ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType); + FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType)); + dctx->dictUses = ZSTD_use_once; + return 0; } size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize) @@ -1215,9 +1299,8 @@ size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSiz size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize) { DEBUGLOG(4, "ZSTD_initDStream_usingDict"); - zds->streamStage = zdss_init; - zds->noForwardProgress = 0; - CHECK_F( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) ); + FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) ); return ZSTD_FRAMEHEADERSIZE_PREFIX; } @@ -1225,7 +1308,7 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di size_t ZSTD_initDStream(ZSTD_DStream* zds) { DEBUGLOG(4, "ZSTD_initDStream"); - return ZSTD_initDStream_usingDict(zds, NULL, 0); + return ZSTD_initDStream_usingDDict(zds, NULL); } /* ZSTD_initDStream_usingDDict() : @@ -1233,9 +1316,9 @@ size_t ZSTD_initDStream(ZSTD_DStream* zds) * this function cannot fail */ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict) { - size_t const initResult = ZSTD_initDStream(dctx); - dctx->ddict = ddict; - return initResult; + FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) ); + FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) ); + return ZSTD_FRAMEHEADERSIZE_PREFIX; } /* ZSTD_resetDStream() : @@ -1243,19 +1326,19 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict) * this function cannot fail */ size_t ZSTD_resetDStream(ZSTD_DStream* dctx) { - DEBUGLOG(4, "ZSTD_resetDStream"); - dctx->streamStage = zdss_loadHeader; - dctx->lhSize = dctx->inPos = dctx->outStart = dctx->outEnd = 0; - dctx->legacyVersion = 0; - dctx->hostageByte = 0; + FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only)); return ZSTD_FRAMEHEADERSIZE_PREFIX; } size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) { - if (dctx->streamStage != zdss_init) return ERROR(stage_wrong); - dctx->ddict = ddict; + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong); + ZSTD_clearDict(dctx); + if (ddict) { + dctx->ddict = ddict; + dctx->dictUses = ZSTD_use_indefinitely; + } return 0; } @@ -1267,9 +1350,9 @@ size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize) ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax); size_t const min = (size_t)1 << bounds.lowerBound; size_t const max = (size_t)1 << bounds.upperBound; - if (dctx->streamStage != zdss_init) return ERROR(stage_wrong); - if (maxWindowSize < min) return ERROR(parameter_outOfBound); - if (maxWindowSize > max) return ERROR(parameter_outOfBound); + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong); + RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound); + RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound); dctx->maxWindowSize = maxWindowSize; return 0; } @@ -1311,15 +1394,15 @@ static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value) } #define CHECK_DBOUNDS(p,v) { \ - if (!ZSTD_dParam_withinBounds(p, v)) \ - return ERROR(parameter_outOfBound); \ + RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound); \ } size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value) { - if (dctx->streamStage != zdss_init) return ERROR(stage_wrong); + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong); switch(dParam) { case ZSTD_d_windowLogMax: + if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT; CHECK_DBOUNDS(ZSTD_d_windowLogMax, value); dctx->maxWindowSize = ((size_t)1) << value; return 0; @@ -1329,19 +1412,20 @@ size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value return 0; default:; } - return ERROR(parameter_unsupported); + RETURN_ERROR(parameter_unsupported); } size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset) { if ( (reset == ZSTD_reset_session_only) || (reset == ZSTD_reset_session_and_parameters) ) { - (void)ZSTD_initDStream(dctx); + dctx->streamStage = zdss_init; + dctx->noForwardProgress = 0; } if ( (reset == ZSTD_reset_parameters) || (reset == ZSTD_reset_session_and_parameters) ) { - if (dctx->streamStage != zdss_init) - return ERROR(stage_wrong); + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong); + ZSTD_clearDict(dctx); dctx->format = ZSTD_f_zstd1; dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT; } @@ -1360,7 +1444,8 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2); unsigned long long const neededSize = MIN(frameContentSize, neededRBSize); size_t const minRBSize = (size_t) neededSize; - if ((unsigned long long)minRBSize != neededSize) return ERROR(frameParameter_windowTooLarge); + RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize, + frameParameter_windowTooLarge); return minRBSize; } @@ -1378,9 +1463,9 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize) ZSTD_frameHeader zfh; size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize); if (ZSTD_isError(err)) return err; - if (err>0) return ERROR(srcSize_wrong); - if (zfh.windowSize > windowSizeMax) - return ERROR(frameParameter_windowTooLarge); + RETURN_ERROR_IF(err>0, srcSize_wrong); + RETURN_ERROR_IF(zfh.windowSize > windowSizeMax, + frameParameter_windowTooLarge); return ZSTD_estimateDStreamSize((size_t)zfh.windowSize); } @@ -1406,16 +1491,16 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB U32 someMoreWork = 1; DEBUGLOG(5, "ZSTD_decompressStream"); - if (input->pos > input->size) { /* forbidden */ - DEBUGLOG(5, "in: pos: %u vs size: %u", - (U32)input->pos, (U32)input->size); - return ERROR(srcSize_wrong); - } - if (output->pos > output->size) { /* forbidden */ - DEBUGLOG(5, "out: pos: %u vs size: %u", - (U32)output->pos, (U32)output->size); - return ERROR(dstSize_tooSmall); - } + RETURN_ERROR_IF( + input->pos > input->size, + srcSize_wrong, + "forbidden. in: pos: %u vs size: %u", + (U32)input->pos, (U32)input->size); + RETURN_ERROR_IF( + output->pos > output->size, + dstSize_tooSmall, + "forbidden. out: pos: %u vs size: %u", + (U32)output->pos, (U32)output->size); DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos)); while (someMoreWork) { @@ -1423,15 +1508,18 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB { case zdss_init : DEBUGLOG(5, "stage zdss_init => transparent reset "); - ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */ + zds->streamStage = zdss_loadHeader; + zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; + zds->legacyVersion = 0; + zds->hostageByte = 0; /* fall-through */ case zdss_loadHeader : DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip)); #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) if (zds->legacyVersion) { - /* legacy support is incompatible with static dctx */ - if (zds->staticSize) return ERROR(memory_allocation); + RETURN_ERROR_IF(zds->staticSize, memory_allocation, + "legacy support is incompatible with static dctx"); { size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input); if (hint==0) zds->streamStage = zdss_init; return hint; @@ -1443,12 +1531,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart); if (legacyVersion) { - const void* const dict = zds->ddict ? ZSTD_DDict_dictContent(zds->ddict) : NULL; - size_t const dictSize = zds->ddict ? ZSTD_DDict_dictSize(zds->ddict) : 0; + ZSTD_DDict const* const ddict = ZSTD_getDDict(zds); + const void* const dict = ddict ? ZSTD_DDict_dictContent(ddict) : NULL; + size_t const dictSize = ddict ? ZSTD_DDict_dictSize(ddict) : 0; DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion); - /* legacy support is incompatible with static dctx */ - if (zds->staticSize) return ERROR(memory_allocation); - CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext, + RETURN_ERROR_IF(zds->staticSize, memory_allocation, + "legacy support is incompatible with static dctx"); + FORWARD_IF_ERROR(ZSTD_initLegacyStream(&zds->legacyContext, zds->previousLegacyVersion, legacyVersion, dict, dictSize)); zds->legacyVersion = zds->previousLegacyVersion = legacyVersion; @@ -1482,7 +1571,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart); if (cSize <= (size_t)(iend-istart)) { /* shortcut : using single-pass mode */ - size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict); + size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, ZSTD_getDDict(zds)); if (ZSTD_isError(decompressedSize)) return decompressedSize; DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()") ip = istart + cSize; @@ -1495,13 +1584,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB /* Consume header (see ZSTDds_decodeFrameHeader) */ DEBUGLOG(4, "Consume header"); - CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict)); + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds))); if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE); zds->stage = ZSTDds_skipFrame; } else { - CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize)); + FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize)); zds->expected = ZSTD_blockHeaderSize; zds->stage = ZSTDds_decodeBlockHeader; } @@ -1511,7 +1600,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB (U32)(zds->fParams.windowSize >>10), (U32)(zds->maxWindowSize >> 10) ); zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN); - if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge); + RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize, + frameParameter_windowTooLarge); /* Adapt buffer sizes to frame header instructions */ { size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */); @@ -1525,14 +1615,15 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB if (zds->staticSize) { /* static DCtx */ DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize); assert(zds->staticSize >= sizeof(ZSTD_DCtx)); /* controlled at init */ - if (bufferSize > zds->staticSize - sizeof(ZSTD_DCtx)) - return ERROR(memory_allocation); + RETURN_ERROR_IF( + bufferSize > zds->staticSize - sizeof(ZSTD_DCtx), + memory_allocation); } else { ZSTD_free(zds->inBuff, zds->customMem); zds->inBuffSize = 0; zds->outBuffSize = 0; zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem); - if (zds->inBuff == NULL) return ERROR(memory_allocation); + RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation); } zds->inBuffSize = neededInBuffSize; zds->outBuff = zds->inBuff + zds->inBuffSize; @@ -1574,7 +1665,9 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB if (isSkipFrame) { loadedSize = MIN(toLoad, (size_t)(iend-ip)); } else { - if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected); /* should never happen */ + RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos, + corruption_detected, + "should never happen"); loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend-ip); } ip += loadedSize; @@ -1615,7 +1708,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB default: assert(0); /* impossible */ - return ERROR(GENERIC); /* some compiler require default to do something */ + RETURN_ERROR(GENERIC); /* some compiler require default to do something */ } } /* result */ @@ -1624,8 +1717,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB if ((ip==istart) && (op==ostart)) { /* no forward progress */ zds->noForwardProgress ++; if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) { - if (op==oend) return ERROR(dstSize_tooSmall); - if (ip==iend) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(op==oend, dstSize_tooSmall); + RETURN_ERROR_IF(ip==iend, srcSize_wrong); assert(0); } } else { diff --git a/lib/decompress/zstd_decompress_block.c b/lib/decompress/zstd_decompress_block.c index 32baad9fbb5c..a2a7eedcf218 100644 --- a/lib/decompress/zstd_decompress_block.c +++ b/lib/decompress/zstd_decompress_block.c @@ -56,14 +56,15 @@ static void ZSTD_copy4(void* dst, const void* src) { memcpy(dst, src, 4); } size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, blockProperties_t* bpPtr) { - if (srcSize < ZSTD_blockHeaderSize) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong); + { U32 const cBlockHeader = MEM_readLE24(src); U32 const cSize = cBlockHeader >> 3; bpPtr->lastBlock = cBlockHeader & 1; bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3); bpPtr->origSize = cSize; /* only useful for RLE */ if (bpPtr->blockType == bt_rle) return 1; - if (bpPtr->blockType == bt_reserved) return ERROR(corruption_detected); + RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected); return cSize; } } @@ -78,7 +79,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, const void* src, size_t srcSize) /* note : srcSize < BLOCKSIZE */ { - if (srcSize < MIN_CBLOCK_SIZE) return ERROR(corruption_detected); + RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected); { const BYTE* const istart = (const BYTE*) src; symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3); @@ -86,11 +87,11 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, switch(litEncType) { case set_repeat: - if (dctx->litEntropy==0) return ERROR(dictionary_corrupted); + RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted); /* fall-through */ case set_compressed: - if (srcSize < 5) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */ + RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3"); { size_t lhSize, litSize, litCSize; U32 singleStream=0; U32 const lhlCode = (istart[0] >> 2) & 3; @@ -118,8 +119,8 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, litCSize = (lhc >> 22) + (istart[4] << 10); break; } - if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected); - if (litCSize + lhSize > srcSize) return ERROR(corruption_detected); + RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected); + RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected); /* prefetch huffman table if cold */ if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) { @@ -157,7 +158,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, } } - if (HUF_isError(hufSuccess)) return ERROR(corruption_detected); + RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected); dctx->litPtr = dctx->litBuffer; dctx->litSize = litSize; @@ -187,7 +188,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, } if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */ - if (litSize+lhSize > srcSize) return ERROR(corruption_detected); + RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected); memcpy(dctx->litBuffer, istart+lhSize, litSize); dctx->litPtr = dctx->litBuffer; dctx->litSize = litSize; @@ -216,17 +217,17 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, case 3: lhSize = 3; litSize = MEM_readLE24(istart) >> 4; - if (srcSize<4) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */ + RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4"); break; } - if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected); + RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected); memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH); dctx->litPtr = dctx->litBuffer; dctx->litSize = litSize; return lhSize+1; } default: - return ERROR(corruption_detected); /* impossible */ + RETURN_ERROR(corruption_detected, "impossible"); } } } @@ -436,8 +437,8 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb switch(type) { case set_rle : - if (!srcSize) return ERROR(srcSize_wrong); - if ( (*(const BYTE*)src) > max) return ERROR(corruption_detected); + RETURN_ERROR_IF(!srcSize, srcSize_wrong); + RETURN_ERROR_IF((*(const BYTE*)src) > max, corruption_detected); { U32 const symbol = *(const BYTE*)src; U32 const baseline = baseValue[symbol]; U32 const nbBits = nbAdditionalBits[symbol]; @@ -449,7 +450,7 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb *DTablePtr = defaultTable; return 0; case set_repeat: - if (!flagRepeatTable) return ERROR(corruption_detected); + RETURN_ERROR_IF(!flagRepeatTable, corruption_detected); /* prefetch FSE table if used */ if (ddictIsCold && (nbSeq > 24 /* heuristic */)) { const void* const pStart = *DTablePtr; @@ -461,15 +462,15 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb { unsigned tableLog; S16 norm[MaxSeq+1]; size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize); - if (FSE_isError(headerSize)) return ERROR(corruption_detected); - if (tableLog > maxLog) return ERROR(corruption_detected); + RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected); + RETURN_ERROR_IF(tableLog > maxLog, corruption_detected); ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog); *DTablePtr = DTableSpace; return headerSize; } - default : /* impossible */ + default : assert(0); - return ERROR(GENERIC); + RETURN_ERROR(GENERIC, "impossible"); } } @@ -483,28 +484,28 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, DEBUGLOG(5, "ZSTD_decodeSeqHeaders"); /* check */ - if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong); /* SeqHead */ nbSeq = *ip++; if (!nbSeq) { *nbSeqPtr=0; - if (srcSize != 1) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize != 1, srcSize_wrong); return 1; } if (nbSeq > 0x7F) { if (nbSeq == 0xFF) { - if (ip+2 > iend) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong); nbSeq = MEM_readLE16(ip) + LONGNBSEQ, ip+=2; } else { - if (ip >= iend) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(ip >= iend, srcSize_wrong); nbSeq = ((nbSeq-0x80)<<8) + *ip++; } } *nbSeqPtr = nbSeq; /* FSE table descriptors */ - if (ip+4 > iend) return ERROR(srcSize_wrong); /* minimum possible size */ + RETURN_ERROR_IF(ip+4 > iend, srcSize_wrong); /* minimum possible size */ { symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6); symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3); symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3); @@ -517,7 +518,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, LL_base, LL_bits, LL_defaultDTable, dctx->fseEntropy, dctx->ddictIsCold, nbSeq); - if (ZSTD_isError(llhSize)) return ERROR(corruption_detected); + RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected); ip += llhSize; } @@ -527,7 +528,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, OF_base, OF_bits, OF_defaultDTable, dctx->fseEntropy, dctx->ddictIsCold, nbSeq); - if (ZSTD_isError(ofhSize)) return ERROR(corruption_detected); + RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected); ip += ofhSize; } @@ -537,7 +538,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, ML_base, ML_bits, ML_defaultDTable, dctx->fseEntropy, dctx->ddictIsCold, nbSeq); - if (ZSTD_isError(mlhSize)) return ERROR(corruption_detected); + RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected); ip += mlhSize; } } @@ -590,8 +591,8 @@ size_t ZSTD_execSequenceLast7(BYTE* op, const BYTE* match = oLitEnd - sequence.offset; /* check */ - if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must fit within dstBuffer */ - if (iLitEnd > litLimit) return ERROR(corruption_detected); /* try to read beyond literal buffer */ + RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must fit within dstBuffer"); + RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "try to read beyond literal buffer"); /* copy literals */ while (op < oLitEnd) *op++ = *(*litPtr)++; @@ -599,7 +600,7 @@ size_t ZSTD_execSequenceLast7(BYTE* op, /* copy Match */ if (sequence.offset > (size_t)(oLitEnd - base)) { /* offset beyond prefix */ - if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected); + RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - vBase),corruption_detected); match = dictEnd - (base-match); if (match + sequence.matchLength <= dictEnd) { memmove(oLitEnd, match, sequence.matchLength); @@ -631,8 +632,8 @@ size_t ZSTD_execSequence(BYTE* op, const BYTE* match = oLitEnd - sequence.offset; /* check */ - if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */ - if (iLitEnd > litLimit) return ERROR(corruption_detected); /* over-read beyond lit buffer */ + RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend"); + RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer"); if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd); /* copy Literals */ @@ -645,8 +646,7 @@ size_t ZSTD_execSequence(BYTE* op, /* copy Match */ if (sequence.offset > (size_t)(oLitEnd - prefixStart)) { /* offset beyond prefix -> go into extDict */ - if (sequence.offset > (size_t)(oLitEnd - virtualStart)) - return ERROR(corruption_detected); + RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected); match = dictEnd + (match - prefixStart); if (match + sequence.matchLength <= dictEnd) { memmove(oLitEnd, match, sequence.matchLength); @@ -712,8 +712,8 @@ size_t ZSTD_execSequenceLong(BYTE* op, const BYTE* match = sequence.match; /* check */ - if (oMatchEnd > oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */ - if (iLitEnd > litLimit) return ERROR(corruption_detected); /* over-read beyond lit buffer */ + RETURN_ERROR_IF(oMatchEnd > oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend"); + RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer"); if (oLitEnd > oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, dictStart, dictEnd); /* copy Literals */ @@ -726,7 +726,7 @@ size_t ZSTD_execSequenceLong(BYTE* op, /* copy Match */ if (sequence.offset > (size_t)(oLitEnd - prefixStart)) { /* offset beyond prefix */ - if (sequence.offset > (size_t)(oLitEnd - dictStart)) return ERROR(corruption_detected); + RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - dictStart), corruption_detected); if (match + sequence.matchLength <= dictEnd) { memmove(oLitEnd, match, sequence.matchLength); return sequenceLength; @@ -801,7 +801,7 @@ ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD) /* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum * offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1) * bits before reloading. This value is the maximum number of bytes we read - * after reloading when we are decoding long offets. + * after reloading when we are decoding long offsets. */ #define LONG_OFFSETS_MAX_EXTRA_BITS_32 \ (ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32 \ @@ -911,7 +911,9 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx, seqState_t seqState; dctx->fseEntropy = 1; { U32 i; for (i=0; i entropy.rep[i]; } - CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected); + RETURN_ERROR_IF( + ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)), + corruption_detected); ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); @@ -927,14 +929,14 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx, /* check if reached exact end */ DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq); - if (nbSeq) return ERROR(corruption_detected); + RETURN_ERROR_IF(nbSeq, corruption_detected); /* save reps for next block */ { U32 i; for (i=0; i entropy.rep[i] = (U32)(seqState.prevOffset[i]); } } /* last literal segment */ { size_t const lastLLSize = litEnd - litPtr; - if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall); memcpy(op, litPtr, lastLLSize); op += lastLLSize; } @@ -1066,7 +1068,9 @@ ZSTD_decompressSequencesLong_body( seqState.pos = (size_t)(op-prefixStart); seqState.dictEnd = dictEnd; assert(iend >= ip); - CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected); + RETURN_ERROR_IF( + ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)), + corruption_detected); ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); @@ -1076,7 +1080,7 @@ ZSTD_decompressSequencesLong_body( sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, isLongOffset); PREFETCH_L1(sequences[seqNb].match); PREFETCH_L1(sequences[seqNb].match + sequences[seqNb].matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */ } - if (seqNb (size_t)(oend-op)) return ERROR(dstSize_tooSmall); + RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall); memcpy(op, litPtr, lastLLSize); op += lastLLSize; } @@ -1176,7 +1180,7 @@ ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize, /* ZSTD_decompressSequencesLong() : * decompression function triggered when a minimum share of offsets is considered "long", * aka out of cache. - * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes mearning "farther than memory cache distance". + * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance". * This function will try to mitigate main memory latency through the use of prefetching */ static size_t ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx, @@ -1240,7 +1244,7 @@ ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx, ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN)))); DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize); - if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong); + RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong); /* Decode literals section */ { size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize); diff --git a/lib/decompress/zstd_decompress_internal.h b/lib/decompress/zstd_decompress_internal.h index abd0030519d2..ccbdfa090faa 100644 --- a/lib/decompress/zstd_decompress_internal.h +++ b/lib/decompress/zstd_decompress_internal.h @@ -89,6 +89,12 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader, typedef enum { zdss_init=0, zdss_loadHeader, zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage; +typedef enum { + ZSTD_use_indefinitely = -1, /* Use the dictionary indefinitely */ + ZSTD_dont_use = 0, /* Do not use the dictionary (if one exists free it) */ + ZSTD_use_once = 1 /* Use the dictionary once and set to ZSTD_dont_use */ +} ZSTD_dictUses_e; + struct ZSTD_DCtx_s { const ZSTD_seqSymbol* LLTptr; @@ -123,6 +129,7 @@ struct ZSTD_DCtx_s const ZSTD_DDict* ddict; /* set by ZSTD_initDStream_usingDDict(), or ZSTD_DCtx_refDDict() */ U32 dictID; int ddictIsCold; /* if == 1 : dictionary is "new" for working context, and presumed "cold" (not in cpu cache) */ + ZSTD_dictUses_e dictUses; /* streaming */ ZSTD_dStreamStage streamStage; diff --git a/lib/dictBuilder/cover.c b/lib/dictBuilder/cover.c index b55bfb510b72..21464ad0310e 100644 --- a/lib/dictBuilder/cover.c +++ b/lib/dictBuilder/cover.c @@ -391,7 +391,7 @@ static void COVER_group(COVER_ctx_t *ctx, const void *group, * * Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1}) * - * Once the dmer d is in the dictionay we set F(d) = 0. + * Once the dmer d is in the dictionary we set F(d) = 0. */ static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs, COVER_map_t *activeDmers, U32 begin, @@ -435,7 +435,7 @@ static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs, U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer); activeSegment.begin += 1; *delDmerOcc -= 1; - /* If this is the last occurence of the dmer, subtract its score */ + /* If this is the last occurrence of the dmer, subtract its score */ if (*delDmerOcc == 0) { COVER_map_remove(activeDmers, delDmer); activeSegment.score -= freqs[delDmer]; @@ -627,6 +627,39 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer, return 1; } +void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel) +{ + const double ratio = (double)nbDmers / maxDictSize; + if (ratio >= 10) { + return; + } + LOCALDISPLAYLEVEL(displayLevel, 1, + "WARNING: The maximum dictionary size %u is too large " + "compared to the source size %u! " + "size(source)/size(dictionary) = %f, but it should be >= " + "10! This may lead to a subpar dictionary! We recommend " + "training on sources at least 10x, and up to 100x the " + "size of the dictionary!\n", (U32)maxDictSize, + (U32)nbDmers, ratio); +} + +COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, + U32 nbDmers, U32 k, U32 passes) +{ + const U32 minEpochSize = k * 10; + COVER_epoch_info_t epochs; + epochs.num = MAX(1, maxDictSize / k / passes); + epochs.size = nbDmers / epochs.num; + if (epochs.size >= minEpochSize) { + assert(epochs.size * epochs.num <= nbDmers); + return epochs; + } + epochs.size = MIN(minEpochSize, nbDmers); + epochs.num = nbDmers / epochs.size; + assert(epochs.size * epochs.num <= nbDmers); + return epochs; +} + /** * Given the prepared context build the dictionary. */ @@ -636,28 +669,34 @@ static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs, ZDICT_cover_params_t parameters) { BYTE *const dict = (BYTE *)dictBuffer; size_t tail = dictBufferCapacity; - /* Divide the data up into epochs of equal size. - * We will select at least one segment from each epoch. - */ - const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k / 4)); - const unsigned epochSize = (U32)(ctx->suffixSize / epochs); + /* Divide the data into epochs. We will select one segment from each epoch. */ + const COVER_epoch_info_t epochs = COVER_computeEpochs( + (U32)dictBufferCapacity, (U32)ctx->suffixSize, parameters.k, 4); + const size_t maxZeroScoreRun = MAX(10, MIN(100, epochs.num >> 3)); + size_t zeroScoreRun = 0; size_t epoch; DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n", - epochs, epochSize); + (U32)epochs.num, (U32)epochs.size); /* Loop through the epochs until there are no more segments or the dictionary * is full. */ - for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) { - const U32 epochBegin = (U32)(epoch * epochSize); - const U32 epochEnd = epochBegin + epochSize; + for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) { + const U32 epochBegin = (U32)(epoch * epochs.size); + const U32 epochEnd = epochBegin + epochs.size; size_t segmentSize; /* Select a segment */ COVER_segment_t segment = COVER_selectSegment( ctx, freqs, activeDmers, epochBegin, epochEnd, parameters); - /* If the segment covers no dmers, then we are out of content */ + /* If the segment covers no dmers, then we are out of content. + * There may be new content in other epochs, for continue for some time. + */ if (segment.score == 0) { - break; + if (++zeroScoreRun >= maxZeroScoreRun) { + break; + } + continue; } + zeroScoreRun = 0; /* Trim the segment if necessary and if it is too small then we are done */ segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail); if (segmentSize < parameters.d) { @@ -706,6 +745,7 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( parameters.d, parameters.splitPoint)) { return ERROR(GENERIC); } + COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, g_displayLevel); if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); COVER_ctx_destroy(&ctx); @@ -977,6 +1017,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( unsigned k; COVER_best_t best; POOL_ctx *pool = NULL; + int warned = 0; /* Checks */ if (splitPoint <= 0 || splitPoint > 1) { @@ -1019,6 +1060,10 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( POOL_free(pool); return ERROR(GENERIC); } + if (!warned) { + COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, displayLevel); + warned = 1; + } /* Loop through k reusing the same context */ for (k = kMinK; k <= kMaxK; k += kStepSize) { /* Prepare the arguments */ diff --git a/lib/dictBuilder/cover.h b/lib/dictBuilder/cover.h index 82e2e1cea43c..efb46807c785 100644 --- a/lib/dictBuilder/cover.h +++ b/lib/dictBuilder/cover.h @@ -38,6 +38,35 @@ typedef struct { U32 score; } COVER_segment_t; +/** + *Number of epochs and size of each epoch. + */ +typedef struct { + U32 num; + U32 size; +} COVER_epoch_info_t; + +/** + * Computes the number of epochs and the size of each epoch. + * We will make sure that each epoch gets at least 10 * k bytes. + * + * The COVER algorithms divide the data up into epochs of equal size and + * select one segment from each epoch. + * + * @param maxDictSize The maximum allowed dictionary size. + * @param nbDmers The number of dmers we are training on. + * @param k The parameter k (segment size). + * @param passes The target number of passes over the dmer corpus. + * More passes means a better dictionary. + */ +COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, U32 nbDmers, + U32 k, U32 passes); + +/** + * Warns the user when their corpus is too small. + */ +void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel); + /** * Checks total compressed size of a dictionary */ diff --git a/lib/dictBuilder/fastcover.c b/lib/dictBuilder/fastcover.c index c289c0690145..5b6b941a9082 100644 --- a/lib/dictBuilder/fastcover.c +++ b/lib/dictBuilder/fastcover.c @@ -132,7 +132,7 @@ typedef struct { * * Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1}) * - * Once the dmer with hash value d is in the dictionay we set F(d) = 0. + * Once the dmer with hash value d is in the dictionary we set F(d) = 0. */ static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx, U32 *freqs, U32 begin, U32 end, @@ -161,7 +161,7 @@ static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx, /* Get hash value of current dmer */ const size_t idx = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, f, d); - /* Add frequency of this index to score if this is the first occurence of index in active segment */ + /* Add frequency of this index to score if this is the first occurrence of index in active segment */ if (segmentFreqs[idx] == 0) { activeSegment.score += freqs[idx]; } @@ -386,29 +386,35 @@ FASTCOVER_buildDictionary(const FASTCOVER_ctx_t* ctx, { BYTE *const dict = (BYTE *)dictBuffer; size_t tail = dictBufferCapacity; - /* Divide the data up into epochs of equal size. - * We will select at least one segment from each epoch. - */ - const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k)); - const unsigned epochSize = (U32)(ctx->nbDmers / epochs); + /* Divide the data into epochs. We will select one segment from each epoch. */ + const COVER_epoch_info_t epochs = COVER_computeEpochs( + (U32)dictBufferCapacity, (U32)ctx->nbDmers, parameters.k, 1); + const size_t maxZeroScoreRun = 10; + size_t zeroScoreRun = 0; size_t epoch; DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n", - epochs, epochSize); + (U32)epochs.num, (U32)epochs.size); /* Loop through the epochs until there are no more segments or the dictionary * is full. */ - for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) { - const U32 epochBegin = (U32)(epoch * epochSize); - const U32 epochEnd = epochBegin + epochSize; + for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) { + const U32 epochBegin = (U32)(epoch * epochs.size); + const U32 epochEnd = epochBegin + epochs.size; size_t segmentSize; /* Select a segment */ COVER_segment_t segment = FASTCOVER_selectSegment( ctx, freqs, epochBegin, epochEnd, parameters, segmentFreqs); - /* If the segment covers no dmers, then we are out of content */ + /* If the segment covers no dmers, then we are out of content. + * There may be new content in other epochs, for continue for some time. + */ if (segment.score == 0) { - break; + if (++zeroScoreRun >= maxZeroScoreRun) { + break; + } + continue; } + zeroScoreRun = 0; /* Trim the segment if necessary and if it is too small then we are done */ segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail); @@ -564,6 +570,7 @@ ZDICT_trainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity, DISPLAYLEVEL(1, "Failed to initialize context\n"); return ERROR(GENERIC); } + COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, g_displayLevel); /* Build the dictionary */ DISPLAYLEVEL(2, "Building dictionary\n"); { @@ -616,6 +623,7 @@ ZDICT_optimizeTrainFromBuffer_fastCover( unsigned k; COVER_best_t best; POOL_ctx *pool = NULL; + int warned = 0; /* Checks */ if (splitPoint <= 0 || splitPoint > 1) { LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect splitPoint\n"); @@ -664,6 +672,10 @@ ZDICT_optimizeTrainFromBuffer_fastCover( POOL_free(pool); return ERROR(GENERIC); } + if (!warned) { + COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, displayLevel); + warned = 1; + } /* Loop through k reusing the same context */ for (k = kMinK; k <= kMaxK; k += kStepSize) { /* Prepare the arguments */ diff --git a/lib/dictBuilder/zdict.h b/lib/dictBuilder/zdict.h index d57d59f01e72..e22973173cb8 100644 --- a/lib/dictBuilder/zdict.h +++ b/lib/dictBuilder/zdict.h @@ -46,7 +46,12 @@ extern "C" { * The resulting dictionary will be saved into `dictBuffer`. * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) * or an error code, which can be tested with ZDICT_isError(). - * Note: ZDICT_trainFromBuffer() requires about 9 bytes of memory for each input byte. + * Note: Dictionary training will fail if there are not enough samples to construct a + * dictionary, or if most of the samples are too small (< 8 bytes being the lower limit). + * If dictionary training fails, you should use zstd without a dictionary, as the dictionary + * would've been ineffective anyways. If you believe your samples would benefit from a dictionary + * please open an issue with details, and we can look into it. + * Note: ZDICT_trainFromBuffer()'s memory usage is about 6 MB. * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. * In general, it's recommended to provide a few thousands samples, though this can vary a lot. @@ -110,6 +115,7 @@ typedef struct { * The resulting dictionary will be saved into `dictBuffer`. * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) * or an error code, which can be tested with ZDICT_isError(). + * See ZDICT_trainFromBuffer() for details on failure modes. * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte. * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. @@ -133,8 +139,9 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000]. * * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - * or an error code, which can be tested with ZDICT_isError(). - * On success `*parameters` contains the parameters selected. + * or an error code, which can be tested with ZDICT_isError(). + * On success `*parameters` contains the parameters selected. + * See ZDICT_trainFromBuffer() for details on failure modes. * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. */ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( @@ -151,7 +158,8 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( * The resulting dictionary will be saved into `dictBuffer`. * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) * or an error code, which can be tested with ZDICT_isError(). - * Note: ZDICT_trainFromBuffer_fastCover() requires about 1 bytes of memory for each input byte and additionally another 6 * 2^f bytes of memory . + * See ZDICT_trainFromBuffer() for details on failure modes. + * Note: ZDICT_trainFromBuffer_fastCover() requires 6 * 2^f bytes of memory. * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. * In general, it's recommended to provide a few thousands samples, though this can vary a lot. @@ -175,9 +183,10 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_fastCover(void *dictBuffer, * If accel is zero, default value of 1 is used. * * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - * or an error code, which can be tested with ZDICT_isError(). - * On success `*parameters` contains the parameters selected. - * Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 1 byte of memory for each input byte and additionally another 6 * 2^f bytes of memory for each thread. + * or an error code, which can be tested with ZDICT_isError(). + * On success `*parameters` contains the parameters selected. + * See ZDICT_trainFromBuffer() for details on failure modes. + * Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 6 * 2^f bytes of memory for each thread. */ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity, const void* samplesBuffer, @@ -195,7 +204,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer, * maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes. * * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`), - * or an error code, which can be tested by ZDICT_isError(). + * or an error code, which can be tested by ZDICT_isError(). * Note: ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0. * Note 2: dictBuffer and dictContent can overlap */ @@ -219,6 +228,7 @@ typedef struct { * `parameters` is optional and can be provided with values set to 0 to mean "default". * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) * or an error code, which can be tested with ZDICT_isError(). + * See ZDICT_trainFromBuffer() for details on failure modes. * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. * In general, it's recommended to provide a few thousands samples, though this can vary a lot. diff --git a/lib/legacy/zstd_legacy.h b/lib/legacy/zstd_legacy.h index 5893cb9657e6..e5b383ee4c0c 100644 --- a/lib/legacy/zstd_legacy.h +++ b/lib/legacy/zstd_legacy.h @@ -20,7 +20,7 @@ extern "C" { ***************************************/ #include "mem.h" /* MEM_STATIC */ #include "error_private.h" /* ERROR */ -#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer */ +#include "zstd_internal.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTD_frameSizeInfo */ #if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0) # undef ZSTD_LEGACY_SUPPORT @@ -178,43 +178,73 @@ MEM_STATIC size_t ZSTD_decompressLegacy( } } -MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, - size_t compressedSize) +MEM_STATIC ZSTD_frameSizeInfo ZSTD_findFrameSizeInfoLegacy(const void *src, size_t srcSize) { - U32 const version = ZSTD_isLegacy(src, compressedSize); + ZSTD_frameSizeInfo frameSizeInfo; + U32 const version = ZSTD_isLegacy(src, srcSize); switch(version) { #if (ZSTD_LEGACY_SUPPORT <= 1) case 1 : - return ZSTDv01_findFrameCompressedSize(src, compressedSize); + ZSTDv01_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 2) case 2 : - return ZSTDv02_findFrameCompressedSize(src, compressedSize); + ZSTDv02_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 3) case 3 : - return ZSTDv03_findFrameCompressedSize(src, compressedSize); + ZSTDv03_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 4) case 4 : - return ZSTDv04_findFrameCompressedSize(src, compressedSize); + ZSTDv04_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 5) case 5 : - return ZSTDv05_findFrameCompressedSize(src, compressedSize); + ZSTDv05_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 6) case 6 : - return ZSTDv06_findFrameCompressedSize(src, compressedSize); + ZSTDv06_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif #if (ZSTD_LEGACY_SUPPORT <= 7) case 7 : - return ZSTDv07_findFrameCompressedSize(src, compressedSize); + ZSTDv07_findFrameSizeInfoLegacy(src, srcSize, + &frameSizeInfo.compressedSize, + &frameSizeInfo.decompressedBound); + break; #endif default : - return ERROR(prefix_unknown); + frameSizeInfo.compressedSize = ERROR(prefix_unknown); + frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR; + break; } + return frameSizeInfo; +} + +MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, size_t srcSize) +{ + ZSTD_frameSizeInfo frameSizeInfo = ZSTD_findFrameSizeInfoLegacy(src, srcSize); + return frameSizeInfo.compressedSize; } MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version) diff --git a/lib/legacy/zstd_v01.c b/lib/legacy/zstd_v01.c index c007e7ceb518..cad2b99b4a73 100644 --- a/lib/legacy/zstd_v01.c +++ b/lib/legacy/zstd_v01.c @@ -1336,6 +1336,8 @@ static const U32 ZSTD_magicNumber = 0xFD2FB51E; /* 3rd version : seqNb header #define LITERAL_NOENTROPY 63 #define COMMAND_NOENTROPY 7 /* to remove */ +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + static const size_t ZSTD_blockHeaderSize = 3; static const size_t ZSTD_frameHeaderSize = 4; @@ -1757,7 +1759,7 @@ static size_t ZSTD_execSequence(BYTE* op, BYTE* const base, BYTE* const oend) { static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */ - static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */ + static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */ const BYTE* const ostart = op; const size_t litLength = sequence.litLength; BYTE* const endMatch = op + litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */ @@ -1999,36 +2001,59 @@ size_t ZSTDv01_decompress(void* dst, size_t maxDstSize, const void* src, size_t return ZSTDv01_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize); } -size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; U32 magicNumber; blockProperties_t blockProperties; /* Frame Header */ - if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong); + if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } magicNumber = ZSTD_readBE32(src); - if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown); + if (magicNumber != ZSTD_magicNumber) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; /* Loop on each block */ while (1) { size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTDv01_isError(blockSize)) return blockSize; + if (ZSTDv01_isError(blockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, blockSize); + return; + } ip += ZSTD_blockHeaderSize; remainingSize -= ZSTD_blockHeaderSize; - if (blockSize > remainingSize) return ERROR(srcSize_wrong); + if (blockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (blockSize == 0) break; /* bt_end */ ip += blockSize; remainingSize -= blockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * BLOCKSIZE; } /******************************* diff --git a/lib/legacy/zstd_v01.h b/lib/legacy/zstd_v01.h index 42f0897c7d23..245f9dd31468 100644 --- a/lib/legacy/zstd_v01.h +++ b/lib/legacy/zstd_v01.h @@ -35,13 +35,18 @@ ZSTDv01_decompress() : decompress ZSTD frames compliant with v0.1.x format size_t ZSTDv01_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize); -/** -ZSTDv01_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.1.x format - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv01_isError()) -*/ -size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t compressedSize); + /** + ZSTDv01_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.1.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. + */ +void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /** ZSTDv01_isError() : tells if the result of ZSTDv01_decompress() is an error diff --git a/lib/legacy/zstd_v02.c b/lib/legacy/zstd_v02.c index c09ef8cff23e..561bc412e9a8 100644 --- a/lib/legacy/zstd_v02.c +++ b/lib/legacy/zstd_v02.c @@ -2728,6 +2728,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_ #define LITERAL_NOENTROPY 63 #define COMMAND_NOENTROPY 7 /* to remove */ +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + static const size_t ZSTD_blockHeaderSize = 3; static const size_t ZSTD_frameHeaderSize = 4; @@ -3096,7 +3098,7 @@ static size_t ZSTD_execSequence(BYTE* op, BYTE* const base, BYTE* const oend) { static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */ - static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */ + static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */ const BYTE* const ostart = op; BYTE* const oLitEnd = op + sequence.litLength; BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */ @@ -3312,37 +3314,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize); } -static size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) { + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} +void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) +{ const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; U32 magicNumber; blockProperties_t blockProperties; /* Frame Header */ - if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong); + if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } magicNumber = MEM_readLE32(src); - if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown); + if (magicNumber != ZSTD_magicNumber) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; /* Loop on each block */ while (1) { size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) return cBlockSize; + if (ZSTD_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTD_blockHeaderSize; remainingSize -= ZSTD_blockHeaderSize; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (cBlockSize == 0) break; /* bt_end */ ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * BLOCKSIZE; } /******************************* @@ -3458,11 +3482,6 @@ size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize, return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); } -size_t ZSTDv02_findFrameCompressedSize(const void *src, size_t compressedSize) -{ - return ZSTD_findFrameCompressedSize(src, compressedSize); -} - ZSTDv02_Dctx* ZSTDv02_createDCtx(void) { return (ZSTDv02_Dctx*)ZSTD_createDCtx(); diff --git a/lib/legacy/zstd_v02.h b/lib/legacy/zstd_v02.h index 0dde7a63773c..9d7d8d9b5bc4 100644 --- a/lib/legacy/zstd_v02.h +++ b/lib/legacy/zstd_v02.h @@ -35,13 +35,18 @@ ZSTDv02_decompress() : decompress ZSTD frames compliant with v0.2.x format size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize); -/** -ZSTDv02_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.2.x format - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv02_isError()) -*/ -size_t ZSTDv02_findFrameCompressedSize(const void* src, size_t compressedSize); + /** + ZSTDv02_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.2.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. + */ +void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /** ZSTDv02_isError() : tells if the result of ZSTDv02_decompress() is an error diff --git a/lib/legacy/zstd_v03.c b/lib/legacy/zstd_v03.c index 0c4cdf6888a7..a1bf0fa9b5c8 100644 --- a/lib/legacy/zstd_v03.c +++ b/lib/legacy/zstd_v03.c @@ -2369,6 +2369,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_ #define LITERAL_NOENTROPY 63 #define COMMAND_NOENTROPY 7 /* to remove */ +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + static const size_t ZSTD_blockHeaderSize = 3; static const size_t ZSTD_frameHeaderSize = 4; @@ -2737,7 +2739,7 @@ static size_t ZSTD_execSequence(BYTE* op, BYTE* const base, BYTE* const oend) { static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */ - static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* substracted */ + static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11}; /* subtracted */ const BYTE* const ostart = op; BYTE* const oLitEnd = op + sequence.litLength; BYTE* const oMatchEnd = op + sequence.litLength + sequence.matchLength; /* risk : address space overflow (32-bits) */ @@ -2953,36 +2955,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize); } -static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +MEM_STATIC void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; U32 magicNumber; blockProperties_t blockProperties; /* Frame Header */ - if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong); + if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } magicNumber = MEM_readLE32(src); - if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown); + if (magicNumber != ZSTD_magicNumber) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; /* Loop on each block */ while (1) { size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) return cBlockSize; + if (ZSTD_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTD_blockHeaderSize; remainingSize -= ZSTD_blockHeaderSize; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (cBlockSize == 0) break; /* bt_end */ ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * BLOCKSIZE; } @@ -3099,11 +3124,6 @@ size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize, return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); } -size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t srcSize) -{ - return ZSTD_findFrameCompressedSize(src, srcSize); -} - ZSTDv03_Dctx* ZSTDv03_createDCtx(void) { return (ZSTDv03_Dctx*)ZSTD_createDCtx(); diff --git a/lib/legacy/zstd_v03.h b/lib/legacy/zstd_v03.h index b4449e2999e0..efd8c2b9241a 100644 --- a/lib/legacy/zstd_v03.h +++ b/lib/legacy/zstd_v03.h @@ -35,13 +35,18 @@ ZSTDv03_decompress() : decompress ZSTD frames compliant with v0.3.x format size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize); -/** -ZSTDv03_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.3.x format - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv03_isError()) -*/ -size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t compressedSize); + /** + ZSTDv03_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.3.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. + */ + void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /** ZSTDv03_isError() : tells if the result of ZSTDv03_decompress() is an error diff --git a/lib/legacy/zstd_v04.c b/lib/legacy/zstd_v04.c index d7522025e7f0..4342330e2553 100644 --- a/lib/legacy/zstd_v04.c +++ b/lib/legacy/zstd_v04.c @@ -373,6 +373,8 @@ static const size_t ZSTD_frameHeaderSize_min = 5; #define MIN_SEQUENCES_SIZE (2 /*seqNb*/ + 2 /*dumps*/ + 3 /*seqTables*/ + 1 /*bitStream*/) #define MIN_CBLOCK_SIZE (3 /*litCSize*/ + MIN_SEQUENCES_SIZE) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t; @@ -2860,7 +2862,7 @@ static size_t ZSTD_execSequence(BYTE* op, const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd) { static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */ - static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */ + static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */ BYTE* const oLitEnd = op + sequence.litLength; const size_t sequenceLength = sequence.litLength + sequence.matchLength; BYTE* const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ @@ -3119,34 +3121,57 @@ static size_t ZSTD_decompress_usingDict(ZSTD_DCtx* ctx, return op-ostart; } -static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; blockProperties_t blockProperties; /* Frame Header */ - if (srcSize < ZSTD_frameHeaderSize_min) return ERROR(srcSize_wrong); - if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) return ERROR(prefix_unknown); + if (srcSize < ZSTD_frameHeaderSize_min) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } + if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } ip += ZSTD_frameHeaderSize_min; remainingSize -= ZSTD_frameHeaderSize_min; /* Loop on each block */ while (1) { size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) return cBlockSize; + if (ZSTD_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTD_blockHeaderSize; remainingSize -= ZSTD_blockHeaderSize; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (cBlockSize == 0) break; /* bt_end */ ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * BLOCKSIZE; } /* ****************************** @@ -3578,11 +3603,6 @@ size_t ZSTDv04_decompress(void* dst, size_t maxDstSize, const void* src, size_t #endif } -size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t srcSize) -{ - return ZSTD_findFrameCompressedSize(src, srcSize); -} - size_t ZSTDv04_resetDCtx(ZSTDv04_Dctx* dctx) { return ZSTD_resetDCtx(dctx); } size_t ZSTDv04_nextSrcSizeToDecompress(ZSTDv04_Dctx* dctx) diff --git a/lib/legacy/zstd_v04.h b/lib/legacy/zstd_v04.h index 6391631fc432..bb5f3b7d0b86 100644 --- a/lib/legacy/zstd_v04.h +++ b/lib/legacy/zstd_v04.h @@ -35,13 +35,18 @@ ZSTDv04_decompress() : decompress ZSTD frames compliant with v0.4.x format size_t ZSTDv04_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize); -/** -ZSTDv04_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.4.x format - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv04_isError()) -*/ -size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t compressedSize); + /** + ZSTDv04_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.4.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. + */ + void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /** ZSTDv04_isError() : tells if the result of ZSTDv04_decompress() is an error diff --git a/lib/legacy/zstd_v05.c b/lib/legacy/zstd_v05.c index 96bffc44a1a4..caaf15f9bdb1 100644 --- a/lib/legacy/zstd_v05.c +++ b/lib/legacy/zstd_v05.c @@ -491,6 +491,8 @@ static const size_t ZSTDv05_frameHeaderSize_min = 5; #define WILDCOPY_OVERLENGTH 8 +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t; @@ -3217,7 +3219,7 @@ static size_t ZSTDv05_execSequence(BYTE* op, const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd) { static const int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */ - static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */ + static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */ BYTE* const oLitEnd = op + sequence.litLength; const size_t sequenceLength = sequence.litLength + sequence.matchLength; BYTE* const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ @@ -3508,34 +3510,57 @@ size_t ZSTDv05_decompress(void* dst, size_t maxDstSize, const void* src, size_t #endif } -size_t ZSTDv05_findFrameCompressedSize(const void *src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; blockProperties_t blockProperties; /* Frame Header */ - if (srcSize < ZSTDv05_frameHeaderSize_min) return ERROR(srcSize_wrong); - if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) return ERROR(prefix_unknown); + if (srcSize < ZSTDv05_frameHeaderSize_min) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } + if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } ip += ZSTDv05_frameHeaderSize_min; remainingSize -= ZSTDv05_frameHeaderSize_min; /* Loop on each block */ while (1) { size_t cBlockSize = ZSTDv05_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTDv05_isError(cBlockSize)) return cBlockSize; + if (ZSTDv05_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTDv05_blockHeaderSize; remainingSize -= ZSTDv05_blockHeaderSize; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (cBlockSize == 0) break; /* bt_end */ ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * BLOCKSIZE; } /* ****************************** diff --git a/lib/legacy/zstd_v05.h b/lib/legacy/zstd_v05.h index b68fd578ee9f..4a979854b36e 100644 --- a/lib/legacy/zstd_v05.h +++ b/lib/legacy/zstd_v05.h @@ -33,13 +33,18 @@ extern "C" { size_t ZSTDv05_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); -/** -ZSTDv05_getFrameSrcSize() : get the source length of a ZSTD frame - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv05_isError()) -*/ -size_t ZSTDv05_findFrameCompressedSize(const void* src, size_t compressedSize); + /** + ZSTDv05_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.5.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. + */ +void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /* ************************************* * Helper functions diff --git a/lib/legacy/zstd_v06.c b/lib/legacy/zstd_v06.c index 60d8d6fd9a9b..a695cbb8a6dd 100644 --- a/lib/legacy/zstd_v06.c +++ b/lib/legacy/zstd_v06.c @@ -506,6 +506,8 @@ typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t; #define FSEv06_ENCODING_STATIC 2 #define FSEv06_ENCODING_DYNAMIC 3 +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12, 13,14,15,16 }; @@ -3406,7 +3408,7 @@ static size_t ZSTDv06_execSequence(BYTE* op, if (sequence.offset < 8) { /* close range match, overlap */ static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */ - static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */ + static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */ int const sub2 = dec64table[sequence.offset]; op[0] = match[0]; op[1] = match[1]; @@ -3654,36 +3656,62 @@ size_t ZSTDv06_decompress(void* dst, size_t dstCapacity, const void* src, size_t #endif } -size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; blockProperties_t blockProperties = { bt_compressed, 0 }; /* Frame Header */ { size_t const frameHeaderSize = ZSTDv06_frameHeaderSize(src, ZSTDv06_frameHeaderSize_min); - if (ZSTDv06_isError(frameHeaderSize)) return frameHeaderSize; - if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) return ERROR(prefix_unknown); - if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) return ERROR(srcSize_wrong); + if (ZSTDv06_isError(frameHeaderSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize); + return; + } + if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } + if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } ip += frameHeaderSize; remainingSize -= frameHeaderSize; } /* Loop on each block */ while (1) { size_t const cBlockSize = ZSTDv06_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTDv06_isError(cBlockSize)) return cBlockSize; + if (ZSTDv06_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTDv06_blockHeaderSize; remainingSize -= ZSTDv06_blockHeaderSize; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } if (cBlockSize == 0) break; /* bt_end */ ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * ZSTDv06_BLOCKSIZE_MAX; } /*_****************************** diff --git a/lib/legacy/zstd_v06.h b/lib/legacy/zstd_v06.h index fb4eb37c89e2..07818571dca0 100644 --- a/lib/legacy/zstd_v06.h +++ b/lib/legacy/zstd_v06.h @@ -43,12 +43,17 @@ ZSTDLIBv06_API size_t ZSTDv06_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); /** -ZSTDv06_getFrameSrcSize() : get the source length of a ZSTD frame - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv06_isError()) +ZSTDv06_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.6.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. */ -size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t compressedSize); +void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /* ************************************* * Helper functions diff --git a/lib/legacy/zstd_v07.c b/lib/legacy/zstd_v07.c index c7bb7a529813..6b9488931f35 100644 --- a/lib/legacy/zstd_v07.c +++ b/lib/legacy/zstd_v07.c @@ -2740,6 +2740,8 @@ typedef enum { lbt_huffman, lbt_repeat, lbt_raw, lbt_rle } litBlockType_t; #define FSEv07_ENCODING_STATIC 2 #define FSEv07_ENCODING_DYNAMIC 3 +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12, 13,14,15,16 }; @@ -3631,7 +3633,7 @@ size_t ZSTDv07_execSequence(BYTE* op, if (sequence.offset < 8) { /* close range match, overlap */ static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */ - static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* substracted */ + static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */ int const sub2 = dec64table[sequence.offset]; op[0] = match[0]; op[1] = match[1]; @@ -3895,19 +3897,40 @@ size_t ZSTDv07_decompress(void* dst, size_t dstCapacity, const void* src, size_t #endif } -size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize) +/* ZSTD_errorFrameSizeInfoLegacy() : + assumes `cSize` and `dBound` are _not_ NULL */ +static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) +{ + *cSize = ret; + *dBound = ZSTD_CONTENTSIZE_ERROR; +} + +void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { const BYTE* ip = (const BYTE*)src; size_t remainingSize = srcSize; + size_t nbBlocks = 0; /* check */ - if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong); + if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } /* Frame Header */ { size_t const frameHeaderSize = ZSTDv07_frameHeaderSize(src, ZSTDv07_frameHeaderSize_min); - if (ZSTDv07_isError(frameHeaderSize)) return frameHeaderSize; - if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) return ERROR(prefix_unknown); - if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong); + if (ZSTDv07_isError(frameHeaderSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize); + return; + } + if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); + return; + } + if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } ip += frameHeaderSize; remainingSize -= frameHeaderSize; } @@ -3915,20 +3938,28 @@ size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize) while (1) { blockProperties_t blockProperties; size_t const cBlockSize = ZSTDv07_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTDv07_isError(cBlockSize)) return cBlockSize; + if (ZSTDv07_isError(cBlockSize)) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); + return; + } ip += ZSTDv07_blockHeaderSize; remainingSize -= ZSTDv07_blockHeaderSize; if (blockProperties.blockType == bt_end) break; - if (cBlockSize > remainingSize) return ERROR(srcSize_wrong); + if (cBlockSize > remainingSize) { + ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); + return; + } ip += cBlockSize; remainingSize -= cBlockSize; + nbBlocks++; } - return ip - (const BYTE*)src; + *cSize = ip - (const BYTE*)src; + *dBound = nbBlocks * ZSTDv07_BLOCKSIZE_ABSOLUTEMAX; } /*_****************************** diff --git a/lib/legacy/zstd_v07.h b/lib/legacy/zstd_v07.h index 6591cd3014b0..a566c1d102ac 100644 --- a/lib/legacy/zstd_v07.h +++ b/lib/legacy/zstd_v07.h @@ -50,12 +50,17 @@ ZSTDLIBv07_API size_t ZSTDv07_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); /** -ZSTDv07_getFrameSrcSize() : get the source length of a ZSTD frame - compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' - return : the number of bytes that would be read to decompress this frame - or an errorCode if it fails (which can be tested using ZSTDv07_isError()) +ZSTDv07_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.7.x format + srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' + cSize (output parameter) : the number of bytes that would be read to decompress this frame + or an error code if it fails (which can be tested using ZSTDv01_isError()) + dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame + or ZSTD_CONTENTSIZE_ERROR if an error occurs + + note : assumes `cSize` and `dBound` are _not_ NULL. */ -size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t compressedSize); +void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, + size_t* cSize, unsigned long long* dBound); /*====== Helper functions ======*/ ZSTDLIBv07_API unsigned ZSTDv07_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ diff --git a/lib/zstd.h b/lib/zstd.h index b18fc8a44bf9..53470c18f367 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -70,8 +70,8 @@ extern "C" { /*------ Version ------*/ #define ZSTD_VERSION_MAJOR 1 -#define ZSTD_VERSION_MINOR 3 -#define ZSTD_VERSION_RELEASE 8 +#define ZSTD_VERSION_MINOR 4 +#define ZSTD_VERSION_RELEASE 0 #define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< to check runtime library version */ @@ -89,6 +89,21 @@ ZSTDLIB_API const char* ZSTD_versionString(void); /* requires v1.3.0+ */ # define ZSTD_CLEVEL_DEFAULT 3 #endif +/*************************************** +* Constants +***************************************/ + +/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* valid since v0.8.0 */ +#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* valid since v0.7.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50 /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */ +#define ZSTD_MAGIC_SKIPPABLE_MASK 0xFFFFFFF0 + +#define ZSTD_BLOCKSIZELOG_MAX 17 +#define ZSTD_BLOCKSIZE_MAX (1< = first frame size + * @return : the compressed size of the first frame starting at `src`, + * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, + * or an error code if input is invalid */ +ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); + /*====== Helper functions ======*/ #define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ +ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ @@ -195,279 +219,6 @@ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, const void* src, size_t srcSize); -/************************** -* Simple dictionary API -***************************/ -/*! ZSTD_compress_usingDict() : - * Compression at an explicit compression level using a Dictionary. - * A dictionary can be any arbitrary data segment (also called a prefix), - * or a buffer with specified information (see dictBuilder/zdict.h). - * Note : This function loads the dictionary, resulting in significant startup delay. - * It's intended for a dictionary used only once. - * Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */ -ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, - int compressionLevel); - -/*! ZSTD_decompress_usingDict() : - * Decompression using a known Dictionary. - * Dictionary must be identical to the one used during compression. - * Note : This function loads the dictionary, resulting in significant startup delay. - * It's intended for a dictionary used only once. - * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ -ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize); - - -/*********************************** - * Bulk processing dictionary API - **********************************/ -typedef struct ZSTD_CDict_s ZSTD_CDict; - -/*! ZSTD_createCDict() : - * When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once. - * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost. - * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. - * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict. - * Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content. - * Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, - int compressionLevel); - -/*! ZSTD_freeCDict() : - * Function frees memory allocated by ZSTD_createCDict(). */ -ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); - -/*! ZSTD_compress_usingCDict() : - * Compression using a digested Dictionary. - * Recommended when same dictionary is used multiple times. - * Note : compression level is _decided at dictionary creation time_, - * and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ -ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict); - - -typedef struct ZSTD_DDict_s ZSTD_DDict; - -/*! ZSTD_createDDict() : - * Create a digested dictionary, ready to start decompression operation without startup delay. - * dictBuffer can be released after DDict creation, as its content is copied inside DDict. */ -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); - -/*! ZSTD_freeDDict() : - * Function frees memory allocated with ZSTD_createDDict() */ -ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); - -/*! ZSTD_decompress_usingDDict() : - * Decompression using a digested Dictionary. - * Recommended when same dictionary is used multiple times. */ -ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_DDict* ddict); - - -/**************************** -* Streaming -****************************/ - -typedef struct ZSTD_inBuffer_s { - const void* src; /**< start of input buffer */ - size_t size; /**< size of input buffer */ - size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_inBuffer; - -typedef struct ZSTD_outBuffer_s { - void* dst; /**< start of output buffer */ - size_t size; /**< size of output buffer */ - size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_outBuffer; - - - -/*-*********************************************************************** -* Streaming compression - HowTo -* -* A ZSTD_CStream object is required to track streaming operation. -* Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. -* ZSTD_CStream objects can be reused multiple times on consecutive compression operations. -* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. -* -* For parallel execution, use one separate ZSTD_CStream per thread. -* -* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. -* -* Parameters are sticky : when starting a new compression on the same context, -* it will re-use the same sticky parameters as previous compression session. -* When in doubt, it's recommended to fully initialize the context before usage. -* Use ZSTD_initCStream() to set the parameter to a selected compression level. -* Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters. -* -* Use ZSTD_compressStream() as many times as necessary to consume input stream. -* The function will automatically update both `pos` fields within `input` and `output`. -* Note that the function may not consume the entire input, -* for example, because the output buffer is already full, -* in which case `input.pos < input.size`. -* The caller must check if input has been entirely consumed. -* If not, the caller must make some room to receive more compressed data, -* and then present again remaining input data. -* @return : a size hint, preferred nb of bytes to use as input for next function call -* or an error code, which can be tested using ZSTD_isError(). -* Note 1 : it's just a hint, to help latency a little, any value will work fine. -* Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize() -* -* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, -* using ZSTD_flushStream(). `output->pos` will be updated. -* Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0). -* In which case, make some room to receive more compressed data, and call again ZSTD_flushStream(). -* @return : 0 if internal buffers are entirely flushed, -* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), -* or an error code, which can be tested using ZSTD_isError(). -* -* ZSTD_endStream() instructs to finish a frame. -* It will perform a flush and write frame epilogue. -* The epilogue is required for decoders to consider a frame completed. -* flush() operation is the same, and follows same rules as ZSTD_flushStream(). -* @return : 0 if frame fully completed and fully flushed, -* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), -* or an error code, which can be tested using ZSTD_isError(). -* -* *******************************************************************/ - -typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ - /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ -/*===== ZSTD_CStream management functions =====*/ -ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); -ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); - -/*===== Streaming compression functions =====*/ -ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); -ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); - -ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ - - - -/*-*************************************************************************** -* Streaming decompression - HowTo -* -* A ZSTD_DStream object is required to track streaming operations. -* Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. -* ZSTD_DStream objects can be re-used multiple times. -* -* Use ZSTD_initDStream() to start a new decompression operation. -* @return : recommended first input size -* Alternatively, use advanced API to set specific properties. -* -* Use ZSTD_decompressStream() repetitively to consume your input. -* The function will update both `pos` fields. -* If `input.pos < input.size`, some input has not been consumed. -* It's up to the caller to present again remaining data. -* The function tries to flush all data decoded immediately, respecting output buffer size. -* If `output.pos < output.size`, decoder has flushed everything it could. -* But if `output.pos == output.size`, there might be some data left within internal buffers., -* In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. -* Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. -* @return : 0 when a frame is completely decoded and fully flushed, -* or an error code, which can be tested using ZSTD_isError(), -* or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : -* the return value is a suggested next input size (just a hint for better latency) -* that will never request more than the remaining frame size. -* *******************************************************************************/ - -typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ - /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ -/*===== ZSTD_DStream management functions =====*/ -ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); -ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); - -/*===== Streaming decompression functions =====*/ -ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); -ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); - -ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ - -#endif /* ZSTD_H_235446 */ - - - - -/**************************************************************************************** - * ADVANCED AND EXPERIMENTAL FUNCTIONS - **************************************************************************************** - * The definitions in the following section are considered experimental. - * They are provided for advanced scenarios. - * They should never be used with a dynamic library, as prototypes may change in the future. - * Use them only in association with static linking. - * ***************************************************************************************/ - -#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) -#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY - - -/**************************************************************************************** - * Candidate API for promotion to stable status - **************************************************************************************** - * The following symbols and constants form the "staging area" : - * they are considered to join "stable API" by v1.4.0. - * The proposal is written so that it can be made stable "as is", - * though it's still possible to suggest improvements. - * Staging is in fact last chance for changes, - * the API is locked once reaching "stable" status. - * ***************************************************************************************/ - - -/* === Constants === */ - -/* all magic numbers are supposed read/written to/from files/memory using little-endian convention */ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* valid since v0.8.0 */ -#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* valid since v0.7.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50 /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */ -#define ZSTD_MAGIC_SKIPPABLE_MASK 0xFFFFFFF0 - -#define ZSTD_BLOCKSIZELOG_MAX 17 -#define ZSTD_BLOCKSIZE_MAX (1< = first frame size - * @return : the compressed size of the first frame starting at `src`, - * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, - * or an error code if input is invalid */ -ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); - - -/* === Memory management === */ - -/*! ZSTD_sizeof_*() : - * These functions give the _current_ memory usage of selected object. - * Note that object memory usage can evolve (increase or decrease) over time. */ -ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); -ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); -ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); -ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); -ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); - - /*************************************** * Advanced compression API ***************************************/ @@ -503,7 +254,10 @@ typedef enum { ZSTD_fast=1, typedef enum { - /* compression parameters */ + /* compression parameters + * Note: When compressing with a ZSTD_CDict these parameters are superseded + * by the parameters used to construct the ZSTD_CDict. See ZSTD_CCtx_refCDict() + * for more info (superseded-by-cdict). */ ZSTD_c_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table * Default level is ZSTD_CLEVEL_DEFAULT==3. * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT. @@ -625,6 +379,7 @@ typedef enum { * ZSTD_c_format * ZSTD_c_forceMaxWindow * ZSTD_c_forceAttachDict + * ZSTD_c_literalCompressionMode * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. * note : never ever use experimentalParam? names directly; * also, the enums values themselves are unstable and can still change. @@ -632,10 +387,10 @@ typedef enum { ZSTD_c_experimentalParam1=500, ZSTD_c_experimentalParam2=10, ZSTD_c_experimentalParam3=1000, - ZSTD_c_experimentalParam4=1001 + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, } ZSTD_cParameter; - typedef struct { size_t error; int lowerBound; @@ -677,10 +432,427 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param * Note 3 : Whenever all input data is provided and consumed in a single round, * for example with ZSTD_compress2(), * or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end), - * this value is automatically overriden by srcSize instead. + * this value is automatically overridden by srcSize instead. */ ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); +typedef enum { + ZSTD_reset_session_only = 1, + ZSTD_reset_parameters = 2, + ZSTD_reset_session_and_parameters = 3 +} ZSTD_ResetDirective; + +/*! ZSTD_CCtx_reset() : + * There are 2 different things that can be reset, independently or jointly : + * - The session : will stop compressing current frame, and make CCtx ready to start a new one. + * Useful after an error, or to interrupt any ongoing compression. + * Any internal data not yet flushed is cancelled. + * Compression parameters and dictionary remain unchanged. + * They will be used to compress next frame. + * Resetting session never fails. + * - The parameters : changes all parameters back to "default". + * This removes any reference to any dictionary too. + * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) + * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) + * - Both : similar to resetting the session, followed by resetting parameters. + */ +ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset); + +/*! ZSTD_compress2() : + * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. + * ZSTD_compress2() always starts a new frame. + * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - The function is always blocking, returns when compression is completed. + * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); + + +/*************************************** +* Advanced decompression API +***************************************/ + +/* The advanced API pushes parameters one by one into an existing DCtx context. + * Parameters are sticky, and remain valid for all following frames + * using the same DCtx context. + * It's possible to reset parameters to default values using ZSTD_DCtx_reset(). + * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream(). + * Therefore, no new decompression function is necessary. + */ + +typedef enum { + + ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which + * the streaming API will refuse to allocate memory buffer + * in order to protect the host from unreasonable memory requirements. + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT). + * Special: value 0 means "use default maximum windowLog". */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_c_format + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly + */ + ZSTD_d_experimentalParam1=1000 + +} ZSTD_dParameter; + +/*! ZSTD_dParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - both lower and upper bounds, inclusive + */ +ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); + +/*! ZSTD_DCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_dParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is only possible during frame initialization (before starting decompression). + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); + +/*! ZSTD_DCtx_reset() : + * Return a DCtx to clean state. + * Session and parameters can be reset jointly or separately. + * Parameters can only be reset when no active frame is being decompressed. + * @return : 0, or an error code, which can be tested with ZSTD_isError() + */ +ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); + + +/**************************** +* Streaming +****************************/ + +typedef struct ZSTD_inBuffer_s { + const void* src; /**< start of input buffer */ + size_t size; /**< size of input buffer */ + size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_inBuffer; + +typedef struct ZSTD_outBuffer_s { + void* dst; /**< start of output buffer */ + size_t size; /**< size of output buffer */ + size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_outBuffer; + + + +/*-*********************************************************************** +* Streaming compression - HowTo +* +* A ZSTD_CStream object is required to track streaming operation. +* Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. +* ZSTD_CStream objects can be reused multiple times on consecutive compression operations. +* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. +* +* For parallel execution, use one separate ZSTD_CStream per thread. +* +* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. +* +* Parameters are sticky : when starting a new compression on the same context, +* it will re-use the same sticky parameters as previous compression session. +* When in doubt, it's recommended to fully initialize the context before usage. +* Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), +* ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to +* set more specific parameters, the pledged source size, or load a dictionary. +* +* Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to +* consume input stream. The function will automatically update both `pos` +* fields within `input` and `output`. +* Note that the function may not consume the entire input, for example, because +* the output buffer is already full, in which case `input.pos < input.size`. +* The caller must check if input has been entirely consumed. +* If not, the caller must make some room to receive more compressed data, +* and then present again remaining input data. +* note: ZSTD_e_continue is guaranteed to make some forward progress when called, +* but doesn't guarantee maximal forward progress. This is especially relevant +* when compressing with multiple threads. The call won't block if it can +* consume some input, but if it can't it will wait for some, but not all, +* output to be flushed. +* @return : provides a minimum amount of data remaining to be flushed from internal buffers +* or an error code, which can be tested using ZSTD_isError(). +* +* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, +* using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated. +* Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0). +* In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the +* operation. +* note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if internal buffers are entirely flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. +* It will perform a flush and write frame epilogue. +* The epilogue is required for decoders to consider a frame completed. +* flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to +* start a new frame. +* note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if frame fully completed and fully flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* *******************************************************************/ + +typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ + /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ +/*===== ZSTD_CStream management functions =====*/ +ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); +ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); + +/*===== Streaming compression functions =====*/ +typedef enum { + ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. + * note : multithreaded compression will block to flush as much output as possible. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * note that frame is only closed after compressed data is fully flushed (return value == 0). + * After that point, any additional data starts a new frame. + * note : each frame is independent (does not reference any content from previous frame). + : note : multithreaded compression will block to flush as much output as possible. */ +} ZSTD_EndDirective; + +/*! ZSTD_compressStream2() : + * Behaves about the same as ZSTD_compressStream, with additional control on end directive. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) + * - output->pos must be <= dstCapacity, input->pos must be <= srcSize + * - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + * - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, + * and then immediately returns, just indicating that there is some data remaining to be flushed. + * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + * - @return provides a minimum amount of data remaining to be flushed from internal buffers + * or an error code, which can be tested using ZSTD_isError(). + * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + * only ZSTD_e_end or ZSTD_e_flush operations are allowed. + * Before starting a new compression job, or changing compression parameters, + * it is required to fully flush internal buffers. + */ +ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); + +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ + +/******************************************************************************* + * This is a legacy streaming API, and can be replaced by ZSTD_CCtx_reset() and + * ZSTD_compressStream2(). It is redundant, but is still fully supported. + * Advanced parameters and dictionary compression can only be used through the + * new API. + ******************************************************************************/ + +/** + * Equivalent to: + * + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + */ +ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); +/** + * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue). + * NOTE: The return value is different. ZSTD_compressStream() returns a hint for + * the next read size (if non-zero and not an error). ZSTD_compressStream2() + * returns the number of bytes left to flush (if non-zero and not an error). + */ +ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ +ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ +ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); + + +/*-*************************************************************************** +* Streaming decompression - HowTo +* +* A ZSTD_DStream object is required to track streaming operations. +* Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. +* ZSTD_DStream objects can be re-used multiple times. +* +* Use ZSTD_initDStream() to start a new decompression operation. +* @return : recommended first input size +* Alternatively, use advanced API to set specific properties. +* +* Use ZSTD_decompressStream() repetitively to consume your input. +* The function will update both `pos` fields. +* If `input.pos < input.size`, some input has not been consumed. +* It's up to the caller to present again remaining data. +* The function tries to flush all data decoded immediately, respecting output buffer size. +* If `output.pos < output.size`, decoder has flushed everything it could. +* But if `output.pos == output.size`, there might be some data left within internal buffers., +* In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. +* Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. +* @return : 0 when a frame is completely decoded and fully flushed, +* or an error code, which can be tested using ZSTD_isError(), +* or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : +* the return value is a suggested next input size (just a hint for better latency) +* that will never request more than the remaining frame size. +* *******************************************************************************/ + +typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ + /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ +/*===== ZSTD_DStream management functions =====*/ +ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); +ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); + +/*===== Streaming decompression functions =====*/ + +/* This function is redundant with the advanced API and equivalent to: + * + * ZSTD_DCtx_reset(zds); + * ZSTD_DCtx_refDDict(zds, NULL); + */ +ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); + +ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); + +ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ + + +/************************** +* Simple dictionary API +***************************/ +/*! ZSTD_compress_usingDict() : + * Compression at an explicit compression level using a Dictionary. + * A dictionary can be any arbitrary data segment (also called a prefix), + * or a buffer with specified information (see dictBuilder/zdict.h). + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + int compressionLevel); + +/*! ZSTD_decompress_usingDict() : + * Decompression using a known Dictionary. + * Dictionary must be identical to the one used during compression. + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize); + + +/*********************************** + * Bulk processing dictionary API + **********************************/ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/*! ZSTD_createCDict() : + * When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once. + * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost. + * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict. + * Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content. + * Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, + int compressionLevel); + +/*! ZSTD_freeCDict() : + * Function frees memory allocated by ZSTD_createCDict(). */ +ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); + +/*! ZSTD_compress_usingCDict() : + * Compression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. + * Note : compression level is _decided at dictionary creation time_, + * and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict); + + +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/*! ZSTD_createDDict() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * dictBuffer can be released after DDict creation, as its content is copied inside DDict. */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_freeDDict() : + * Function frees memory allocated with ZSTD_createDDict() */ +ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); + +/*! ZSTD_decompress_usingDDict() : + * Decompression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict); + + +/******************************** + * Dictionary helper functions + *******************************/ + +/*! ZSTD_getDictID_fromDict() : + * Provides the dictID stored within dictionary. + * if @return == 0, the dictionary is not conformant with Zstandard specification. + * It can still be loaded, but as a content-only dictionary. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); + +/*! ZSTD_getDictID_fromDDict() : + * Provides the dictID of the dictionary loaded into `ddict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); + +/*! ZSTD_getDictID_fromFrame() : + * Provides the dictID required to decompressed the frame stored within `src`. + * If @return == 0, the dictID could not be decoded. + * This could for one of the following reasons : + * - The frame does not require a dictionary to be decoded (most common case). + * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. + * Note : this use case also happens when using a non-conformant dictionary. + * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). + * - This is not a Zstandard frame. + * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); + + +/******************************************************************************* + * Advanced dictionary and prefix API + * + * This API allows dictionaries to be used with ZSTD_compress2(), + * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and + * only reset with the context is reset with ZSTD_reset_parameters or + * ZSTD_reset_session_and_parameters. Prefixes are single-use. + ******************************************************************************/ + + /*! ZSTD_CCtx_loadDictionary() : * Create an internal CDict from `dict` buffer. * Decompression will have to use same dictionary. @@ -703,7 +875,9 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s /*! ZSTD_CCtx_refCDict() : * Reference a prepared dictionary, to be used for all next compressed frames. * Note that compression parameters are enforced from within CDict, - * and supercede any compression parameter previously set within CCtx. + * and supersede any compression parameter previously set within CCtx. + * The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. + * The ignored parameters will be used again if the CCtx is returned to no-dictionary mode. * The dictionary will remain valid for future compressed frames using same CCtx. * @result : 0, or an error code (which can be tested with ZSTD_isError()). * Special : Referencing a NULL CDict means "return to no-dictionary mode". @@ -733,136 +907,6 @@ ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); - -typedef enum { - ZSTD_reset_session_only = 1, - ZSTD_reset_parameters = 2, - ZSTD_reset_session_and_parameters = 3 -} ZSTD_ResetDirective; - -/*! ZSTD_CCtx_reset() : - * There are 2 different things that can be reset, independently or jointly : - * - The session : will stop compressing current frame, and make CCtx ready to start a new one. - * Useful after an error, or to interrupt any ongoing compression. - * Any internal data not yet flushed is cancelled. - * Compression parameters and dictionary remain unchanged. - * They will be used to compress next frame. - * Resetting session never fails. - * - The parameters : changes all parameters back to "default". - * This removes any reference to any dictionary too. - * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) - * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) - * - Both : similar to resetting the session, followed by resetting parameters. - */ -ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset); - - - -/*! ZSTD_compress2() : - * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. - * ZSTD_compress2() always starts a new frame. - * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. - * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() - * - The function is always blocking, returns when compression is completed. - * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. - * @return : compressed size written into `dst` (<= `dstCapacity), - * or an error code if it fails (which can be tested using ZSTD_isError()). - */ -ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize); - -typedef enum { - ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ - ZSTD_e_flush=1, /* flush any data provided so far, - * it creates (at least) one new block, that can be decoded immediately on reception; - * frame will continue: any future data can still reference previously compressed data, improving compression. */ - ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. - * note that frame is only closed after compressed data is fully flushed (return value == 0). - * After that point, any additional data starts a new frame. - * note : each frame is independent (does not reference any content from previous frame). */ -} ZSTD_EndDirective; - -/*! ZSTD_compressStream2() : - * Behaves about the same as ZSTD_compressStream, with additional control on end directive. - * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() - * - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) - * - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize - * - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. - * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. - * - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, - * and then immediately returns, just indicating that there is some data remaining to be flushed. - * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. - * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. - * - @return provides a minimum amount of data remaining to be flushed from internal buffers - * or an error code, which can be tested using ZSTD_isError(). - * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. - * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. - * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. - * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), - * only ZSTD_e_end or ZSTD_e_flush operations are allowed. - * Before starting a new compression job, or changing compression parameters, - * it is required to fully flush internal buffers. - */ -ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective endOp); - - - -/* ============================== */ -/* Advanced decompression API */ -/* ============================== */ - -/* The advanced API pushes parameters one by one into an existing DCtx context. - * Parameters are sticky, and remain valid for all following frames - * using the same DCtx context. - * It's possible to reset parameters to default values using ZSTD_DCtx_reset(). - * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream(). - * Therefore, no new decompression function is necessary. - */ - - -typedef enum { - - ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which - * the streaming API will refuse to allocate memory buffer - * in order to protect the host from unreasonable memory requirements. - * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. - * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) */ - - /* note : additional experimental parameters are also available - * within the experimental section of the API. - * At the time of this writing, they include : - * ZSTD_c_format - * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. - * note : never ever use experimentalParam? names directly - */ - ZSTD_d_experimentalParam1=1000 - -} ZSTD_dParameter; - - -/*! ZSTD_dParam_getBounds() : - * All parameters must belong to an interval with lower and upper bounds, - * otherwise they will either trigger an error or be automatically clamped. - * @return : a structure, ZSTD_bounds, which contains - * - an error status field, which must be tested using ZSTD_isError() - * - both lower and upper bounds, inclusive - */ -ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); - -/*! ZSTD_DCtx_setParameter() : - * Set one compression parameter, selected by enum ZSTD_dParameter. - * All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds(). - * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). - * Setting a parameter is only possible during frame initialization (before starting decompression). - * @return : 0, or an error code (which can be tested using ZSTD_isError()). - */ -ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); - - /*! ZSTD_DCtx_loadDictionary() : * Create an internal DDict from dict buffer, * to be used to decompress next frames. @@ -910,15 +954,32 @@ ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize); -/*! ZSTD_DCtx_reset() : - * Return a DCtx to clean state. - * Session and parameters can be reset jointly or separately. - * Parameters can only be reset when no active frame is being decompressed. - * @return : 0, or an error code, which can be tested with ZSTD_isError() - */ -ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); +/* === Memory management === */ + +/*! ZSTD_sizeof_*() : + * These functions give the _current_ memory usage of selected object. + * Note that object memory usage can evolve (increase or decrease) over time. */ +ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); +ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); +ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); + +#endif /* ZSTD_H_235446 */ +/**************************************************************************************** + * ADVANCED AND EXPERIMENTAL FUNCTIONS + **************************************************************************************** + * The definitions in the following section are considered experimental. + * They are provided for advanced scenarios. + * They should never be used with a dynamic library, as prototypes may change in the future. + * Use them only in association with static linking. + * ***************************************************************************************/ + +#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) +#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY /**************************************************************************************** * experimental API (static linking only) @@ -962,7 +1023,7 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); #define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27 /* by default, the streaming decoder will refuse any frame * requiring larger than (1< = ZSTD_FRAMEHEADERSIZE_PREFIX. * @return : size of the Frame Header, @@ -1110,7 +1195,7 @@ ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); * It will also consider src size to be arbitrarily "large", which is worst case. * If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation. * ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + * ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. * Note : CCtx size estimation is only correct for single-threaded compression. */ ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel); ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); @@ -1122,7 +1207,7 @@ ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); * It will also consider src size to be arbitrarily "large", which is worst case. * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. * Note : CStream size estimation is only correct for single-threaded compression. * ZSTD_DStream memory budget depends on window Size. * This information can be passed manually, using ZSTD_estimateDStreamSize, @@ -1226,22 +1311,26 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictS ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); /*! ZSTD_getCParams() : -* @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. -* `estimatedSrcSize` value is optional, select 0 if not known */ + * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. + * `estimatedSrcSize` value is optional, select 0 if not known */ ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); /*! ZSTD_getParams() : -* same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. -* All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */ + * same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. + * All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */ ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); /*! ZSTD_checkCParams() : -* Ensure param values remain within authorized range */ + * Ensure param values remain within authorized range. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */ ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); /*! ZSTD_adjustCParams() : * optimize params for a given `srcSize` and `dictSize`. - * both values are optional, select `0` if unknown. */ + * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. + * `dictSize` must be `0` when there is no dictionary. + * cPar can be invalid : all parameters will be clamped within valid range in the @return struct. + * This function never fails (wide contract) */ ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); /*! ZSTD_compress_advanced() : @@ -1314,6 +1403,12 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre * See the comments on that enum for an explanation of the feature. */ #define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4 +/* Controls how the literals are compressed (default is auto). + * The value must be of type ZSTD_literalCompressionMode_e. + * See ZSTD_literalCompressionMode_t enum definition for details. + */ +#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5 + /*! ZSTD_CCtx_getParameter() : * Get the requested compression parameter value, selected by enum ZSTD_cParameter, * and store it into int* value. @@ -1325,10 +1420,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param /*! ZSTD_CCtx_params : * Quick howto : * - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure - * - ZSTD_CCtxParam_setParameter() : Push parameters one by one into - * an existing ZSTD_CCtx_params structure. - * This is similar to - * ZSTD_CCtx_setParameter(). + * - ZSTD_CCtxParams_setParameter() : Push parameters one by one into + * an existing ZSTD_CCtx_params structure. + * This is similar to + * ZSTD_CCtx_setParameter(). * - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to * an existing CCtx. * These parameters will be applied to @@ -1359,20 +1454,20 @@ ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compre */ ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); -/*! ZSTD_CCtxParam_setParameter() : +/*! ZSTD_CCtxParams_setParameter() : * Similar to ZSTD_CCtx_setParameter. * Set one compression parameter, selected by enum ZSTD_cParameter. * Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams(). * @result : 0, or an error code (which can be tested with ZSTD_isError()). */ -ZSTDLIB_API size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); +ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); -/*! ZSTD_CCtxParam_getParameter() : +/*! ZSTD_CCtxParams_getParameter() : * Similar to ZSTD_CCtx_getParameter. * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter. * @result : 0, or an error code (which can be tested with ZSTD_isError()). */ -ZSTDLIB_API size_t ZSTD_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); +ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); /*! ZSTD_CCtx_setParametersUsingCCtxParams() : * Apply a set of ZSTD_CCtx_params to the compression context. @@ -1415,31 +1510,6 @@ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); * it must remain read accessible throughout the lifetime of DDict */ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); - -/*! ZSTD_getDictID_fromDict() : - * Provides the dictID stored within dictionary. - * if @return == 0, the dictionary is not conformant with Zstandard specification. - * It can still be loaded, but as a content-only dictionary. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); - -/*! ZSTD_getDictID_fromDDict() : - * Provides the dictID of the dictionary loaded into `ddict`. - * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. - * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); - -/*! ZSTD_getDictID_fromFrame() : - * Provides the dictID required to decompressed the frame stored within `src`. - * If @return == 0, the dictID could not be decoded. - * This could for one of the following reasons : - * - The frame does not require a dictionary to be decoded (most common case). - * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. - * Note : this use case also happens when using a non-conformant dictionary. - * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). - * - This is not a Zstandard frame. - * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); - /*! ZSTD_DCtx_loadDictionary_byReference() : * Same as ZSTD_DCtx_loadDictionary(), * but references `dict` content instead of copying it into `dctx`. @@ -1501,14 +1571,68 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs ( ********************************************************************/ /*===== Advanced Streaming compression functions =====*/ -ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/ +/**! ZSTD_initCStream_srcSize() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * pledgedSrcSize must be correct. If it is not known at init time, use + * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, + * "0" also disables frame content size field. It may be enabled in the future. + */ +ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); +/**! ZSTD_initCStream_usingDict() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * Creates of an internal CDict (incompatible with static CCtx), except if + * dict == NULL or dictSize < 8, in which case no dict is used. + * Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if + * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy. + */ +ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); +/**! ZSTD_initCStream_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setZstdParams(zcs, params); // Set the zstd params and leave the rest as-is + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. + */ ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, - ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */ + ZSTD_parameters params, unsigned long long pledgedSrcSize); +/**! ZSTD_initCStream_usingCDict() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * note : cdict will just be referenced, and must outlive compression session + */ +ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); +/**! ZSTD_initCStream_usingCDict_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setZstdFrameParams(zcs, fParams); // Set the zstd frame params and leave the rest as-is + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters. + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. + */ +ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /*! ZSTD_resetCStream() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * * start a new frame, using same parameters from previous frame. * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. * Note that zcs must be init at least once before using ZSTD_resetCStream(). @@ -1555,9 +1679,32 @@ ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); /*===== Advanced Streaming decompression functions =====*/ -ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: no dictionary will be used if dict == NULL or dictSize < 8 */ -ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict is referenced, it must outlive decompression session */ -ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */ +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_loadDictionary(zds, dict, dictSize); + * + * note: no dictionary will be used if dict == NULL or dictSize < 8 + */ +ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, ddict); + * + * note : ddict is referenced, it must outlive decompression session + */ +ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * + * re-use decompression parameters from previous init; saves dictionary loading + */ +ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /********************************************************************* diff --git a/programs/Makefile b/programs/Makefile index d1910fbb4b79..64dcae0028e7 100644 --- a/programs/Makefile +++ b/programs/Makefile @@ -51,7 +51,7 @@ endif CFLAGS ?= -O3 DEBUGFLAGS+=-Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \ - -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \ + -Wstrict-prototypes -Wundef -Wpointer-arith \ -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \ -Wredundant-decls -Wmissing-prototypes -Wc++-compat CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS) @@ -165,7 +165,7 @@ $(ZSTDDECOMP_O): CFLAGS += $(ALIGN_LOOP) zstd : CPPFLAGS += $(THREAD_CPP) $(ZLIBCPP) $(LZMACPP) $(LZ4CPP) zstd : LDFLAGS += $(THREAD_LD) $(ZLIBLD) $(LZMALD) $(LZ4LD) $(DEBUGFLAGS_LD) zstd : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) -zstd : $(ZSTDLIB_FILES) zstdcli.o util.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o +zstd : $(ZSTDLIB_FILES) zstdcli.o util.o timefn.o fileio.o benchfn.o benchzstd.o datagen.o dibio.o @echo "$(THREAD_MSG)" @echo "$(ZLIB_MSG)" @echo "$(LZMA_MSG)" @@ -183,13 +183,13 @@ zstd-release: zstd zstd32 : CPPFLAGS += $(THREAD_CPP) zstd32 : LDFLAGS += $(THREAD_LD) zstd32 : CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) -zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c +zstd32 : $(ZSTDLIB_FILES) zstdcli.c util.c timefn.c fileio.c benchfn.c benchzstd.c datagen.c dibio.c ifneq (,$(filter Windows%,$(OS))) windres/generate_res.bat endif $(CC) -m32 $(FLAGS) $^ $(RES32_FILE) -o $@$(EXT) -zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o datagen.o dibio.o +zstd-nolegacy : $(ZSTD_FILES) $(ZDICT_FILES) zstdcli.o util.o fileio.c benchfn.o benchzstd.o timefn.o datagen.o dibio.o $(CC) $(FLAGS) $^ -o $@$(EXT) $(LDFLAGS) zstd-nomt : THREAD_CPP := @@ -222,13 +222,13 @@ zstd-pgo : # minimal target, with only zstd compression and decompression. no bench. no legacy. zstd-small: CFLAGS = -Os -s -zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c fileio.c +zstd-frugal zstd-small: $(ZSTD_FILES) zstdcli.c util.c timefn.c fileio.c $(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT $^ -o $@$(EXT) -zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c fileio.c +zstd-decompress: $(ZSTDCOMMON_FILES) $(ZSTDDECOMP_FILES) zstdcli.c util.c timefn.c fileio.c $(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NOCOMPRESS $^ -o $@$(EXT) -zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c fileio.c +zstd-compress: $(ZSTDCOMMON_FILES) $(ZSTDCOMP_FILES) zstdcli.c util.c timefn.c fileio.c $(CC) $(FLAGS) -DZSTD_NOBENCH -DZSTD_NODICT -DZSTD_NODECOMPRESS $^ -o $@$(EXT) zstdmt: zstd @@ -265,9 +265,9 @@ man: zstd.1 zstdgrep.1 zstdless.1 .PHONY: clean-man clean-man: - rm zstd.1 - rm zstdgrep.1 - rm zstdless.1 + $(RM) zstd.1 + $(RM) zstdgrep.1 + $(RM) zstdless.1 .PHONY: preview-man preview-man: clean-man man diff --git a/programs/benchfn.c b/programs/benchfn.c index f5118d0871f1..0932d155de49 100644 --- a/programs/benchfn.c +++ b/programs/benchfn.c @@ -13,25 +13,20 @@ /* ************************************* * Includes ***************************************/ -#include "platform.h" /* Large Files support */ -#include "util.h" /* UTIL_getFileSize, UTIL_sleep */ #include /* malloc, free */ #include /* memset */ -#include /* fprintf, fopen */ #undef NDEBUG /* assert must not be disabled */ #include /* assert */ -#include "mem.h" +#include "timefn.h" /* UTIL_time_t, UTIL_getTime */ #include "benchfn.h" /* ************************************* * Constants ***************************************/ -#define TIMELOOP_MICROSEC (1*1000000ULL) /* 1 second */ +#define TIMELOOP_MICROSEC SEC_TO_MICRO /* 1 second */ #define TIMELOOP_NANOSEC (1*1000000000ULL) /* 1 second */ -#define ACTIVEPERIOD_MICROSEC (70*TIMELOOP_MICROSEC) /* 70 seconds */ -#define COOLPERIOD_SEC 10 #define KB *(1 <<10) #define MB *(1 <<20) @@ -39,14 +34,16 @@ /* ************************************* -* Errors +* Debug errors ***************************************/ -#ifndef DEBUG -# define DEBUG 0 +#if defined(DEBUG) && (DEBUG >= 1) +# include /* fprintf */ +# define DISPLAY(...) fprintf(stderr, __VA_ARGS__) +# define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); } +#else +# define DEBUGOUTPUT(...) #endif -#define DISPLAY(...) fprintf(stderr, __VA_ARGS__) -#define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); } /* error without displaying */ #define RETURN_QUIET_ERROR(retValue, ...) { \ @@ -116,15 +113,7 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p, { size_t i; for(i = 0; i < p.blockCount; i++) { memset(p.dstBuffers[i], 0xE5, p.dstCapacities[i]); /* warm up and erase result buffer */ - } -#if 0 - /* based on testing these seem to lower accuracy of multiple calls of 1 nbLoops vs 1 call of multiple nbLoops - * (Makes former slower) - */ - UTIL_sleepMilli(5); /* give processor time to other processes */ - UTIL_waitForNextTick(); -#endif - } + } } /* benchmark */ { UTIL_time_t const clockStart = UTIL_getTime(); @@ -146,9 +135,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p, } } } /* for (loopNb = 0; loopNb < nbLoops; loopNb++) */ - { U64 const totalTime = UTIL_clockSpanNano(clockStart); + { PTime const totalTime = UTIL_clockSpanNano(clockStart); BMK_runTime_t rt; - rt.nanoSecPerRun = totalTime / nbLoops; + rt.nanoSecPerRun = (double)totalTime / nbLoops; rt.sumOfReturn = dstSize; return BMK_setValid_runTime(rt); } } @@ -158,9 +147,9 @@ BMK_runOutcome_t BMK_benchFunction(BMK_benchParams_t p, /* ==== Benchmarking any function, providing intermediate results ==== */ struct BMK_timedFnState_s { - U64 timeSpent_ns; - U64 timeBudget_ns; - U64 runBudget_ns; + PTime timeSpent_ns; + PTime timeBudget_ns; + PTime runBudget_ns; BMK_runTime_t fastestRun; unsigned nbLoops; UTIL_time_t coolTime; @@ -174,8 +163,20 @@ BMK_timedFnState_t* BMK_createTimedFnState(unsigned total_ms, unsigned run_ms) return r; } -void BMK_freeTimedFnState(BMK_timedFnState_t* state) { - free(state); +void BMK_freeTimedFnState(BMK_timedFnState_t* state) { free(state); } + +BMK_timedFnState_t* +BMK_initStatic_timedFnState(void* buffer, size_t size, unsigned total_ms, unsigned run_ms) +{ + typedef char check_size[ 2 * (sizeof(BMK_timedFnState_shell) >= sizeof(struct BMK_timedFnState_s)) - 1]; /* static assert : a compilation failure indicates that BMK_timedFnState_shell is not large enough */ + typedef struct { check_size c; BMK_timedFnState_t tfs; } tfs_align; /* force tfs to be aligned at its next best position */ + size_t const tfs_alignment = offsetof(tfs_align, tfs); /* provides the minimal alignment restriction for BMK_timedFnState_t */ + BMK_timedFnState_t* const r = (BMK_timedFnState_t*)buffer; + if (buffer == NULL) return NULL; + if (size < sizeof(struct BMK_timedFnState_s)) return NULL; + if ((size_t)buffer % tfs_alignment) return NULL; /* buffer must be properly aligned */ + BMK_resetTimedFnState(r, total_ms, run_ms); + return r; } void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms, unsigned run_ms) @@ -184,9 +185,9 @@ void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms, if (!run_ms) run_ms = 1; if (run_ms > total_ms) run_ms = total_ms; timedFnState->timeSpent_ns = 0; - timedFnState->timeBudget_ns = (U64)total_ms * TIMELOOP_NANOSEC / 1000; - timedFnState->runBudget_ns = (U64)run_ms * TIMELOOP_NANOSEC / 1000; - timedFnState->fastestRun.nanoSecPerRun = (U64)(-1LL); + timedFnState->timeBudget_ns = (PTime)total_ms * TIMELOOP_NANOSEC / 1000; + timedFnState->runBudget_ns = (PTime)run_ms * TIMELOOP_NANOSEC / 1000; + timedFnState->fastestRun.nanoSecPerRun = (double)TIMELOOP_NANOSEC * 2000000000; /* hopefully large enough : must be larger than any potential measurement */ timedFnState->fastestRun.sumOfReturn = (size_t)(-1LL); timedFnState->nbLoops = 1; timedFnState->coolTime = UTIL_getTime(); @@ -208,37 +209,27 @@ int BMK_isCompleted_TimedFn(const BMK_timedFnState_t* timedFnState) BMK_runOutcome_t BMK_benchTimedFn(BMK_timedFnState_t* cont, BMK_benchParams_t p) { - U64 const runBudget_ns = cont->runBudget_ns; - U64 const runTimeMin_ns = runBudget_ns / 2; + PTime const runBudget_ns = cont->runBudget_ns; + PTime const runTimeMin_ns = runBudget_ns / 2; int completed = 0; BMK_runTime_t bestRunTime = cont->fastestRun; while (!completed) { - BMK_runOutcome_t runResult; - - /* Overheat protection */ - if (UTIL_clockSpanMicro(cont->coolTime) > ACTIVEPERIOD_MICROSEC) { - DEBUGOUTPUT("\rcooling down ... \r"); - UTIL_sleep(COOLPERIOD_SEC); - cont->coolTime = UTIL_getTime(); - } - - /* reinitialize capacity */ - runResult = BMK_benchFunction(p, cont->nbLoops); + BMK_runOutcome_t const runResult = BMK_benchFunction(p, cont->nbLoops); if(!BMK_isSuccessful_runOutcome(runResult)) { /* error : move out */ return runResult; } { BMK_runTime_t const newRunTime = BMK_extract_runTime(runResult); - U64 const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops; + double const loopDuration_ns = newRunTime.nanoSecPerRun * cont->nbLoops; - cont->timeSpent_ns += loopDuration_ns; + cont->timeSpent_ns += (unsigned long long)loopDuration_ns; /* estimate nbLoops for next run to last approximately 1 second */ if (loopDuration_ns > (runBudget_ns / 50)) { - U64 const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun); - cont->nbLoops = (U32)(runBudget_ns / fastestRun_ns) + 1; + double const fastestRun_ns = MIN(bestRunTime.nanoSecPerRun, newRunTime.nanoSecPerRun); + cont->nbLoops = (unsigned)(runBudget_ns / fastestRun_ns) + 1; } else { /* previous run was too short : blindly increase workload by x multiplier */ const unsigned multiplier = 10; diff --git a/programs/benchfn.h b/programs/benchfn.h index 3ca36e3623da..19e056581a5b 100644 --- a/programs/benchfn.h +++ b/programs/benchfn.h @@ -31,7 +31,7 @@ extern "C" { /* BMK_runTime_t: valid result return type */ typedef struct { - unsigned long long nanoSecPerRun; /* time per iteration (over all blocks) */ + double nanoSecPerRun; /* time per iteration (over all blocks) */ size_t sumOfReturn; /* sum of return values */ } BMK_runTime_t; @@ -58,30 +58,31 @@ typedef size_t (*BMK_initFn_t)(void* initPayload); typedef unsigned (*BMK_errorFn_t)(size_t); -/* BMK_benchFunction() parameters are provided through following structure. - * This is preferable for readability, - * as the number of parameters required is pretty large. +/* BMK_benchFunction() parameters are provided via the following structure. + * A structure is preferable for readability, + * as the number of parameters required is fairly large. * No initializer is provided, because it doesn't make sense to provide some "default" : - * all parameters should be specified by the caller */ + * all parameters must be specified by the caller. + * optional parameters are labelled explicitly, and accept value NULL when not used */ typedef struct { - BMK_benchFn_t benchFn; /* the function to benchmark, over the set of blocks */ - void* benchPayload; /* pass custom parameters to benchFn : - * (*benchFn)(srcBuffers[i], srcSizes[i], dstBuffers[i], dstCapacities[i], benchPayload) */ - BMK_initFn_t initFn; /* (*initFn)(initPayload) is run once per run, at the beginning. */ - void* initPayload; /* Both arguments can be NULL, in which case nothing is run. */ - BMK_errorFn_t errorFn; /* errorFn will check each return value of benchFn over each block, to determine if it failed or not. - * errorFn can be NULL, in which case no check is performed. - * errorFn must return 0 when benchFn was successful, and >= 1 if it detects an error. - * Execution is stopped as soon as an error is detected. - * the triggering return value can be retrieved using BMK_extract_errorResult(). */ - size_t blockCount; /* number of blocks to operate benchFn on. - * It's also the size of all array parameters : - * srcBuffers, srcSizes, dstBuffers, dstCapacities, blockResults */ - const void *const * srcBuffers; /* array of buffers to be operated on by benchFn */ - const size_t* srcSizes; /* array of the sizes of srcBuffers buffers */ - void *const * dstBuffers;/* array of buffers to be written into by benchFn */ - const size_t* dstCapacities; /* array of the capacities of dstBuffers buffers */ - size_t* blockResults; /* Optional: store the return value of benchFn for each block. Use NULL if this result is not requested. */ + BMK_benchFn_t benchFn; /* the function to benchmark, over the set of blocks */ + void* benchPayload; /* pass custom parameters to benchFn : + * (*benchFn)(srcBuffers[i], srcSizes[i], dstBuffers[i], dstCapacities[i], benchPayload) */ + BMK_initFn_t initFn; /* (*initFn)(initPayload) is run once per run, at the beginning. */ + void* initPayload; /* Both arguments can be NULL, in which case nothing is run. */ + BMK_errorFn_t errorFn; /* errorFn will check each return value of benchFn over each block, to determine if it failed or not. + * errorFn can be NULL, in which case no check is performed. + * errorFn must return 0 when benchFn was successful, and >= 1 if it detects an error. + * Execution is stopped as soon as an error is detected. + * the triggering return value can be retrieved using BMK_extract_errorResult(). */ + size_t blockCount; /* number of blocks to operate benchFn on. + * It's also the size of all array parameters : + * srcBuffers, srcSizes, dstBuffers, dstCapacities, blockResults */ + const void *const * srcBuffers; /* read-only array of buffers to be operated on by benchFn */ + const size_t* srcSizes; /* read-only array containing sizes of srcBuffers */ + void *const * dstBuffers; /* array of buffers to be written into by benchFn. This array is not optional, it must be provided even if unused by benchfn. */ + const size_t* dstCapacities; /* read-only array containing capacities of dstBuffers. This array must be present. */ + size_t* blockResults; /* Optional: store the return value of benchFn for each block. Use NULL if this result is not requested. */ } BMK_benchParams_t; @@ -159,6 +160,21 @@ void BMK_resetTimedFnState(BMK_timedFnState_t* timedFnState, unsigned total_ms, void BMK_freeTimedFnState(BMK_timedFnState_t* state); +/* BMK_timedFnState_shell and BMK_initStatic_timedFnState() : + * Makes it possible to statically allocate a BMK_timedFnState_t on stack. + * BMK_timedFnState_shell is only there to allocate space, + * never ever access its members. + * BMK_timedFnState_t() actually accepts any buffer. + * It will check if provided buffer is large enough and is correctly aligned, + * and will return NULL if conditions are not respected. + */ +#define BMK_TIMEDFNSTATE_SIZE 64 +typedef union { + char never_access_space[BMK_TIMEDFNSTATE_SIZE]; + long long alignment_enforcer; /* must be aligned on 8-bytes boundaries */ +} BMK_timedFnState_shell; +BMK_timedFnState_t* BMK_initStatic_timedFnState(void* buffer, size_t size, unsigned total_ms, unsigned run_ms); + #endif /* BENCH_FN_H_23876 */ diff --git a/programs/benchzstd.c b/programs/benchzstd.c index 0be74a965047..263dc08887f7 100644 --- a/programs/benchzstd.c +++ b/programs/benchzstd.c @@ -28,6 +28,7 @@ #include #include /* assert */ +#include "timefn.h" /* UTIL_time_t */ #include "benchfn.h" #include "mem.h" #define ZSTD_STATIC_LINKING_ONLY @@ -135,7 +136,8 @@ BMK_advancedParams_t BMK_initAdvancedParams(void) { 0, /* ldmMinMatch */ 0, /* ldmHashLog */ 0, /* ldmBuckSizeLog */ - 0 /* ldmHashRateLog */ + 0, /* ldmHashRateLog */ + ZSTD_lcm_auto /* literalCompressionMode */ }; return res; } @@ -159,9 +161,13 @@ typedef struct { #define MIN(a,b) ((a) < (b) ? (a) : (b)) #define MAX(a,b) ((a) > (b) ? (a) : (b)) -static void BMK_initCCtx(ZSTD_CCtx* ctx, - const void* dictBuffer, size_t dictBufferSize, int cLevel, - const ZSTD_compressionParameters* comprParams, const BMK_advancedParams_t* adv) { +static void +BMK_initCCtx(ZSTD_CCtx* ctx, + const void* dictBuffer, size_t dictBufferSize, + int cLevel, + const ZSTD_compressionParameters* comprParams, + const BMK_advancedParams_t* adv) +{ ZSTD_CCtx_reset(ctx, ZSTD_reset_session_and_parameters); if (adv->nbWorkers==1) { CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_nbWorkers, 0)); @@ -174,12 +180,13 @@ static void BMK_initCCtx(ZSTD_CCtx* ctx, CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmHashLog, adv->ldmHashLog)); CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmBucketSizeLog, adv->ldmBucketSizeLog)); CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_ldmHashRateLog, adv->ldmHashRateLog)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_windowLog, comprParams->windowLog)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_hashLog, comprParams->hashLog)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_chainLog, comprParams->chainLog)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_searchLog, comprParams->searchLog)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_minMatch, comprParams->minMatch)); - CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_targetLength, comprParams->targetLength)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_windowLog, (int)comprParams->windowLog)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_hashLog, (int)comprParams->hashLog)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_chainLog, (int)comprParams->chainLog)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_searchLog, (int)comprParams->searchLog)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_minMatch, (int)comprParams->minMatch)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_targetLength, (int)comprParams->targetLength)); + CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_literalCompressionMode, (int)adv->literalCompressionMode)); CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_strategy, comprParams->strategy)); CHECK_Z(ZSTD_CCtx_loadDictionary(ctx, dictBuffer, dictBufferSize)); } @@ -376,7 +383,7 @@ BMK_benchMemAdvancedNoAlloc( } } - /* warmimg up `compressedBuffer` */ + /* warming up `compressedBuffer` */ if (adv->mode == BMK_decodeOnly) { memcpy(compressedBuffer, srcBuffer, loadedCompressedSize); } else { @@ -444,7 +451,7 @@ BMK_benchMemAdvancedNoAlloc( cSize = cResult.sumOfReturn; ratio = (double)srcSize / cSize; { BMK_benchResult_t newResult; - newResult.cSpeed = ((U64)srcSize * TIMELOOP_NANOSEC / cResult.nanoSecPerRun); + newResult.cSpeed = (U64)((double)srcSize * TIMELOOP_NANOSEC / cResult.nanoSecPerRun); benchResult.cSize = cSize; if (newResult.cSpeed > benchResult.cSpeed) benchResult.cSpeed = newResult.cSpeed; @@ -468,7 +475,7 @@ BMK_benchMemAdvancedNoAlloc( } { BMK_runTime_t const dResult = BMK_extract_runTime(dOutcome); - U64 const newDSpeed = (srcSize * TIMELOOP_NANOSEC / dResult.nanoSecPerRun); + U64 const newDSpeed = (U64)((double)srcSize * TIMELOOP_NANOSEC / dResult.nanoSecPerRun); if (newDSpeed > benchResult.dSpeed) benchResult.dSpeed = newDSpeed; } @@ -505,17 +512,21 @@ BMK_benchMemAdvancedNoAlloc( pos = (U32)(u - bacc); bNb = pos / (128 KB); DISPLAY("(sample %u, block %u, pos %u) \n", segNb, bNb, pos); - if (u>5) { - int n; + { size_t const lowest = (u>5) ? 5 : u; + size_t n; DISPLAY("origin: "); - for (n=-5; n<0; n++) DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]); + for (n=lowest; n>0; n--) + DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u-n]); DISPLAY(" :%02X: ", ((const BYTE*)srcBuffer)[u]); - for (n=1; n<3; n++) DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]); + for (n=1; n<3; n++) + DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]); DISPLAY(" \n"); DISPLAY("decode: "); - for (n=-5; n<0; n++) DISPLAY("%02X ", resultBuffer[u+n]); + for (n=lowest; n>0; n++) + DISPLAY("%02X ", resultBuffer[u-n]); DISPLAY(" :%02X: ", resultBuffer[u]); - for (n=1; n<3; n++) DISPLAY("%02X ", resultBuffer[u+n]); + for (n=1; n<3; n++) + DISPLAY("%02X ", resultBuffer[u+n]); DISPLAY(" \n"); } break; diff --git a/programs/benchzstd.h b/programs/benchzstd.h index 3a8b893e7ee6..2c7627713ee4 100644 --- a/programs/benchzstd.h +++ b/programs/benchzstd.h @@ -105,17 +105,18 @@ typedef enum { } BMK_mode_t; typedef struct { - BMK_mode_t mode; /* 0: all, 1: compress only 2: decode only */ - unsigned nbSeconds; /* default timing is in nbSeconds */ - size_t blockSize; /* Maximum size of each block*/ - unsigned nbWorkers; /* multithreading */ - unsigned realTime; /* real time priority */ - int additionalParam; /* used by python speed benchmark */ - unsigned ldmFlag; /* enables long distance matching */ - unsigned ldmMinMatch; /* below: parameters for long distance matching, see zstd.1.md */ - unsigned ldmHashLog; - unsigned ldmBucketSizeLog; - unsigned ldmHashRateLog; + BMK_mode_t mode; /* 0: all, 1: compress only 2: decode only */ + unsigned nbSeconds; /* default timing is in nbSeconds */ + size_t blockSize; /* Maximum size of each block*/ + int nbWorkers; /* multithreading */ + unsigned realTime; /* real time priority */ + int additionalParam; /* used by python speed benchmark */ + int ldmFlag; /* enables long distance matching */ + int ldmMinMatch; /* below: parameters for long distance matching, see zstd.1.md */ + int ldmHashLog; + int ldmBucketSizeLog; + int ldmHashRateLog; + ZSTD_literalCompressionMode_e literalCompressionMode; } BMK_advancedParams_t; /* returns default parameters used by nonAdvanced functions */ @@ -169,7 +170,7 @@ BMK_benchOutcome_t BMK_syntheticTest( * comprParams - basic compression parameters * dictBuffer - a dictionary if used, null otherwise * dictBufferSize - size of dictBuffer, 0 otherwise - * diplayLevel - see BMK_benchFiles + * displayLevel - see BMK_benchFiles * displayName - name used by display * @return: * a variant, which expresses either an error, or a valid result. diff --git a/programs/dibio.c b/programs/dibio.c index c9d214e754e6..12eb32680859 100644 --- a/programs/dibio.c +++ b/programs/dibio.c @@ -29,6 +29,7 @@ #include /* errno */ #include +#include "timefn.h" /* UTIL_time_t, UTIL_clockSpanMicro, UTIL_getTime */ #include "mem.h" /* read */ #include "error_private.h" #include "dibio.h" diff --git a/programs/fileio.c b/programs/fileio.c index 9fb795ed3f27..7ada5921b123 100644 --- a/programs/fileio.c +++ b/programs/fileio.c @@ -24,13 +24,14 @@ * Includes ***************************************/ #include "platform.h" /* Large Files support, SET_BINARY_MODE */ -#include "util.h" /* UTIL_getFileSize, UTIL_isRegularFile */ +#include "util.h" /* UTIL_getFileSize, UTIL_isRegularFile, UTIL_isSameFile */ #include /* fprintf, fopen, fread, _fileno, stdin, stdout */ #include /* malloc, free */ #include /* strcmp, strlen */ #include #include /* errno */ #include +#include "timefn.h" /* UTIL_getTime, UTIL_clockSpanMicro */ #if defined (_MSC_VER) # include @@ -79,23 +80,29 @@ /*-************************************* * Macros ***************************************/ + +struct FIO_display_prefs_s { + int displayLevel; /* 0 : no display; 1: errors; 2: + result + interaction + warnings; 3: + progression; 4: + information */ + U32 noProgress; +}; + +static FIO_display_prefs_t g_display_prefs = {2, 0}; + #define DISPLAY(...) fprintf(stderr, __VA_ARGS__) #define DISPLAYOUT(...) fprintf(stdout, __VA_ARGS__) -#define DISPLAYLEVEL(l, ...) { if (g_displayLevel>=l) { DISPLAY(__VA_ARGS__); } } -static int g_displayLevel = 2; /* 0 : no display; 1: errors; 2: + result + interaction + warnings; 3: + progression; 4: + information */ -void FIO_setNotificationLevel(unsigned level) { g_displayLevel=level; } +#define DISPLAYLEVEL(l, ...) { if (g_display_prefs.displayLevel>=l) { DISPLAY(__VA_ARGS__); } } static const U64 g_refreshRate = SEC_TO_MICRO / 6; static UTIL_time_t g_displayClock = UTIL_TIME_INITIALIZER; -#define READY_FOR_UPDATE() (!g_noProgress && UTIL_clockSpanMicro(g_displayClock) > g_refreshRate) +#define READY_FOR_UPDATE() (!g_display_prefs.noProgress && UTIL_clockSpanMicro(g_displayClock) > g_refreshRate) #define DELAY_NEXT_UPDATE() { g_displayClock = UTIL_getTime(); } #define DISPLAYUPDATE(l, ...) { \ - if (g_displayLevel>=l && !g_noProgress) { \ - if (READY_FOR_UPDATE() || (g_displayLevel>=4)) { \ + if (g_display_prefs.displayLevel>=l && !g_display_prefs.noProgress) { \ + if (READY_FOR_UPDATE() || (g_display_prefs.displayLevel>=4)) { \ DELAY_NEXT_UPDATE(); \ DISPLAY(__VA_ARGS__); \ - if (g_displayLevel>=4) fflush(stderr); \ + if (g_display_prefs.displayLevel>=4) fflush(stderr); \ } } } #undef MIN /* in case it would be already defined */ @@ -189,7 +196,7 @@ static void ABRThandler(int sig) { const char* name; void* addrlist[MAX_STACK_FRAMES]; char** symbollist; - U32 addrlen, i; + int addrlen, i; switch (sig) { case SIGABRT: name = "SIGABRT"; break; @@ -237,10 +244,13 @@ void FIO_addAbortHandler() ***************************************************************/ #if defined(_MSC_VER) && _MSC_VER >= 1400 # define LONG_SEEK _fseeki64 +# define LONG_TELL _ftelli64 #elif !defined(__64BIT__) && (PLATFORM_POSIX_VERSION >= 200112L) /* No point defining Large file for 64 bit */ # define LONG_SEEK fseeko +# define LONG_TELL ftello #elif defined(__MINGW32__) && !defined(__STRICT_ANSI__) && !defined(__NO_MINGW_LFS) && defined(__MSVCRT__) # define LONG_SEEK fseeko64 +# define LONG_TELL ftello64 #elif defined(_WIN32) && !defined(__DJGPP__) # include static int LONG_SEEK(FILE* file, __int64 offset, int origin) { @@ -261,100 +271,183 @@ void FIO_addAbortHandler() } #else # define LONG_SEEK fseek +# define LONG_TELL ftell #endif /*-************************************* -* Local Parameters - Not thread safe +* Parameters: Typedefs ***************************************/ -static FIO_compressionType_t g_compressionType = FIO_zstdCompression; -void FIO_setCompressionType(FIO_compressionType_t compressionType) { g_compressionType = compressionType; } -static U32 g_overwrite = 0; -void FIO_overwriteMode(void) { g_overwrite = 1; } -static U32 g_sparseFileSupport = ZSTD_SPARSE_DEFAULT; /* 0: no sparse allowed; 1: auto (file yes, stdout no); 2: force sparse */ -void FIO_setSparseWrite(unsigned sparse) { g_sparseFileSupport = sparse; } -static U32 g_dictIDFlag = 1; -void FIO_setDictIDFlag(unsigned dictIDFlag) { g_dictIDFlag = dictIDFlag; } -static U32 g_checksumFlag = 1; -void FIO_setChecksumFlag(unsigned checksumFlag) { g_checksumFlag = checksumFlag; } -static U32 g_removeSrcFile = 0; -void FIO_setRemoveSrcFile(unsigned flag) { g_removeSrcFile = (flag>0); } -static unsigned g_memLimit = 0; -void FIO_setMemLimit(unsigned memLimit) { g_memLimit = memLimit; } -static unsigned g_nbWorkers = 1; -void FIO_setNbWorkers(unsigned nbWorkers) { + +struct FIO_prefs_s { + + /* Algorithm preferences */ + FIO_compressionType_t compressionType; + U32 sparseFileSupport; /* 0: no sparse allowed; 1: auto (file yes, stdout no); 2: force sparse */ + int dictIDFlag; + int checksumFlag; + int blockSize; + int overlapLog; + U32 adaptiveMode; + int rsyncable; + int minAdaptLevel; + int maxAdaptLevel; + int ldmFlag; + int ldmHashLog; + int ldmMinMatch; + int ldmBucketSizeLog; + int ldmHashRateLog; + ZSTD_literalCompressionMode_e literalCompressionMode; + + /* IO preferences */ + U32 removeSrcFile; + U32 overwrite; + + /* Computation resources preferences */ + unsigned memLimit; + int nbWorkers; +}; + + +/*-************************************* +* Parameters: Initialization +***************************************/ + +#define FIO_OVERLAP_LOG_NOTSET 9999 +#define FIO_LDM_PARAM_NOTSET 9999 + + +FIO_prefs_t* FIO_createPreferences(void) +{ + FIO_prefs_t* const ret = (FIO_prefs_t*)malloc(sizeof(FIO_prefs_t)); + if (!ret) EXM_THROW(21, "Allocation error : not enough memory"); + + ret->compressionType = FIO_zstdCompression; + ret->overwrite = 0; + ret->sparseFileSupport = ZSTD_SPARSE_DEFAULT; + ret->dictIDFlag = 1; + ret->checksumFlag = 1; + ret->removeSrcFile = 0; + ret->memLimit = 0; + ret->nbWorkers = 1; + ret->blockSize = 0; + ret->overlapLog = FIO_OVERLAP_LOG_NOTSET; + ret->adaptiveMode = 0; + ret->rsyncable = 0; + ret->minAdaptLevel = -50; /* initializing this value requires a constant, so ZSTD_minCLevel() doesn't work */ + ret->maxAdaptLevel = 22; /* initializing this value requires a constant, so ZSTD_maxCLevel() doesn't work */ + ret->ldmFlag = 0; + ret->ldmHashLog = 0; + ret->ldmMinMatch = 0; + ret->ldmBucketSizeLog = FIO_LDM_PARAM_NOTSET; + ret->ldmHashRateLog = FIO_LDM_PARAM_NOTSET; + ret->literalCompressionMode = ZSTD_lcm_auto; + return ret; +} + +void FIO_freePreferences(FIO_prefs_t* const prefs) +{ + free(prefs); +} + + +/*-************************************* +* Parameters: Display Options +***************************************/ + +void FIO_setNotificationLevel(int level) { g_display_prefs.displayLevel=level; } + +void FIO_setNoProgress(unsigned noProgress) { g_display_prefs.noProgress = noProgress; } + + +/*-************************************* +* Parameters: Setters +***************************************/ + +void FIO_setCompressionType(FIO_prefs_t* const prefs, FIO_compressionType_t compressionType) { prefs->compressionType = compressionType; } + +void FIO_overwriteMode(FIO_prefs_t* const prefs) { prefs->overwrite = 1; } + +void FIO_setSparseWrite(FIO_prefs_t* const prefs, unsigned sparse) { prefs->sparseFileSupport = sparse; } + +void FIO_setDictIDFlag(FIO_prefs_t* const prefs, int dictIDFlag) { prefs->dictIDFlag = dictIDFlag; } + +void FIO_setChecksumFlag(FIO_prefs_t* const prefs, int checksumFlag) { prefs->checksumFlag = checksumFlag; } + +void FIO_setRemoveSrcFile(FIO_prefs_t* const prefs, unsigned flag) { prefs->removeSrcFile = (flag>0); } + +void FIO_setMemLimit(FIO_prefs_t* const prefs, unsigned memLimit) { prefs->memLimit = memLimit; } + +void FIO_setNbWorkers(FIO_prefs_t* const prefs, int nbWorkers) { #ifndef ZSTD_MULTITHREAD if (nbWorkers > 0) DISPLAYLEVEL(2, "Note : multi-threading is disabled \n"); #endif - g_nbWorkers = nbWorkers; + prefs->nbWorkers = nbWorkers; } -static U32 g_blockSize = 0; -void FIO_setBlockSize(unsigned blockSize) { - if (blockSize && g_nbWorkers==0) + +void FIO_setBlockSize(FIO_prefs_t* const prefs, int blockSize) { + if (blockSize && prefs->nbWorkers==0) DISPLAYLEVEL(2, "Setting block size is useless in single-thread mode \n"); - g_blockSize = blockSize; + prefs->blockSize = blockSize; } -#define FIO_OVERLAP_LOG_NOTSET 9999 -static unsigned g_overlapLog = FIO_OVERLAP_LOG_NOTSET; -void FIO_setOverlapLog(unsigned overlapLog){ - if (overlapLog && g_nbWorkers==0) + +void FIO_setOverlapLog(FIO_prefs_t* const prefs, int overlapLog){ + if (overlapLog && prefs->nbWorkers==0) DISPLAYLEVEL(2, "Setting overlapLog is useless in single-thread mode \n"); - g_overlapLog = overlapLog; + prefs->overlapLog = overlapLog; } -static U32 g_adaptiveMode = 0; -void FIO_setAdaptiveMode(unsigned adapt) { - if ((adapt>0) && (g_nbWorkers==0)) + +void FIO_setAdaptiveMode(FIO_prefs_t* const prefs, unsigned adapt) { + if ((adapt>0) && (prefs->nbWorkers==0)) EXM_THROW(1, "Adaptive mode is not compatible with single thread mode \n"); - g_adaptiveMode = adapt; + prefs->adaptiveMode = adapt; } -static U32 g_rsyncable = 0; -void FIO_setRsyncable(unsigned rsyncable) { - if ((rsyncable>0) && (g_nbWorkers==0)) + +void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable) { + if ((rsyncable>0) && (prefs->nbWorkers==0)) EXM_THROW(1, "Rsyncable mode is not compatible with single thread mode \n"); - g_rsyncable = rsyncable; + prefs->rsyncable = rsyncable; } -static int g_minAdaptLevel = -50; /* initializing this value requires a constant, so ZSTD_minCLevel() doesn't work */ -void FIO_setAdaptMin(int minCLevel) + +void FIO_setLiteralCompressionMode( + FIO_prefs_t* const prefs, + ZSTD_literalCompressionMode_e mode) { + prefs->literalCompressionMode = mode; +} + +void FIO_setAdaptMin(FIO_prefs_t* const prefs, int minCLevel) { #ifndef ZSTD_NOCOMPRESS assert(minCLevel >= ZSTD_minCLevel()); #endif - g_minAdaptLevel = minCLevel; + prefs->minAdaptLevel = minCLevel; } -static int g_maxAdaptLevel = 22; /* initializing this value requires a constant, so ZSTD_maxCLevel() doesn't work */ -void FIO_setAdaptMax(int maxCLevel) + +void FIO_setAdaptMax(FIO_prefs_t* const prefs, int maxCLevel) { - g_maxAdaptLevel = maxCLevel; + prefs->maxAdaptLevel = maxCLevel; } -static U32 g_ldmFlag = 0; -void FIO_setLdmFlag(unsigned ldmFlag) { - g_ldmFlag = (ldmFlag>0); -} -static U32 g_ldmHashLog = 0; -void FIO_setLdmHashLog(unsigned ldmHashLog) { - g_ldmHashLog = ldmHashLog; -} -static U32 g_ldmMinMatch = 0; -void FIO_setLdmMinMatch(unsigned ldmMinMatch) { - g_ldmMinMatch = ldmMinMatch; +void FIO_setLdmFlag(FIO_prefs_t* const prefs, unsigned ldmFlag) { + prefs->ldmFlag = (ldmFlag>0); } -#define FIO_LDM_PARAM_NOTSET 9999 -static U32 g_ldmBucketSizeLog = FIO_LDM_PARAM_NOTSET; -void FIO_setLdmBucketSizeLog(unsigned ldmBucketSizeLog) { - g_ldmBucketSizeLog = ldmBucketSizeLog; +void FIO_setLdmHashLog(FIO_prefs_t* const prefs, int ldmHashLog) { + prefs->ldmHashLog = ldmHashLog; } -static U32 g_ldmHashRateLog = FIO_LDM_PARAM_NOTSET; -void FIO_setLdmHashRateLog(unsigned ldmHashRateLog) { - g_ldmHashRateLog = ldmHashRateLog; -} -static U32 g_noProgress = 0; -void FIO_setNoProgress(unsigned noProgress) { - g_noProgress = noProgress; +void FIO_setLdmMinMatch(FIO_prefs_t* const prefs, int ldmMinMatch) { + prefs->ldmMinMatch = ldmMinMatch; } +void FIO_setLdmBucketSizeLog(FIO_prefs_t* const prefs, int ldmBucketSizeLog) { + prefs->ldmBucketSizeLog = ldmBucketSizeLog; +} + + +void FIO_setLdmHashRateLog(FIO_prefs_t* const prefs, int ldmHashRateLog) { + prefs->ldmHashRateLog = ldmHashRateLog; +} /*-************************************* @@ -410,45 +503,27 @@ static FILE* FIO_openSrcFile(const char* srcFileName) /** FIO_openDstFile() : * condition : `dstFileName` must be non-NULL. * @result : FILE* to `dstFileName`, or NULL if it fails */ -static FILE* FIO_openDstFile(const char* srcFileName, const char* dstFileName) +static FILE* FIO_openDstFile(FIO_prefs_t* const prefs, const char* srcFileName, const char* dstFileName) { assert(dstFileName != NULL); if (!strcmp (dstFileName, stdoutmark)) { DISPLAYLEVEL(4,"Using stdout for output \n"); SET_BINARY_MODE(stdout); - if (g_sparseFileSupport == 1) { - g_sparseFileSupport = 0; + if (prefs->sparseFileSupport == 1) { + prefs->sparseFileSupport = 0; DISPLAYLEVEL(4, "Sparse File Support is automatically disabled on stdout ; try --sparse \n"); } return stdout; } - /* ensure dst is not the same file as src */ - if (srcFileName != NULL) { -#ifdef _MSC_VER - /* note : Visual does not support file identification by inode. - * The following work-around is limited to detecting exact name repetition only, - * aka `filename` is considered different from `subdir/../filename` */ - if (!strcmp(srcFileName, dstFileName)) { - DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n"); - return NULL; - } -#else - stat_t srcStat; - stat_t dstStat; - if (UTIL_getFileStat(srcFileName, &srcStat) - && UTIL_getFileStat(dstFileName, &dstStat)) { - if (srcStat.st_dev == dstStat.st_dev - && srcStat.st_ino == dstStat.st_ino) { - DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n"); - return NULL; - } - } -#endif + /* ensure dst is not the same as src */ + if (srcFileName != NULL && UTIL_isSameFile(srcFileName, dstFileName)) { + DISPLAYLEVEL(1, "zstd: Refusing to open an output file which will overwrite the input file \n"); + return NULL; } - if (g_sparseFileSupport == 1) { - g_sparseFileSupport = ZSTD_SPARSE_DEFAULT; + if (prefs->sparseFileSupport == 1) { + prefs->sparseFileSupport = ZSTD_SPARSE_DEFAULT; } if (UTIL_isRegularFile(dstFileName)) { @@ -460,8 +535,8 @@ static FILE* FIO_openDstFile(const char* srcFileName, const char* dstFileName) } if (fCheck != NULL) { /* dst file exists, authorization prompt */ fclose(fCheck); - if (!g_overwrite) { - if (g_displayLevel <= 1) { + if (!prefs->overwrite) { + if (g_display_prefs.displayLevel <= 1) { /* No interaction possible */ DISPLAY("zstd: %s already exists; not overwritten \n", dstFileName); @@ -536,10 +611,12 @@ typedef struct { size_t srcBufferSize; void* dstBuffer; size_t dstBufferSize; + const char* dictFileName; ZSTD_CStream* cctx; } cRess_t; -static cRess_t FIO_createCResources(const char* dictFileName, int cLevel, +static cRess_t FIO_createCResources(FIO_prefs_t* const prefs, + const char* dictFileName, int cLevel, U64 srcSize, ZSTD_compressionParameters comprParams) { cRess_t ress; @@ -562,43 +639,45 @@ static cRess_t FIO_createCResources(const char* dictFileName, int cLevel, size_t const dictBuffSize = FIO_createDictBuffer(&dictBuffer, dictFileName); /* works with dictFileName==NULL */ if (dictFileName && (dictBuffer==NULL)) EXM_THROW(32, "allocation error : can't create dictBuffer"); + ress.dictFileName = dictFileName; - if (g_adaptiveMode && !g_ldmFlag && !comprParams.windowLog) + if (prefs->adaptiveMode && !prefs->ldmFlag && !comprParams.windowLog) comprParams.windowLog = ADAPT_WINDOWLOG_DEFAULT; CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_contentSizeFlag, 1) ); /* always enable content size when available (note: supposed to be default) */ - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_dictIDFlag, g_dictIDFlag) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, g_checksumFlag) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_dictIDFlag, prefs->dictIDFlag) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, prefs->checksumFlag) ); /* compression level */ CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, cLevel) ); /* long distance matching */ - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_enableLongDistanceMatching, g_ldmFlag) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashLog, g_ldmHashLog) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmMinMatch, g_ldmMinMatch) ); - if (g_ldmBucketSizeLog != FIO_LDM_PARAM_NOTSET) { - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmBucketSizeLog, g_ldmBucketSizeLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_enableLongDistanceMatching, prefs->ldmFlag) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashLog, prefs->ldmHashLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmMinMatch, prefs->ldmMinMatch) ); + if (prefs->ldmBucketSizeLog != FIO_LDM_PARAM_NOTSET) { + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmBucketSizeLog, prefs->ldmBucketSizeLog) ); } - if (g_ldmHashRateLog != FIO_LDM_PARAM_NOTSET) { - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashRateLog, g_ldmHashRateLog) ); + if (prefs->ldmHashRateLog != FIO_LDM_PARAM_NOTSET) { + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_ldmHashRateLog, prefs->ldmHashRateLog) ); } /* compression parameters */ - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_windowLog, comprParams.windowLog) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_chainLog, comprParams.chainLog) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_hashLog, comprParams.hashLog) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_searchLog, comprParams.searchLog) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_minMatch, comprParams.minMatch) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetLength, comprParams.targetLength) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_windowLog, (int)comprParams.windowLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_chainLog, (int)comprParams.chainLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_hashLog, (int)comprParams.hashLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_searchLog, (int)comprParams.searchLog) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_minMatch, (int)comprParams.minMatch) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetLength, (int)comprParams.targetLength) ); CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_strategy, comprParams.strategy) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_literalCompressionMode, (int)prefs->literalCompressionMode) ); /* multi-threading */ #ifdef ZSTD_MULTITHREAD - DISPLAYLEVEL(5,"set nb workers = %u \n", g_nbWorkers); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_nbWorkers, g_nbWorkers) ); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_jobSize, g_blockSize) ); - if (g_overlapLog != FIO_OVERLAP_LOG_NOTSET) { - DISPLAYLEVEL(3,"set overlapLog = %u \n", g_overlapLog); - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_overlapLog, g_overlapLog) ); + DISPLAYLEVEL(5,"set nb workers = %u \n", prefs->nbWorkers); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_nbWorkers, prefs->nbWorkers) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_jobSize, prefs->blockSize) ); + if (prefs->overlapLog != FIO_OVERLAP_LOG_NOTSET) { + DISPLAYLEVEL(3,"set overlapLog = %u \n", prefs->overlapLog); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_overlapLog, prefs->overlapLog) ); } - CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_rsyncable, g_rsyncable) ); + CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_rsyncable, prefs->rsyncable) ); #endif /* dictionary */ CHECK( ZSTD_CCtx_setPledgedSrcSize(ress.cctx, srcSize) ); /* set the value temporarily for dictionary loading, to adapt compression parameters */ @@ -774,15 +853,19 @@ FIO_compressLzmaFrame(cRess_t* ress, #endif #ifdef ZSTD_LZ4COMPRESS + #if LZ4_VERSION_NUMBER <= 10600 #define LZ4F_blockLinked blockLinked #define LZ4F_max64KB max64KB #endif + static int FIO_LZ4_GetBlockSize_FromBlockId (int id) { return (1 << (8 + (2 * id))); } + static unsigned long long FIO_compressLz4Frame(cRess_t* ress, const char* srcFileName, U64 const srcFileSize, - int compressionLevel, U64* readsize) + int compressionLevel, int checksumFlag, + U64* readsize) { const size_t blockSize = FIO_LZ4_GetBlockSize_FromBlockId(LZ4F_max64KB); unsigned long long inFileSize = 0, outFileSize = 0; @@ -802,7 +885,7 @@ FIO_compressLz4Frame(cRess_t* ress, prefs.compressionLevel = compressionLevel; prefs.frameInfo.blockMode = LZ4F_blockLinked; prefs.frameInfo.blockSizeID = LZ4F_max64KB; - prefs.frameInfo.contentChecksumFlag = (contentChecksum_t)g_checksumFlag; + prefs.frameInfo.contentChecksumFlag = (contentChecksum_t)checksumFlag; #if LZ4_VERSION_NUMBER >= 10600 prefs.frameInfo.contentSize = (srcFileSize==UTIL_FILESIZE_UNKNOWN) ? 0 : srcFileSize; #endif @@ -876,7 +959,8 @@ FIO_compressLz4Frame(cRess_t* ress, static unsigned long long -FIO_compressZstdFrame(const cRess_t* ressPtr, +FIO_compressZstdFrame(FIO_prefs_t* const prefs, + const cRess_t* ressPtr, const char* srcFileName, U64 fileSize, int compressionLevel, U64* readsize) { @@ -947,7 +1031,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, double const cShare = (double)zfp.produced / (zfp.consumed + !zfp.consumed/*avoid div0*/) * 100; /* display progress notifications */ - if (g_displayLevel >= 3) { + if (g_display_prefs.displayLevel >= 3) { DISPLAYUPDATE(3, "\r(L%i) Buffered :%4u MB - Consumed :%4u MB - Compressed :%4u MB => %.2f%% ", compressionLevel, (unsigned)((zfp.ingested - zfp.consumed) >> 20), @@ -963,7 +1047,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, } /* adaptive mode : statistics measurement and speed correction */ - if (g_adaptiveMode) { + if (prefs->adaptiveMode) { /* check output speed */ if (zfp.currentJobID > 1) { /* only possible if nbWorkers >= 1 */ @@ -971,12 +1055,12 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, unsigned long long newlyProduced = zfp.produced - previous_zfp_update.produced; unsigned long long newlyFlushed = zfp.flushed - previous_zfp_update.flushed; assert(zfp.produced >= previous_zfp_update.produced); - assert(g_nbWorkers >= 1); + assert(prefs->nbWorkers >= 1); /* test if compression is blocked * either because output is slow and all buffers are full * or because input is slow and no job can start while waiting for at least one buffer to be filled. - * note : excluse starting part, since currentJobID > 1 */ + * note : exclude starting part, since currentJobID > 1 */ if ( (zfp.consumed == previous_zfp_update.consumed) /* no data compressed : no data available, or no more buffer to compress to, OR compression is really slow (compression of a single block is slower than update rate)*/ && (zfp.nbActiveWorkers == 0) /* confirmed : no compression ongoing */ ) { @@ -1000,7 +1084,7 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, DISPLAYLEVEL(6, "compression level adaptation check \n") /* check input speed */ - if (zfp.currentJobID > g_nbWorkers+1) { /* warm up period, to fill all workers */ + if (zfp.currentJobID > (unsigned)(prefs->nbWorkers+1)) { /* warm up period, to fill all workers */ if (inputBlocked <= 0) { DISPLAYLEVEL(6, "input is never blocked => input is slower than ingestion \n"); speedChange = slower; @@ -1032,14 +1116,14 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, DISPLAYLEVEL(6, "slower speed , higher compression \n") compressionLevel ++; if (compressionLevel > ZSTD_maxCLevel()) compressionLevel = ZSTD_maxCLevel(); - if (compressionLevel > g_maxAdaptLevel) compressionLevel = g_maxAdaptLevel; + if (compressionLevel > prefs->maxAdaptLevel) compressionLevel = prefs->maxAdaptLevel; compressionLevel += (compressionLevel == 0); /* skip 0 */ ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, compressionLevel); } if (speedChange == faster) { DISPLAYLEVEL(6, "faster speed , lighter compression \n") compressionLevel --; - if (compressionLevel < g_minAdaptLevel) compressionLevel = g_minAdaptLevel; + if (compressionLevel < prefs->minAdaptLevel) compressionLevel = prefs->minAdaptLevel; compressionLevel -= (compressionLevel == 0); /* skip 0 */ ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, compressionLevel); } @@ -1069,7 +1153,8 @@ FIO_compressZstdFrame(const cRess_t* ressPtr, * 1 : missing or pb opening srcFileName */ static int -FIO_compressFilename_internal(cRess_t ress, +FIO_compressFilename_internal(FIO_prefs_t* const prefs, + cRess_t ress, const char* dstFileName, const char* srcFileName, int compressionLevel) { @@ -1079,10 +1164,10 @@ FIO_compressFilename_internal(cRess_t ress, DISPLAYLEVEL(5, "%s: %u bytes \n", srcFileName, (unsigned)fileSize); /* compression format selection */ - switch (g_compressionType) { + switch (prefs->compressionType) { default: case FIO_zstdCompression: - compressedfilesize = FIO_compressZstdFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize); + compressedfilesize = FIO_compressZstdFrame(prefs, &ress, srcFileName, fileSize, compressionLevel, &readsize); break; case FIO_gzipCompression: @@ -1098,7 +1183,7 @@ FIO_compressFilename_internal(cRess_t ress, case FIO_xzCompression: case FIO_lzmaCompression: #ifdef ZSTD_LZMACOMPRESS - compressedfilesize = FIO_compressLzmaFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize, g_compressionType==FIO_lzmaCompression); + compressedfilesize = FIO_compressLzmaFrame(&ress, srcFileName, fileSize, compressionLevel, &readsize, prefs->compressionType==FIO_lzmaCompression); #else (void)compressionLevel; EXM_THROW(20, "zstd: %s: file cannot be compressed as xz/lzma (zstd compiled without ZSTD_LZMACOMPRESS) -- ignored \n", @@ -1108,7 +1193,7 @@ FIO_compressFilename_internal(cRess_t ress, case FIO_lz4Compression: #ifdef ZSTD_LZ4COMPRESS - compressedfilesize = FIO_compressLz4Frame(&ress, srcFileName, fileSize, compressionLevel, &readsize); + compressedfilesize = FIO_compressLz4Frame(&ress, srcFileName, fileSize, compressionLevel, prefs->checksumFlag, &readsize); #else (void)compressionLevel; EXM_THROW(20, "zstd: %s: file cannot be compressed as lz4 (zstd compiled without ZSTD_LZ4COMPRESS) -- ignored \n", @@ -1138,7 +1223,8 @@ FIO_compressFilename_internal(cRess_t ress, * @return : 0 : compression completed correctly, * 1 : pb */ -static int FIO_compressFilename_dstFile(cRess_t ress, +static int FIO_compressFilename_dstFile(FIO_prefs_t* const prefs, + cRess_t ress, const char* dstFileName, const char* srcFileName, int compressionLevel) @@ -1153,7 +1239,7 @@ static int FIO_compressFilename_dstFile(cRess_t ress, if (ress.dstFile == NULL) { closeDstFile = 1; DISPLAYLEVEL(6, "FIO_compressFilename_dstFile: opening dst: %s", dstFileName); - ress.dstFile = FIO_openDstFile(srcFileName, dstFileName); + ress.dstFile = FIO_openDstFile(prefs, srcFileName, dstFileName); if (ress.dstFile==NULL) return 1; /* could not open dstFileName */ /* Must only be added after FIO_openDstFile() succeeds. * Otherwise we may delete the destination file if it already exists, @@ -1166,7 +1252,7 @@ static int FIO_compressFilename_dstFile(cRess_t ress, transfer_permissions = 1; } - result = FIO_compressFilename_internal(ress, dstFileName, srcFileName, compressionLevel); + result = FIO_compressFilename_internal(prefs, ress, dstFileName, srcFileName, compressionLevel); if (closeDstFile) { FILE* const dstFile = ress.dstFile; @@ -1199,27 +1285,34 @@ static int FIO_compressFilename_dstFile(cRess_t ress, * 1 : missing or pb opening srcFileName */ static int -FIO_compressFilename_srcFile(cRess_t ress, +FIO_compressFilename_srcFile(FIO_prefs_t* const prefs, + cRess_t ress, const char* dstFileName, const char* srcFileName, int compressionLevel) { int result; - /* File check */ + /* ensure src is not a directory */ if (UTIL_isDirectory(srcFileName)) { DISPLAYLEVEL(1, "zstd: %s is a directory -- ignored \n", srcFileName); return 1; } + /* ensure src is not the same as dict (if present) */ + if (ress.dictFileName != NULL && UTIL_isSameFile(srcFileName, ress.dictFileName)) { + DISPLAYLEVEL(1, "zstd: cannot use %s as an input file and dictionary \n", srcFileName); + return 1; + } + ress.srcFile = FIO_openSrcFile(srcFileName); if (ress.srcFile == NULL) return 1; /* srcFile could not be opened */ - result = FIO_compressFilename_dstFile(ress, dstFileName, srcFileName, compressionLevel); + result = FIO_compressFilename_dstFile(prefs, ress, dstFileName, srcFileName, compressionLevel); fclose(ress.srcFile); ress.srcFile = NULL; - if ( g_removeSrcFile /* --rm */ + if ( prefs->removeSrcFile /* --rm */ && result == 0 /* success */ && strcmp(srcFileName, stdinmark) /* exception : don't erase stdin */ ) { @@ -1234,7 +1327,8 @@ FIO_compressFilename_srcFile(cRess_t ress, } -int FIO_compressFilename(const char* dstFileName, const char* srcFileName, +int FIO_compressFilename(FIO_prefs_t* const prefs, + const char* dstFileName, const char* srcFileName, const char* dictFileName, int compressionLevel, ZSTD_compressionParameters comprParams) { @@ -1242,8 +1336,8 @@ int FIO_compressFilename(const char* dstFileName, const char* srcFileName, U64 const fileSize = UTIL_getFileSize(srcFileName); U64 const srcSize = (fileSize == UTIL_FILESIZE_UNKNOWN) ? ZSTD_CONTENTSIZE_UNKNOWN : fileSize; - cRess_t const ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, comprParams); - int const result = FIO_compressFilename_srcFile(ress, dstFileName, srcFileName, compressionLevel); + cRess_t const ress = FIO_createCResources(prefs, dictFileName, compressionLevel, srcSize, comprParams); + int const result = FIO_compressFilename_srcFile(prefs, ress, dstFileName, srcFileName, compressionLevel); double const seconds = (double)(clock() - start) / CLOCKS_PER_SEC; DISPLAYLEVEL(4, "Completed in %.2f sec \n", seconds); @@ -1288,7 +1382,8 @@ FIO_determineCompressedName(const char* srcFileName, const char* suffix) * into one destination (outFileName) * or into one file each (outFileName == NULL, but suffix != NULL). */ -int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFiles, +int FIO_compressMultipleFilenames(FIO_prefs_t* const prefs, + const char** inFileNamesTable, unsigned nbFiles, const char* outFileName, const char* suffix, const char* dictFileName, int compressionLevel, ZSTD_compressionParameters comprParams) @@ -1297,19 +1392,19 @@ int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFile U64 const firstFileSize = UTIL_getFileSize(inFileNamesTable[0]); U64 const firstSrcSize = (firstFileSize == UTIL_FILESIZE_UNKNOWN) ? ZSTD_CONTENTSIZE_UNKNOWN : firstFileSize; U64 const srcSize = (nbFiles != 1) ? ZSTD_CONTENTSIZE_UNKNOWN : firstSrcSize ; - cRess_t ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, comprParams); + cRess_t ress = FIO_createCResources(prefs, dictFileName, compressionLevel, srcSize, comprParams); /* init */ assert(outFileName != NULL || suffix != NULL); if (outFileName != NULL) { /* output into a single destination (stdout typically) */ - ress.dstFile = FIO_openDstFile(NULL, outFileName); + ress.dstFile = FIO_openDstFile(prefs, NULL, outFileName); if (ress.dstFile == NULL) { /* could not open outFileName */ error = 1; } else { unsigned u; for (u=0; u memLimit) ); ress.srcBufferSize = ZSTD_DStreamInSize(); ress.srcBuffer = malloc(ress.srcBufferSize); ress.dstBufferSize = ZSTD_DStreamOutSize(); @@ -1383,7 +1478,7 @@ static void FIO_freeDResources(dRess_t ress) /** FIO_fwriteSparse() : * @return : storedSkips, to be provided to next call to FIO_fwriteSparse() of LZ4IO_fwriteSparseEnd() */ -static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSize, unsigned storedSkips) +static unsigned FIO_fwriteSparse(FIO_prefs_t* const prefs, FILE* file, const void* buffer, size_t bufferSize, unsigned storedSkips) { const size_t* const bufferT = (const size_t*)buffer; /* Buffer is supposed malloc'ed, hence aligned on size_t */ size_t bufferSizeT = bufferSize / sizeof(size_t); @@ -1391,7 +1486,7 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi const size_t* ptrT = bufferT; static const size_t segmentSizeT = (32 KB) / sizeof(size_t); /* 0-test re-attempted every 32 KB */ - if (!g_sparseFileSupport) { /* normal write */ + if (!prefs->sparseFileSupport) { /* normal write */ size_t const sizeCheck = fwrite(buffer, 1, bufferSize, file); if (sizeCheck != bufferSize) EXM_THROW(70, "Write error : %s (cannot write decoded block)", @@ -1444,7 +1539,7 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi if (seekResult) EXM_THROW(74, "Sparse skip error ; try --no-sparse"); storedSkips = 0; - { size_t const sizeCheck = fwrite(restPtr, 1, restEnd - restPtr, file); + { size_t const sizeCheck = fwrite(restPtr, 1, (size_t)(restEnd - restPtr), file); if (sizeCheck != (size_t)(restEnd - restPtr)) EXM_THROW(75, "Write error : cannot write decoded end of block"); } } } } @@ -1452,10 +1547,12 @@ static unsigned FIO_fwriteSparse(FILE* file, const void* buffer, size_t bufferSi return storedSkips; } -static void FIO_fwriteSparseEnd(FILE* file, unsigned storedSkips) +static void +FIO_fwriteSparseEnd(FIO_prefs_t* const prefs, FILE* file, unsigned storedSkips) { if (storedSkips>0) { - assert(g_sparseFileSupport > 0); /* storedSkips>0 implies sparse support is enabled */ + assert(prefs->sparseFileSupport > 0); /* storedSkips>0 implies sparse support is enabled */ + (void)prefs; /* assert can be disabled, in which case prefs becomes unused */ if (LONG_SEEK(file, storedSkips-1, SEEK_CUR) != 0) EXM_THROW(69, "Final skip error (sparse file support)"); /* last zero must be explicitly written, @@ -1469,7 +1566,10 @@ static void FIO_fwriteSparseEnd(FILE* file, unsigned storedSkips) /** FIO_passThrough() : just copy input into output, for compatibility with gzip -df mode @return : 0 (no error) */ -static unsigned FIO_passThrough(FILE* foutput, FILE* finput, void* buffer, size_t bufferSize, size_t alreadyLoaded) +static int FIO_passThrough(FIO_prefs_t* const prefs, + FILE* foutput, FILE* finput, + void* buffer, size_t bufferSize, + size_t alreadyLoaded) { size_t const blockSize = MIN(64 KB, bufferSize); size_t readFromInput = 1; @@ -1484,10 +1584,10 @@ static unsigned FIO_passThrough(FILE* foutput, FILE* finput, void* buffer, size_ while (readFromInput) { readFromInput = fread(buffer, 1, blockSize, finput); - storedSkips = FIO_fwriteSparse(foutput, buffer, readFromInput, storedSkips); + storedSkips = FIO_fwriteSparse(prefs, foutput, buffer, readFromInput, storedSkips); } - FIO_fwriteSparseEnd(foutput, storedSkips); + FIO_fwriteSparseEnd(prefs, foutput, storedSkips); return 0; } @@ -1506,7 +1606,7 @@ static unsigned FIO_highbit64(unsigned long long v) /* FIO_zstdErrorHelp() : * detailed error message when requested window size is too large */ -static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName) +static void FIO_zstdErrorHelp(FIO_prefs_t* const prefs, dRess_t* ress, size_t err, char const* srcFileName) { ZSTD_frameHeader header; @@ -1519,9 +1619,9 @@ static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName if (err == 0) { unsigned long long const windowSize = header.windowSize; unsigned const windowLog = FIO_highbit64(windowSize) + ((windowSize & (windowSize - 1)) != 0); - assert(g_memLimit > 0); + assert(prefs->memLimit > 0); DISPLAYLEVEL(1, "%s : Window size larger than maximum : %llu > %u\n", - srcFileName, windowSize, g_memLimit); + srcFileName, windowSize, prefs->memLimit); if (windowLog <= ZSTD_WINDOWLOG_MAX) { unsigned const windowMB = (unsigned)((windowSize >> 20) + ((windowSize & ((1 MB) - 1)) != 0)); assert(windowSize < (U64)(1ULL << 52)); /* ensure now overflow for windowMB */ @@ -1538,7 +1638,9 @@ static void FIO_zstdErrorHelp(dRess_t* ress, size_t err, char const* srcFileName * @return : size of decoded zstd frame, or an error code */ #define FIO_ERROR_FRAME_DECODING ((unsigned long long)(-2)) -static unsigned long long FIO_decompressZstdFrame(dRess_t* ress, +static unsigned long long FIO_decompressZstdFrame( + FIO_prefs_t* const prefs, + dRess_t* ress, FILE* finput, const char* srcFileName, U64 alreadyDecoded) @@ -1567,12 +1669,12 @@ static unsigned long long FIO_decompressZstdFrame(dRess_t* ress, if (ZSTD_isError(readSizeHint)) { DISPLAYLEVEL(1, "%s : Decoding error (36) : %s \n", srcFileName, ZSTD_getErrorName(readSizeHint)); - FIO_zstdErrorHelp(ress, readSizeHint, srcFileName); + FIO_zstdErrorHelp(prefs, ress, readSizeHint, srcFileName); return FIO_ERROR_FRAME_DECODING; } /* Write block */ - storedSkips = FIO_fwriteSparse(ress->dstFile, ress->dstBuffer, outBuff.pos, storedSkips); + storedSkips = FIO_fwriteSparse(prefs, ress->dstFile, ress->dstBuffer, outBuff.pos, storedSkips); frameSize += outBuff.pos; DISPLAYUPDATE(2, "\r%-20.20s : %u MB... ", srcFileName, (unsigned)((alreadyDecoded+frameSize)>>20) ); @@ -1603,7 +1705,7 @@ static unsigned long long FIO_decompressZstdFrame(dRess_t* ress, ress->srcBufferLoaded += readSize; } } } - FIO_fwriteSparseEnd(ress->dstFile, storedSkips); + FIO_fwriteSparseEnd(prefs, ress->dstFile, storedSkips); return frameSize; } @@ -1834,7 +1936,7 @@ static unsigned long long FIO_decompressLz4Frame(dRess_t* ress, * @return : 0 : OK * 1 : error */ -static int FIO_decompressFrames(dRess_t ress, FILE* srcFile, +static int FIO_decompressFrames(FIO_prefs_t* const prefs, dRess_t ress, FILE* srcFile, const char* dstFileName, const char* srcFileName) { unsigned readSomething = 0; @@ -1862,7 +1964,7 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile, return 1; } if (ZSTD_isFrame(buf, ress.srcBufferLoaded)) { - unsigned long long const frameSize = FIO_decompressZstdFrame(&ress, srcFile, srcFileName, filesize); + unsigned long long const frameSize = FIO_decompressZstdFrame(prefs, &ress, srcFile, srcFileName, filesize); if (frameSize == FIO_ERROR_FRAME_DECODING) return 1; filesize += frameSize; } else if (buf[0] == 31 && buf[1] == 139) { /* gz magic number */ @@ -1893,9 +1995,11 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile, DISPLAYLEVEL(1, "zstd: %s: lz4 file cannot be uncompressed (zstd compiled without HAVE_LZ4) -- ignored \n", srcFileName); return 1; #endif - } else if ((g_overwrite) && !strcmp (dstFileName, stdoutmark)) { /* pass-through mode */ - return FIO_passThrough(ress.dstFile, srcFile, - ress.srcBuffer, ress.srcBufferSize, ress.srcBufferLoaded); + } else if ((prefs->overwrite) && !strcmp (dstFileName, stdoutmark)) { /* pass-through mode */ + return FIO_passThrough(prefs, + ress.dstFile, srcFile, + ress.srcBuffer, ress.srcBufferSize, + ress.srcBufferLoaded); } else { DISPLAYLEVEL(1, "zstd: %s: unsupported format \n", srcFileName); return 1; @@ -1915,7 +2019,8 @@ static int FIO_decompressFrames(dRess_t ress, FILE* srcFile, @return : 0 : OK 1 : operation aborted */ -static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile, +static int FIO_decompressDstFile(FIO_prefs_t* const prefs, + dRess_t ress, FILE* srcFile, const char* dstFileName, const char* srcFileName) { int result; @@ -1926,7 +2031,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile, if (ress.dstFile == NULL) { releaseDstFile = 1; - ress.dstFile = FIO_openDstFile(srcFileName, dstFileName); + ress.dstFile = FIO_openDstFile(prefs, srcFileName, dstFileName); if (ress.dstFile==0) return 1; /* Must only be added after FIO_openDstFile() succeeds. @@ -1941,7 +2046,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile, } - result = FIO_decompressFrames(ress, srcFile, dstFileName, srcFileName); + result = FIO_decompressFrames(prefs, ress, srcFile, dstFileName, srcFileName); if (releaseDstFile) { FILE* const dstFile = ress.dstFile; @@ -1974,7 +2079,7 @@ static int FIO_decompressDstFile(dRess_t ress, FILE* srcFile, @return : 0 : OK 1 : error */ -static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const char* srcFileName) +static int FIO_decompressSrcFile(FIO_prefs_t* const prefs, dRess_t ress, const char* dstFileName, const char* srcFileName) { FILE* srcFile; int result; @@ -1988,14 +2093,14 @@ static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const ch if (srcFile==NULL) return 1; ress.srcBufferLoaded = 0; - result = FIO_decompressDstFile(ress, srcFile, dstFileName, srcFileName); + result = FIO_decompressDstFile(prefs, ress, srcFile, dstFileName, srcFileName); /* Close file */ if (fclose(srcFile)) { DISPLAYLEVEL(1, "zstd: %s: %s \n", srcFileName, strerror(errno)); /* error should not happen */ return 1; } - if ( g_removeSrcFile /* --rm */ + if ( prefs->removeSrcFile /* --rm */ && (result==0) /* decompression successful */ && strcmp(srcFileName, stdinmark) ) /* not stdin */ { /* We must clear the handler, since after this point calling it would @@ -2012,12 +2117,13 @@ static int FIO_decompressSrcFile(dRess_t ress, const char* dstFileName, const ch -int FIO_decompressFilename(const char* dstFileName, const char* srcFileName, +int FIO_decompressFilename(FIO_prefs_t* const prefs, + const char* dstFileName, const char* srcFileName, const char* dictFileName) { - dRess_t const ress = FIO_createDResources(dictFileName); + dRess_t const ress = FIO_createDResources(prefs, dictFileName); - int const decodingError = FIO_decompressSrcFile(ress, dstFileName, srcFileName); + int const decodingError = FIO_decompressSrcFile(prefs, ress, dstFileName, srcFileName); FIO_freeDResources(ress); return decodingError; @@ -2094,19 +2200,20 @@ FIO_determineDstName(const char* srcFileName) int -FIO_decompressMultipleFilenames(const char* srcNamesTable[], unsigned nbFiles, +FIO_decompressMultipleFilenames(FIO_prefs_t* const prefs, + const char* srcNamesTable[], unsigned nbFiles, const char* outFileName, const char* dictFileName) { int error = 0; - dRess_t ress = FIO_createDResources(dictFileName); + dRess_t ress = FIO_createDResources(prefs, dictFileName); if (outFileName) { unsigned u; - ress.dstFile = FIO_openDstFile(NULL, outFileName); + ress.dstFile = FIO_openDstFile(prefs, NULL, outFileName); if (ress.dstFile == 0) EXM_THROW(71, "cannot open %s", outFileName); for (u=0; u compressedSize > 0) && (info->compressedSize != UTIL_FILESIZE_UNKNOWN) ) { + unsigned long long file_position = (unsigned long long) LONG_TELL(srcFile); + unsigned long long file_size = (unsigned long long) info->compressedSize; + ERROR_IF(file_position != file_size, info_truncated_input, + "Error: seeked to position %llu, which is beyond file size of %llu\n", + file_position, + file_size); break; /* correct end of file => success */ } ERROR_IF(feof(srcFile), info_not_zstd, "Error: reached end of file with incomplete frame"); @@ -2332,20 +2451,28 @@ FIO_listFile(fileInfo_t* total, const char* inFileName, int displayLevel) fileInfo_t info; memset(&info, 0, sizeof(info)); { InfoError const error = getFileInfo(&info, inFileName); - if (error == info_frame_error) { - /* display error, but provide output */ - DISPLAYLEVEL(1, "Error while parsing %s \n", inFileName); - } - else if (error == info_not_zstd) { - DISPLAYOUT("File %s not compressed by zstd \n", inFileName); - if (displayLevel > 2) DISPLAYOUT("\n"); - return 1; - } - else if (error == info_file_error) { - /* error occurred while opening the file */ - if (displayLevel > 2) DISPLAYOUT("\n"); - return 1; + switch (error) { + case info_frame_error: + /* display error, but provide output */ + DISPLAYLEVEL(1, "Error while parsing \"%s\" \n", inFileName); + break; + case info_not_zstd: + DISPLAYOUT("File \"%s\" not compressed by zstd \n", inFileName); + if (displayLevel > 2) DISPLAYOUT("\n"); + return 1; + case info_file_error: + /* error occurred while opening the file */ + if (displayLevel > 2) DISPLAYOUT("\n"); + return 1; + case info_truncated_input: + DISPLAYOUT("File \"%s\" is truncated \n", inFileName); + if (displayLevel > 2) DISPLAYOUT("\n"); + return 1; + case info_success: + default: + break; } + displayInfo(inFileName, &info, displayLevel); *total = FIO_addFInfo(*total, info); assert(error == info_success || error == info_frame_error); diff --git a/programs/fileio.h b/programs/fileio.h index 97f270632071..e46633752f4a 100644 --- a/programs/fileio.h +++ b/programs/fileio.h @@ -42,44 +42,55 @@ extern "C" { ***************************************/ typedef enum { FIO_zstdCompression, FIO_gzipCompression, FIO_xzCompression, FIO_lzmaCompression, FIO_lz4Compression } FIO_compressionType_t; +typedef struct FIO_prefs_s FIO_prefs_t; + +FIO_prefs_t* FIO_createPreferences(void); +void FIO_freePreferences(FIO_prefs_t* const prefs); + +typedef struct FIO_display_prefs_s FIO_display_prefs_t; /*-************************************* * Parameters ***************************************/ -void FIO_setCompressionType(FIO_compressionType_t compressionType); -void FIO_overwriteMode(void); -void FIO_setAdaptiveMode(unsigned adapt); -void FIO_setAdaptMin(int minCLevel); -void FIO_setAdaptMax(int maxCLevel); -void FIO_setBlockSize(unsigned blockSize); -void FIO_setChecksumFlag(unsigned checksumFlag); -void FIO_setDictIDFlag(unsigned dictIDFlag); -void FIO_setLdmBucketSizeLog(unsigned ldmBucketSizeLog); -void FIO_setLdmFlag(unsigned ldmFlag); -void FIO_setLdmHashRateLog(unsigned ldmHashRateLog); -void FIO_setLdmHashLog(unsigned ldmHashLog); -void FIO_setLdmMinMatch(unsigned ldmMinMatch); -void FIO_setMemLimit(unsigned memLimit); -void FIO_setNbWorkers(unsigned nbWorkers); -void FIO_setNotificationLevel(unsigned level); -void FIO_setOverlapLog(unsigned overlapLog); -void FIO_setRemoveSrcFile(unsigned flag); -void FIO_setSparseWrite(unsigned sparse); /**< 0: no sparse; 1: disable on stdout; 2: always enabled */ -void FIO_setRsyncable(unsigned rsyncable); -void FIO_setNoProgress(unsigned noProgress); +void FIO_setCompressionType(FIO_prefs_t* const prefs, FIO_compressionType_t compressionType); +void FIO_overwriteMode(FIO_prefs_t* const prefs); +void FIO_setAdaptiveMode(FIO_prefs_t* const prefs, unsigned adapt); +void FIO_setAdaptMin(FIO_prefs_t* const prefs, int minCLevel); +void FIO_setAdaptMax(FIO_prefs_t* const prefs, int maxCLevel); +void FIO_setBlockSize(FIO_prefs_t* const prefs, int blockSize); +void FIO_setChecksumFlag(FIO_prefs_t* const prefs, int checksumFlag); +void FIO_setDictIDFlag(FIO_prefs_t* const prefs, int dictIDFlag); +void FIO_setLdmBucketSizeLog(FIO_prefs_t* const prefs, int ldmBucketSizeLog); +void FIO_setLdmFlag(FIO_prefs_t* const prefs, unsigned ldmFlag); +void FIO_setLdmHashRateLog(FIO_prefs_t* const prefs, int ldmHashRateLog); +void FIO_setLdmHashLog(FIO_prefs_t* const prefs, int ldmHashLog); +void FIO_setLdmMinMatch(FIO_prefs_t* const prefs, int ldmMinMatch); +void FIO_setMemLimit(FIO_prefs_t* const prefs, unsigned memLimit); +void FIO_setNbWorkers(FIO_prefs_t* const prefs, int nbWorkers); +void FIO_setOverlapLog(FIO_prefs_t* const prefs, int overlapLog); +void FIO_setRemoveSrcFile(FIO_prefs_t* const prefs, unsigned flag); +void FIO_setSparseWrite(FIO_prefs_t* const prefs, unsigned sparse); /**< 0: no sparse; 1: disable on stdout; 2: always enabled */ +void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable); +void FIO_setLiteralCompressionMode( + FIO_prefs_t* const prefs, + ZSTD_literalCompressionMode_e mode); +void FIO_setNoProgress(unsigned noProgress); +void FIO_setNotificationLevel(int level); /*-************************************* * Single File functions ***************************************/ /** FIO_compressFilename() : @return : 0 == ok; 1 == pb with src file. */ -int FIO_compressFilename (const char* outfilename, const char* infilename, const char* dictFileName, +int FIO_compressFilename (FIO_prefs_t* const prefs, + const char* outfilename, const char* infilename, const char* dictFileName, int compressionLevel, ZSTD_compressionParameters comprParams); /** FIO_decompressFilename() : @return : 0 == ok; 1 == pb with src file. */ -int FIO_decompressFilename (const char* outfilename, const char* infilename, const char* dictFileName); +int FIO_decompressFilename (FIO_prefs_t* const prefs, + const char* outfilename, const char* infilename, const char* dictFileName); int FIO_listMultipleFiles(unsigned numFiles, const char** filenameTable, int displayLevel); @@ -89,14 +100,16 @@ int FIO_listMultipleFiles(unsigned numFiles, const char** filenameTable, int dis ***************************************/ /** FIO_compressMultipleFilenames() : @return : nb of missing files */ -int FIO_compressMultipleFilenames(const char** srcNamesTable, unsigned nbFiles, +int FIO_compressMultipleFilenames(FIO_prefs_t* const prefs, + const char** srcNamesTable, unsigned nbFiles, const char* outFileName, const char* suffix, const char* dictFileName, int compressionLevel, ZSTD_compressionParameters comprParams); /** FIO_decompressMultipleFilenames() : @return : nb of missing or skipped files */ -int FIO_decompressMultipleFilenames(const char** srcNamesTable, unsigned nbFiles, +int FIO_decompressMultipleFilenames(FIO_prefs_t* const prefs, + const char** srcNamesTable, unsigned nbFiles, const char* outFileName, const char* dictFileName); diff --git a/programs/platform.h b/programs/platform.h index 1a8f97bc4dff..38ded872743e 100644 --- a/programs/platform.h +++ b/programs/platform.h @@ -87,8 +87,8 @@ extern "C" { * The following list of build macros tries to "guess" if target OS is likely unix-like, and therefore can #include */ # elif !defined(_WIN32) \ - && (defined(__unix__) || defined(__unix) \ - || defined(__midipix__) || defined(__VMS) || defined(__HAIKU__)) + && ( defined(__unix__) || defined(__unix) \ + || defined(__midipix__) || defined(__VMS) || defined(__HAIKU__) ) # if defined(__linux__) || defined(__linux) # ifndef _POSIX_C_SOURCE @@ -108,6 +108,7 @@ extern "C" { #endif /* PLATFORM_POSIX_VERSION */ + /*-********************************************* * Detect if isatty() and fileno() are available ************************************************/ diff --git a/programs/timefn.c b/programs/timefn.c new file mode 100644 index 000000000000..096e1910bf4b --- /dev/null +++ b/programs/timefn.c @@ -0,0 +1,168 @@ +/* + * Copyright (c) 2019-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +/* === Dependencies === */ + +#include "timefn.h" + + +/*-**************************************** +* Time functions +******************************************/ + +#if defined(_WIN32) /* Windows */ + +#include /* abort */ +#include /* perror */ + +UTIL_time_t UTIL_getTime(void) { UTIL_time_t x; QueryPerformanceCounter(&x); return x; } + +PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) +{ + static LARGE_INTEGER ticksPerSecond; + static int init = 0; + if (!init) { + if (!QueryPerformanceFrequency(&ticksPerSecond)) { + perror("timefn::QueryPerformanceFrequency"); + abort(); + } + init = 1; + } + return 1000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart; +} + +PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) +{ + static LARGE_INTEGER ticksPerSecond; + static int init = 0; + if (!init) { + if (!QueryPerformanceFrequency(&ticksPerSecond)) { + perror("timefn::QueryPerformanceFrequency"); + abort(); + } + init = 1; + } + return 1000000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart; +} + + + +#elif defined(__APPLE__) && defined(__MACH__) + +UTIL_time_t UTIL_getTime(void) { return mach_absolute_time(); } + +PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) +{ + static mach_timebase_info_data_t rate; + static int init = 0; + if (!init) { + mach_timebase_info(&rate); + init = 1; + } + return (((clockEnd - clockStart) * (PTime)rate.numer) / ((PTime)rate.denom))/1000ULL; +} + +PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) +{ + static mach_timebase_info_data_t rate; + static int init = 0; + if (!init) { + mach_timebase_info(&rate); + init = 1; + } + return ((clockEnd - clockStart) * (PTime)rate.numer) / ((PTime)rate.denom); +} + + + +#elif (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L) /* C11 */) \ + && defined(TIME_UTC) /* C11 requires timespec_get, but FreeBSD 11 lacks it, while still claiming C11 compliance */ + +#include /* abort */ +#include /* perror */ + +UTIL_time_t UTIL_getTime(void) +{ + /* time must be initialized, othersize it may fail msan test. + * No good reason, likely a limitation of timespec_get() for some target */ + UTIL_time_t time = UTIL_TIME_INITIALIZER; + if (timespec_get(&time, TIME_UTC) != TIME_UTC) { + perror("timefn::timespec_get"); + abort(); + } + return time; +} + +static UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end) +{ + UTIL_time_t diff; + if (end.tv_nsec < begin.tv_nsec) { + diff.tv_sec = (end.tv_sec - 1) - begin.tv_sec; + diff.tv_nsec = (end.tv_nsec + 1000000000ULL) - begin.tv_nsec; + } else { + diff.tv_sec = end.tv_sec - begin.tv_sec; + diff.tv_nsec = end.tv_nsec - begin.tv_nsec; + } + return diff; +} + +PTime UTIL_getSpanTimeMicro(UTIL_time_t begin, UTIL_time_t end) +{ + UTIL_time_t const diff = UTIL_getSpanTime(begin, end); + PTime micro = 0; + micro += 1000000ULL * diff.tv_sec; + micro += diff.tv_nsec / 1000ULL; + return micro; +} + +PTime UTIL_getSpanTimeNano(UTIL_time_t begin, UTIL_time_t end) +{ + UTIL_time_t const diff = UTIL_getSpanTime(begin, end); + PTime nano = 0; + nano += 1000000000ULL * diff.tv_sec; + nano += diff.tv_nsec; + return nano; +} + + + +#else /* relies on standard C90 (note : clock_t measurements can be wrong when using multi-threading) */ + +UTIL_time_t UTIL_getTime(void) { return clock(); } +PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; } +PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; } + +#endif + + + +/* returns time span in microseconds */ +PTime UTIL_clockSpanMicro(UTIL_time_t clockStart ) +{ + UTIL_time_t const clockEnd = UTIL_getTime(); + return UTIL_getSpanTimeMicro(clockStart, clockEnd); +} + +/* returns time span in microseconds */ +PTime UTIL_clockSpanNano(UTIL_time_t clockStart ) +{ + UTIL_time_t const clockEnd = UTIL_getTime(); + return UTIL_getSpanTimeNano(clockStart, clockEnd); +} + +void UTIL_waitForNextTick(void) +{ + UTIL_time_t const clockStart = UTIL_getTime(); + UTIL_time_t clockEnd; + do { + clockEnd = UTIL_getTime(); + } while (UTIL_getSpanTimeNano(clockStart, clockEnd) == 0); +} diff --git a/programs/timefn.h b/programs/timefn.h new file mode 100644 index 000000000000..d1ddd31b1c00 --- /dev/null +++ b/programs/timefn.h @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef TIME_FN_H_MODULE_287987 +#define TIME_FN_H_MODULE_287987 + +#if defined (__cplusplus) +extern "C" { +#endif + + +/*-**************************************** +* Dependencies +******************************************/ +#include /* utime */ +#if defined(_MSC_VER) +# include /* utime */ +#else +# include /* utime */ +#endif +#include /* clock_t, clock, CLOCKS_PER_SEC */ + + + +/*-**************************************** +* Local Types +******************************************/ + +#if !defined (__VMS) && (defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) ) +# include + typedef uint64_t PTime; /* Precise Time */ +#else + typedef unsigned long long PTime; /* does not support compilers without long long support */ +#endif + + + +/*-**************************************** +* Time functions +******************************************/ +#if defined(_WIN32) /* Windows */ + + #include /* LARGE_INTEGER */ + typedef LARGE_INTEGER UTIL_time_t; + #define UTIL_TIME_INITIALIZER { { 0, 0 } } + +#elif defined(__APPLE__) && defined(__MACH__) + + #include + typedef PTime UTIL_time_t; + #define UTIL_TIME_INITIALIZER 0 + +#elif (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L) /* C11 */) \ + && defined(TIME_UTC) /* C11 requires timespec_get, but FreeBSD 11 lacks it, while still claiming C11 compliance */ + + typedef struct timespec UTIL_time_t; + #define UTIL_TIME_INITIALIZER { 0, 0 } + +#else /* relies on standard C90 (note : clock_t measurements can be wrong when using multi-threading) */ + + typedef clock_t UTIL_time_t; + #define UTIL_TIME_INITIALIZER 0 + +#endif + + +UTIL_time_t UTIL_getTime(void); +PTime UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd); +PTime UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd); + +#define SEC_TO_MICRO ((PTime)1000000) +PTime UTIL_clockSpanMicro(UTIL_time_t clockStart); +PTime UTIL_clockSpanNano(UTIL_time_t clockStart); + +void UTIL_waitForNextTick(void); + + +#if defined (__cplusplus) +} +#endif + +#endif /* TIME_FN_H_MODULE_287987 */ diff --git a/programs/util.c b/programs/util.c index 34634318c638..7b827d4536ad 100644 --- a/programs/util.c +++ b/programs/util.c @@ -87,6 +87,23 @@ U32 UTIL_isDirectory(const char* infilename) return 0; } +int UTIL_isSameFile(const char* file1, const char* file2) +{ +#if defined(_MSC_VER) + /* note : Visual does not support file identification by inode. + * The following work-around is limited to detecting exact name repetition only, + * aka `filename` is considered different from `subdir/../filename` */ + return !strcmp(file1, file2); +#else + stat_t file1Stat; + stat_t file2Stat; + return UTIL_getFileStat(file1, &file1Stat) + && UTIL_getFileStat(file2, &file2Stat) + && (file1Stat.st_dev == file2Stat.st_dev) + && (file1Stat.st_ino == file2Stat.st_ino); +#endif +} + U32 UTIL_isLink(const char* infilename) { /* macro guards, as defined in : https://linux.die.net/man/2/lstat */ @@ -95,7 +112,9 @@ U32 UTIL_isLink(const char* infilename) || (defined(_XOPEN_SOURCE) && (_XOPEN_SOURCE >= 500)) \ || (defined(_XOPEN_SOURCE) && defined(_XOPEN_SOURCE_EXTENDED)) \ || (defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L)) \ - || (defined(__APPLE__) && defined(__MACH__)) + || (defined(__APPLE__) && defined(__MACH__)) \ + || defined(__OpenBSD__) \ + || defined(__FreeBSD__) int r; stat_t statbuf; r = lstat(infilename, &statbuf); @@ -333,146 +352,18 @@ UTIL_createFileList(const char **inputNames, unsigned inputNamesNb, return fileTable; } + /*-**************************************** * Console log ******************************************/ int g_utilDisplayLevel; + /*-**************************************** -* Time functions +* count the number of physical cores ******************************************/ -#if defined(_WIN32) /* Windows */ -UTIL_time_t UTIL_getTime(void) { UTIL_time_t x; QueryPerformanceCounter(&x); return x; } - -U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) -{ - static LARGE_INTEGER ticksPerSecond; - static int init = 0; - if (!init) { - if (!QueryPerformanceFrequency(&ticksPerSecond)) - UTIL_DISPLAYLEVEL(1, "ERROR: QueryPerformanceFrequency() failure\n"); - init = 1; - } - return 1000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart; -} - -U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) -{ - static LARGE_INTEGER ticksPerSecond; - static int init = 0; - if (!init) { - if (!QueryPerformanceFrequency(&ticksPerSecond)) - UTIL_DISPLAYLEVEL(1, "ERROR: QueryPerformanceFrequency() failure\n"); - init = 1; - } - return 1000000000ULL*(clockEnd.QuadPart - clockStart.QuadPart)/ticksPerSecond.QuadPart; -} - -#elif defined(__APPLE__) && defined(__MACH__) - -UTIL_time_t UTIL_getTime(void) { return mach_absolute_time(); } - -U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) -{ - static mach_timebase_info_data_t rate; - static int init = 0; - if (!init) { - mach_timebase_info(&rate); - init = 1; - } - return (((clockEnd - clockStart) * (U64)rate.numer) / ((U64)rate.denom))/1000ULL; -} - -U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) -{ - static mach_timebase_info_data_t rate; - static int init = 0; - if (!init) { - mach_timebase_info(&rate); - init = 1; - } - return ((clockEnd - clockStart) * (U64)rate.numer) / ((U64)rate.denom); -} - -#elif (PLATFORM_POSIX_VERSION >= 200112L) \ - && (defined(__UCLIBC__) \ - || (defined(__GLIBC__) \ - && ((__GLIBC__ == 2 && __GLIBC_MINOR__ >= 17) \ - || (__GLIBC__ > 2)))) - -UTIL_time_t UTIL_getTime(void) -{ - UTIL_time_t time; - if (clock_gettime(CLOCK_MONOTONIC, &time)) - UTIL_DISPLAYLEVEL(1, "ERROR: Failed to get time\n"); /* we could also exit() */ - return time; -} - -UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end) -{ - UTIL_time_t diff; - if (end.tv_nsec < begin.tv_nsec) { - diff.tv_sec = (end.tv_sec - 1) - begin.tv_sec; - diff.tv_nsec = (end.tv_nsec + 1000000000ULL) - begin.tv_nsec; - } else { - diff.tv_sec = end.tv_sec - begin.tv_sec; - diff.tv_nsec = end.tv_nsec - begin.tv_nsec; - } - return diff; -} - -U64 UTIL_getSpanTimeMicro(UTIL_time_t begin, UTIL_time_t end) -{ - UTIL_time_t const diff = UTIL_getSpanTime(begin, end); - U64 micro = 0; - micro += 1000000ULL * diff.tv_sec; - micro += diff.tv_nsec / 1000ULL; - return micro; -} - -U64 UTIL_getSpanTimeNano(UTIL_time_t begin, UTIL_time_t end) -{ - UTIL_time_t const diff = UTIL_getSpanTime(begin, end); - U64 nano = 0; - nano += 1000000000ULL * diff.tv_sec; - nano += diff.tv_nsec; - return nano; -} - -#else /* relies on standard C (note : clock_t measurements can be wrong when using multi-threading) */ - -UTIL_time_t UTIL_getTime(void) { return clock(); } -U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; } -U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd) { return 1000000000ULL * (clockEnd - clockStart) / CLOCKS_PER_SEC; } - -#endif - -/* returns time span in microseconds */ -U64 UTIL_clockSpanMicro(UTIL_time_t clockStart ) -{ - UTIL_time_t const clockEnd = UTIL_getTime(); - return UTIL_getSpanTimeMicro(clockStart, clockEnd); -} - -/* returns time span in microseconds */ -U64 UTIL_clockSpanNano(UTIL_time_t clockStart ) -{ - UTIL_time_t const clockEnd = UTIL_getTime(); - return UTIL_getSpanTimeNano(clockStart, clockEnd); -} - -void UTIL_waitForNextTick(void) -{ - UTIL_time_t const clockStart = UTIL_getTime(); - UTIL_time_t clockEnd; - do { - clockEnd = UTIL_getTime(); - } while (UTIL_getSpanTimeNano(clockStart, clockEnd) == 0); -} - -/* count the number of physical cores */ #if defined(_WIN32) || defined(WIN32) #include @@ -640,10 +531,42 @@ int UTIL_countPhysicalCores(void) } } -#elif defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) +#elif defined(__FreeBSD__) -/* Use apple-provided syscall - * see: man 3 sysctl */ +#include +#include + +/* Use physical core sysctl when available + * see: man 4 smp, man 3 sysctl */ +int UTIL_countPhysicalCores(void) +{ + static int numPhysicalCores = 0; /* freebsd sysctl is native int sized */ + if (numPhysicalCores != 0) return numPhysicalCores; + +#if __FreeBSD_version >= 1300008 + { size_t size = sizeof(numPhysicalCores); + int ret = sysctlbyname("kern.smp.cores", &numPhysicalCores, &size, NULL, 0); + if (ret == 0) return numPhysicalCores; + if (errno != ENOENT) { + perror("zstd: can't get number of physical cpus"); + exit(1); + } + /* sysctl not present, fall through to older sysconf method */ + } +#endif + + numPhysicalCores = (int)sysconf(_SC_NPROCESSORS_ONLN); + if (numPhysicalCores == -1) { + /* value not queryable, fall back on 1 */ + numPhysicalCores = 1; + } + return numPhysicalCores; +} + +#elif defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) + +/* Use POSIX sysconf + * see: man 3 sysconf */ int UTIL_countPhysicalCores(void) { static int numPhysicalCores = 0; diff --git a/programs/util.h b/programs/util.h index f78bcbe1b3f8..d6e5bb550ec7 100644 --- a/programs/util.h +++ b/programs/util.h @@ -112,52 +112,6 @@ extern int g_utilDisplayLevel; #define UTIL_DISPLAYLEVEL(l, ...) { if (g_utilDisplayLevel>=l) { UTIL_DISPLAY(__VA_ARGS__); } } -/*-**************************************** -* Time functions -******************************************/ -#if defined(_WIN32) /* Windows */ - - #define UTIL_TIME_INITIALIZER { { 0, 0 } } - typedef LARGE_INTEGER UTIL_time_t; - -#elif defined(__APPLE__) && defined(__MACH__) - - #include - #define UTIL_TIME_INITIALIZER 0 - typedef U64 UTIL_time_t; - -#elif (PLATFORM_POSIX_VERSION >= 200112L) \ - && (defined(__UCLIBC__) \ - || (defined(__GLIBC__) \ - && ((__GLIBC__ == 2 && __GLIBC_MINOR__ >= 17) \ - || (__GLIBC__ > 2)))) - - #define UTIL_TIME_INITIALIZER { 0, 0 } - typedef struct timespec UTIL_freq_t; - typedef struct timespec UTIL_time_t; - - UTIL_time_t UTIL_getSpanTime(UTIL_time_t begin, UTIL_time_t end); - -#else /* relies on standard C (note : clock_t measurements can be wrong when using multi-threading) */ - - typedef clock_t UTIL_time_t; - #define UTIL_TIME_INITIALIZER 0 - -#endif - -UTIL_time_t UTIL_getTime(void); -U64 UTIL_getSpanTimeMicro(UTIL_time_t clockStart, UTIL_time_t clockEnd); -U64 UTIL_getSpanTimeNano(UTIL_time_t clockStart, UTIL_time_t clockEnd); - -#define SEC_TO_MICRO 1000000 - -/* returns time span in microseconds */ -U64 UTIL_clockSpanMicro(UTIL_time_t clockStart); - -/* returns time span in microseconds */ -U64 UTIL_clockSpanNano(UTIL_time_t clockStart); -void UTIL_waitForNextTick(void); - /*-**************************************** * File functions ******************************************/ @@ -174,6 +128,7 @@ int UTIL_isRegularFile(const char* infilename); int UTIL_setFileStat(const char* filename, stat_t* statbuf); U32 UTIL_isDirectory(const char* infilename); int UTIL_getFileStat(const char* infilename, stat_t* statbuf); +int UTIL_isSameFile(const char* file1, const char* file2); U32 UTIL_isLink(const char* infilename); #define UTIL_FILESIZE_UNKNOWN ((U64)(-1)) diff --git a/programs/zstd.1 b/programs/zstd.1 index c93755f877ed..cb4e1271a0f2 100644 --- a/programs/zstd.1 +++ b/programs/zstd.1 @@ -164,7 +164,7 @@ keep source file(s) after successful compression or decompression\. This is the . .TP \fB\-r\fR -operate recursively on dictionaries +operate recursively on directories . .TP \fB\-\-format=FORMAT\fR diff --git a/programs/zstd.1.md b/programs/zstd.1.md index a029af5ff3ce..93c6fa40010e 100644 --- a/programs/zstd.1.md +++ b/programs/zstd.1.md @@ -178,7 +178,7 @@ the last one takes effect. keep source file(s) after successful compression or decompression. This is the default behavior. * `-r`: - operate recursively on dictionaries + operate recursively on directories * `--format=FORMAT`: compress and decompress in other formats. If compiled with support, zstd can compress to or decompress from other compression algorithm diff --git a/programs/zstdcli.c b/programs/zstdcli.c index 64dad110c7af..fbb1c048a363 100644 --- a/programs/zstdcli.c +++ b/programs/zstdcli.c @@ -148,6 +148,7 @@ static int usage_advanced(const char* programName) #endif DISPLAY( "--no-dictID : don't write dictID into header (dictionary compression)\n"); DISPLAY( "--[no-]check : integrity check (default: enabled) \n"); + DISPLAY( "--[no-]compress-literals : force (un)compressed literals \n"); #endif #ifdef UTIL_HAS_CREATEFILELIST DISPLAY( " -r : operate recursively on directories \n"); @@ -241,18 +242,20 @@ static void errorOut(const char* msg) * @return 1 if an overflow error occurs */ static int readU32FromCharChecked(const char** stringPtr, unsigned* value) { - static unsigned const max = (((unsigned)(-1)) / 10) - 1; unsigned result = 0; while ((**stringPtr >='0') && (**stringPtr <='9')) { - if (result > max) return 1; // overflow error - result *= 10, result += **stringPtr - '0', (*stringPtr)++ ; + unsigned const max = (((unsigned)(-1)) / 10) - 1; + if (result > max) return 1; /* overflow error */ + result *= 10; + result += (unsigned)(**stringPtr - '0'); + (*stringPtr)++ ; } if ((**stringPtr=='K') || (**stringPtr=='M')) { unsigned const maxK = ((unsigned)(-1)) >> 10; - if (result > maxK) return 1; // overflow error + if (result > maxK) return 1; /* overflow error */ result <<= 10; if (**stringPtr=='M') { - if (result > maxK) return 1; // overflow error + if (result > maxK) return 1; /* overflow error */ result <<= 10; } (*stringPtr)++; /* skip `K` or `M` */ @@ -344,7 +347,7 @@ static unsigned parseFastCoverParameters(const char* stringPtr, ZDICT_fastCover_ /** * parseLegacyParameters() : - * reads legacy dictioanry builter parameters from *stringPtr (e.g. "--train-legacy=selectivity=8") into *selectivity + * reads legacy dictionary builder parameters from *stringPtr (e.g. "--train-legacy=selectivity=8") into *selectivity * @return 1 means that legacy dictionary builder parameters were correct * @return 0 in case of malformed parameters */ @@ -483,7 +486,7 @@ static int init_cLevel(void) { if ((*ptr>='0') && (*ptr<='9')) { unsigned absLevel; - if (readU32FromCharChecked(&ptr, &absLevel)) { + if (readU32FromCharChecked(&ptr, &absLevel)) { DISPLAYLEVEL(2, "Ignore environment variable setting %s=%s: numeric value too large\n", ENV_CLEVEL, env); return ZSTDCLI_CLEVEL_DEFAULT; } else if (*ptr == 0) { @@ -536,6 +539,8 @@ int main(int argCount, const char* argv[]) double compressibility = 0.5; unsigned bench_nbSeconds = 3; /* would be better if this value was synchronized from bench */ size_t blockSize = 0; + + FIO_prefs_t* const prefs = FIO_createPreferences(); zstd_operation_mode operation = zom_compress; ZSTD_compressionParameters compressionParams; int cLevel; @@ -565,6 +570,7 @@ int main(int argCount, const char* argv[]) #ifndef ZSTD_NOBENCH BMK_advancedParams_t benchParams = BMK_initAdvancedParams(); #endif + ZSTD_literalCompressionMode_e literalCompressionMode = ZSTD_lcm_auto; /* init */ @@ -582,17 +588,17 @@ int main(int argCount, const char* argv[]) /* preset behaviors */ if (exeNameMatch(programName, ZSTD_ZSTDMT)) nbWorkers=0, singleThread=0; if (exeNameMatch(programName, ZSTD_UNZSTD)) operation=zom_decompress; - if (exeNameMatch(programName, ZSTD_CAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; } /* supports multiple formats */ - if (exeNameMatch(programName, ZSTD_ZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; } /* behave like zcat, also supports multiple formats */ - if (exeNameMatch(programName, ZSTD_GZ)) { suffix = GZ_EXTENSION; FIO_setCompressionType(FIO_gzipCompression); FIO_setRemoveSrcFile(1); } /* behave like gzip */ - if (exeNameMatch(programName, ZSTD_GUNZIP)) { operation=zom_decompress; FIO_setRemoveSrcFile(1); } /* behave like gunzip, also supports multiple formats */ - if (exeNameMatch(programName, ZSTD_GZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(); outFileName=stdoutmark; g_displayLevel=1; } /* behave like gzcat, also supports multiple formats */ - if (exeNameMatch(programName, ZSTD_LZMA)) { suffix = LZMA_EXTENSION; FIO_setCompressionType(FIO_lzmaCompression); FIO_setRemoveSrcFile(1); } /* behave like lzma */ - if (exeNameMatch(programName, ZSTD_UNLZMA)) { operation=zom_decompress; FIO_setCompressionType(FIO_lzmaCompression); FIO_setRemoveSrcFile(1); } /* behave like unlzma, also supports multiple formats */ - if (exeNameMatch(programName, ZSTD_XZ)) { suffix = XZ_EXTENSION; FIO_setCompressionType(FIO_xzCompression); FIO_setRemoveSrcFile(1); } /* behave like xz */ - if (exeNameMatch(programName, ZSTD_UNXZ)) { operation=zom_decompress; FIO_setCompressionType(FIO_xzCompression); FIO_setRemoveSrcFile(1); } /* behave like unxz, also supports multiple formats */ - if (exeNameMatch(programName, ZSTD_LZ4)) { suffix = LZ4_EXTENSION; FIO_setCompressionType(FIO_lz4Compression); } /* behave like lz4 */ - if (exeNameMatch(programName, ZSTD_UNLZ4)) { operation=zom_decompress; FIO_setCompressionType(FIO_lz4Compression); } /* behave like unlz4, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_CAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(prefs); outFileName=stdoutmark; g_displayLevel=1; } /* supports multiple formats */ + if (exeNameMatch(programName, ZSTD_ZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(prefs); outFileName=stdoutmark; g_displayLevel=1; } /* behave like zcat, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_GZ)) { suffix = GZ_EXTENSION; FIO_setCompressionType(prefs, FIO_gzipCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like gzip */ + if (exeNameMatch(programName, ZSTD_GUNZIP)) { operation=zom_decompress; FIO_setRemoveSrcFile(prefs, 1); } /* behave like gunzip, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_GZCAT)) { operation=zom_decompress; forceStdout=1; FIO_overwriteMode(prefs); outFileName=stdoutmark; g_displayLevel=1; } /* behave like gzcat, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_LZMA)) { suffix = LZMA_EXTENSION; FIO_setCompressionType(prefs, FIO_lzmaCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like lzma */ + if (exeNameMatch(programName, ZSTD_UNLZMA)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_lzmaCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like unlzma, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_XZ)) { suffix = XZ_EXTENSION; FIO_setCompressionType(prefs, FIO_xzCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like xz */ + if (exeNameMatch(programName, ZSTD_UNXZ)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_xzCompression); FIO_setRemoveSrcFile(prefs, 1); } /* behave like unxz, also supports multiple formats */ + if (exeNameMatch(programName, ZSTD_LZ4)) { suffix = LZ4_EXTENSION; FIO_setCompressionType(prefs, FIO_lz4Compression); } /* behave like lz4 */ + if (exeNameMatch(programName, ZSTD_UNLZ4)) { operation=zom_decompress; FIO_setCompressionType(prefs, FIO_lz4Compression); } /* behave like unlz4, also supports multiple formats */ memset(&compressionParams, 0, sizeof(compressionParams)); /* init crash handler */ @@ -623,40 +629,42 @@ int main(int argCount, const char* argv[]) if (!strcmp(argument, "--compress")) { operation=zom_compress; continue; } if (!strcmp(argument, "--decompress")) { operation=zom_decompress; continue; } if (!strcmp(argument, "--uncompress")) { operation=zom_decompress; continue; } - if (!strcmp(argument, "--force")) { FIO_overwriteMode(); forceStdout=1; followLinks=1; continue; } + if (!strcmp(argument, "--force")) { FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; continue; } if (!strcmp(argument, "--version")) { g_displayOut=stdout; DISPLAY(WELCOME_MESSAGE); CLEAN_RETURN(0); } if (!strcmp(argument, "--help")) { g_displayOut=stdout; CLEAN_RETURN(usage_advanced(programName)); } if (!strcmp(argument, "--verbose")) { g_displayLevel++; continue; } if (!strcmp(argument, "--quiet")) { g_displayLevel--; continue; } if (!strcmp(argument, "--stdout")) { forceStdout=1; outFileName=stdoutmark; g_displayLevel-=(g_displayLevel==2); continue; } if (!strcmp(argument, "--ultra")) { ultra=1; continue; } - if (!strcmp(argument, "--check")) { FIO_setChecksumFlag(2); continue; } - if (!strcmp(argument, "--no-check")) { FIO_setChecksumFlag(0); continue; } - if (!strcmp(argument, "--sparse")) { FIO_setSparseWrite(2); continue; } - if (!strcmp(argument, "--no-sparse")) { FIO_setSparseWrite(0); continue; } + if (!strcmp(argument, "--check")) { FIO_setChecksumFlag(prefs, 2); continue; } + if (!strcmp(argument, "--no-check")) { FIO_setChecksumFlag(prefs, 0); continue; } + if (!strcmp(argument, "--sparse")) { FIO_setSparseWrite(prefs, 2); continue; } + if (!strcmp(argument, "--no-sparse")) { FIO_setSparseWrite(prefs, 0); continue; } if (!strcmp(argument, "--test")) { operation=zom_test; continue; } if (!strcmp(argument, "--train")) { operation=zom_train; if (outFileName==NULL) outFileName=g_defaultDictName; continue; } if (!strcmp(argument, "--maxdict")) { nextArgumentIsMaxDict=1; lastCommand=1; continue; } /* kept available for compatibility with old syntax ; will be removed one day */ if (!strcmp(argument, "--dictID")) { nextArgumentIsDictID=1; lastCommand=1; continue; } /* kept available for compatibility with old syntax ; will be removed one day */ - if (!strcmp(argument, "--no-dictID")) { FIO_setDictIDFlag(0); continue; } - if (!strcmp(argument, "--keep")) { FIO_setRemoveSrcFile(0); continue; } - if (!strcmp(argument, "--rm")) { FIO_setRemoveSrcFile(1); continue; } + if (!strcmp(argument, "--no-dictID")) { FIO_setDictIDFlag(prefs, 0); continue; } + if (!strcmp(argument, "--keep")) { FIO_setRemoveSrcFile(prefs, 0); continue; } + if (!strcmp(argument, "--rm")) { FIO_setRemoveSrcFile(prefs, 1); continue; } if (!strcmp(argument, "--priority=rt")) { setRealTimePrio = 1; continue; } if (!strcmp(argument, "--adapt")) { adapt = 1; continue; } if (longCommandWArg(&argument, "--adapt=")) { adapt = 1; if (!parseAdaptParameters(argument, &adaptMin, &adaptMax)) CLEAN_RETURN(badusage(programName)); continue; } if (!strcmp(argument, "--single-thread")) { nbWorkers = 0; singleThread = 1; continue; } - if (!strcmp(argument, "--format=zstd")) { suffix = ZSTD_EXTENSION; FIO_setCompressionType(FIO_zstdCompression); continue; } + if (!strcmp(argument, "--format=zstd")) { suffix = ZSTD_EXTENSION; FIO_setCompressionType(prefs, FIO_zstdCompression); continue; } #ifdef ZSTD_GZCOMPRESS - if (!strcmp(argument, "--format=gzip")) { suffix = GZ_EXTENSION; FIO_setCompressionType(FIO_gzipCompression); continue; } + if (!strcmp(argument, "--format=gzip")) { suffix = GZ_EXTENSION; FIO_setCompressionType(prefs, FIO_gzipCompression); continue; } #endif #ifdef ZSTD_LZMACOMPRESS - if (!strcmp(argument, "--format=lzma")) { suffix = LZMA_EXTENSION; FIO_setCompressionType(FIO_lzmaCompression); continue; } - if (!strcmp(argument, "--format=xz")) { suffix = XZ_EXTENSION; FIO_setCompressionType(FIO_xzCompression); continue; } + if (!strcmp(argument, "--format=lzma")) { suffix = LZMA_EXTENSION; FIO_setCompressionType(prefs, FIO_lzmaCompression); continue; } + if (!strcmp(argument, "--format=xz")) { suffix = XZ_EXTENSION; FIO_setCompressionType(prefs, FIO_xzCompression); continue; } #endif #ifdef ZSTD_LZ4COMPRESS - if (!strcmp(argument, "--format=lz4")) { suffix = LZ4_EXTENSION; FIO_setCompressionType(FIO_lz4Compression); continue; } + if (!strcmp(argument, "--format=lz4")) { suffix = LZ4_EXTENSION; FIO_setCompressionType(prefs, FIO_lz4Compression); continue; } #endif if (!strcmp(argument, "--rsyncable")) { rsyncable = 1; continue; } + if (!strcmp(argument, "--compress-literals")) { literalCompressionMode = ZSTD_lcm_huffman; continue; } + if (!strcmp(argument, "--no-compress-literals")) { literalCompressionMode = ZSTD_lcm_uncompressed; continue; } if (!strcmp(argument, "--no-progress")) { FIO_setNoProgress(1); continue; } /* long commands with arguments */ @@ -784,7 +792,7 @@ int main(int argCount, const char* argv[]) case 'D': nextEntryIsDictionary = 1; lastCommand = 1; argument++; break; /* Overwrite */ - case 'f': FIO_overwriteMode(); forceStdout=1; followLinks=1; argument++; break; + case 'f': FIO_overwriteMode(prefs); forceStdout=1; followLinks=1; argument++; break; /* Verbose mode */ case 'v': g_displayLevel++; argument++; break; @@ -793,10 +801,10 @@ int main(int argCount, const char* argv[]) case 'q': g_displayLevel--; argument++; break; /* keep source file (default) */ - case 'k': FIO_setRemoveSrcFile(0); argument++; break; + case 'k': FIO_setRemoveSrcFile(prefs, 0); argument++; break; /* Checksum */ - case 'C': FIO_setChecksumFlag(2); argument++; break; + case 'C': FIO_setChecksumFlag(prefs, 2); argument++; break; /* test compressed file */ case 't': operation=zom_test; argument++; break; @@ -949,6 +957,8 @@ int main(int argCount, const char* argv[]) filenameTable[fileNamesNb++] = filenameTable[u]; } } + if (fileNamesNb == 0 && filenameIdx > 0) + CLEAN_RETURN(1); filenameIdx = fileNamesNb; } if (recursive) { /* at this stage, filenameTable is a list of paths, which can contain both files and directories */ @@ -991,6 +1001,7 @@ int main(int argCount, const char* argv[]) if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) { benchParams.ldmHashRateLog = g_ldmHashRateLog; } + benchParams.literalCompressionMode = literalCompressionMode; if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel(); if (cLevelLast > ZSTD_maxCLevel()) cLevelLast = ZSTD_maxCLevel(); @@ -1057,7 +1068,7 @@ int main(int argCount, const char* argv[]) } #ifndef ZSTD_NODECOMPRESS - if (operation==zom_test) { outFileName=nulmark; FIO_setRemoveSrcFile(0); } /* test mode */ + if (operation==zom_test) { outFileName=nulmark; FIO_setRemoveSrcFile(prefs, 0); } /* test mode */ #endif /* No input filename ==> use stdin and stdout */ @@ -1092,27 +1103,28 @@ int main(int argCount, const char* argv[]) FIO_setNotificationLevel(g_displayLevel); if (operation==zom_compress) { #ifndef ZSTD_NOCOMPRESS - FIO_setNbWorkers(nbWorkers); - FIO_setBlockSize((U32)blockSize); - if (g_overlapLog!=OVERLAP_LOG_DEFAULT) FIO_setOverlapLog(g_overlapLog); - FIO_setLdmFlag(ldmFlag); - FIO_setLdmHashLog(g_ldmHashLog); - FIO_setLdmMinMatch(g_ldmMinMatch); - if (g_ldmBucketSizeLog != LDM_PARAM_DEFAULT) FIO_setLdmBucketSizeLog(g_ldmBucketSizeLog); - if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) FIO_setLdmHashRateLog(g_ldmHashRateLog); - FIO_setAdaptiveMode(adapt); - FIO_setAdaptMin(adaptMin); - FIO_setAdaptMax(adaptMax); - FIO_setRsyncable(rsyncable); + FIO_setNbWorkers(prefs, nbWorkers); + FIO_setBlockSize(prefs, (U32)blockSize); + if (g_overlapLog!=OVERLAP_LOG_DEFAULT) FIO_setOverlapLog(prefs, g_overlapLog); + FIO_setLdmFlag(prefs, ldmFlag); + FIO_setLdmHashLog(prefs, g_ldmHashLog); + FIO_setLdmMinMatch(prefs, g_ldmMinMatch); + if (g_ldmBucketSizeLog != LDM_PARAM_DEFAULT) FIO_setLdmBucketSizeLog(prefs, g_ldmBucketSizeLog); + if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) FIO_setLdmHashRateLog(prefs, g_ldmHashRateLog); + FIO_setAdaptiveMode(prefs, adapt); + FIO_setAdaptMin(prefs, adaptMin); + FIO_setAdaptMax(prefs, adaptMax); + FIO_setRsyncable(prefs, rsyncable); + FIO_setLiteralCompressionMode(prefs, literalCompressionMode); if (adaptMin > cLevel) cLevel = adaptMin; if (adaptMax < cLevel) cLevel = adaptMax; if ((filenameIdx==1) && outFileName) - operationResult = FIO_compressFilename(outFileName, filenameTable[0], dictFileName, cLevel, compressionParams); + operationResult = FIO_compressFilename(prefs, outFileName, filenameTable[0], dictFileName, cLevel, compressionParams); else - operationResult = FIO_compressMultipleFilenames(filenameTable, filenameIdx, outFileName, suffix, dictFileName, cLevel, compressionParams); + operationResult = FIO_compressMultipleFilenames(prefs, filenameTable, filenameIdx, outFileName, suffix, dictFileName, cLevel, compressionParams); #else - (void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; /* not used when ZSTD_NOCOMPRESS set */ + (void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; (void)literalCompressionMode; /* not used when ZSTD_NOCOMPRESS set */ DISPLAY("Compression not supported \n"); #endif } else { /* decompression or test */ @@ -1124,17 +1136,19 @@ int main(int argCount, const char* argv[]) memLimit = (U32)1 << (compressionParams.windowLog & 31); } } - FIO_setMemLimit(memLimit); + FIO_setMemLimit(prefs, memLimit); if (filenameIdx==1 && outFileName) - operationResult = FIO_decompressFilename(outFileName, filenameTable[0], dictFileName); + operationResult = FIO_decompressFilename(prefs, outFileName, filenameTable[0], dictFileName); else - operationResult = FIO_decompressMultipleFilenames(filenameTable, filenameIdx, outFileName, dictFileName); + operationResult = FIO_decompressMultipleFilenames(prefs, filenameTable, filenameIdx, outFileName, dictFileName); #else DISPLAY("Decompression not supported \n"); #endif } _end: + FIO_freePreferences(prefs); + if (main_pause) waitEnter(); #ifdef UTIL_HAS_CREATEFILELIST if (extendedFileList) diff --git a/programs/zstdgrep b/programs/zstdgrep index a10e0710a296..cb804b8bead4 100755 --- a/programs/zstdgrep +++ b/programs/zstdgrep @@ -22,8 +22,8 @@ # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF # THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -grep=grep -zcat=zstdcat +grep=${GREP:-grep} +zcat=${ZCAT:-zstdcat} endofopts=0 pattern_found=0 @@ -31,12 +31,13 @@ grep_args="" hyphen=0 silent=0 -prg=$(basename "$0") +prog=${0##*/} # handle being called 'zegrep' or 'zfgrep' -case "${prg}" in - *zegrep) grep_args="-E";; - *zfgrep) grep_args="-F";; +case $prog in + *egrep*) prog=zegrep; grep_args='-E';; + *fgrep*) prog=zfgrep; grep_args='-F';; + *) prog=zstdgrep;; esac # skip all options and pass them on to grep taking care of options @@ -47,7 +48,7 @@ while [ "$#" -gt 0 ] && [ "${endofopts}" -eq 0 ]; do # from GNU grep-2.5.1 -- keep in sync! -[ABCDXdefm]) if [ "$#" -lt 2 ]; then - printf '%s: missing argument for %s flag\n' "${prg}" "$1" >&2 + printf '%s: missing argument for %s flag\n' "${prog}" "$1" >&2 exit 1 fi case "$1" in @@ -94,7 +95,7 @@ if [ "${pattern_found}" -lt 1 ]; then elif [ "${hyphen}" -gt 0 ]; then pattern="-" else - printf '%s: missing pattern\n' "${prg}" >&2 + printf '%s: missing pattern\n' "${prog}" >&2 exit 1 fi fi @@ -113,16 +114,11 @@ else if [ "${silent}" -lt 1 ] && [ "$#" -gt 1 ]; then grep_args="-H ${grep_args}" fi - CUR_EXIT_CODE=0 - EXIT_CODE=1 set -f while [ "$#" -gt 0 ]; do # shellcheck disable=SC2086 "${zcat}" -fq -- "$1" | "${grep}" --label="${1}" ${grep_args} -- "${pattern}" - - CUR_EXIT_CODE=$? - if [ "${CUR_EXIT_CODE}" -eq 0 ] && [ "${EXIT_CODE}" -ne 1 ]; then - EXIT_CODE=0 - fi + [ "$?" -ne 0 ] && EXIT_CODE=1 shift done set +f diff --git a/tests/Makefile b/tests/Makefile index 25bd5c84ef90..f11b731835ea 100644 --- a/tests/Makefile +++ b/tests/Makefile @@ -33,7 +33,7 @@ endif CFLAGS ?= -O3 CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \ - -Wstrict-prototypes -Wundef -Wformat-security \ + -Wstrict-prototypes -Wundef \ -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \ -Wredundant-decls -Wmissing-prototypes CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS) @@ -82,7 +82,7 @@ default: fullbench @echo $(ZSTDMT_OBJECTS) all: fullbench fuzzer zstreamtest paramgrill datagen decodecorpus roundTripCrash \ - fullbench-lib + fullbench-lib poolTests all32: fullbench32 fuzzer32 zstreamtest32 @@ -132,18 +132,18 @@ fullbench fullbench32 : CPPFLAGS += $(MULTITHREAD_CPP) fullbench fullbench32 : LDFLAGS += $(MULTITHREAD_LD) fullbench fullbench32 : DEBUGFLAGS = -DNDEBUG # turn off assert() for speed measurements fullbench fullbench32 : $(ZSTD_FILES) -fullbench fullbench32 : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c +fullbench fullbench32 : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c fullbench.c $(CC) $(FLAGS) $^ -o $@$(EXT) fullbench-lib : CPPFLAGS += -DXXH_NAMESPACE=ZSTD_ fullbench-lib : zstd-staticLib -fullbench-lib : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c +fullbench-lib : $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c fullbench.c $(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT) $(ZSTDDIR)/libzstd.a # note : broken : requires unavailable symbols fullbench-dll : zstd-dll fullbench-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd -fullbench-dll: $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c fullbench.c +fullbench-dll: $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/benchfn.c $(PRGDIR)/timefn.c fullbench.c # $(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT) -DZSTD_DLL_IMPORT=1 $(ZSTDDIR)/dll/libzstd.dll $(CC) $(FLAGS) $(filter %.c,$^) -o $@$(EXT) @@ -152,32 +152,32 @@ fuzzer : LDFLAGS += $(MULTITHREAD_LD) fuzzer32: CFLAGS += -m32 fuzzer : $(ZSTDMT_OBJECTS) fuzzer32: $(ZSTD_FILES) -fuzzer fuzzer32 : $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c fuzzer.c +fuzzer fuzzer32 : $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c fuzzer.c $(CC) $(FLAGS) $^ -o $@$(EXT) fuzzer-dll : zstd-dll fuzzer-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd -fuzzer-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/datagen.c fuzzer.c +fuzzer-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c fuzzer.c $(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT) zbufftest : CPPFLAGS += -I$(ZSTDDIR)/deprecated zbufftest : CFLAGS += -Wno-deprecated-declarations # required to silence deprecation warnings -zbufftest : $(ZSTD_OBJECTS) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c +zbufftest : $(ZSTD_OBJECTS) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c $(CC) $(FLAGS) $^ -o $@$(EXT) zbufftest32 : CPPFLAGS += -I$(ZSTDDIR)/deprecated zbufftest32 : CFLAGS += -Wno-deprecated-declarations -m32 -zbufftest32 : $(ZSTD_FILES) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c +zbufftest32 : $(ZSTD_FILES) $(ZBUFF_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c $(CC) $(FLAGS) $^ -o $@$(EXT) zbufftest-dll : zstd-dll zbufftest-dll : CPPFLAGS += -I$(ZSTDDIR)/deprecated zbufftest-dll : CFLAGS += -Wno-deprecated-declarations # required to silence deprecation warnings zbufftest-dll : LDFLAGS+= -L$(ZSTDDIR) -lzstd -zbufftest-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/datagen.c zbufftest.c +zbufftest-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/datagen.c zbufftest.c $(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT) -ZSTREAM_LOCAL_FILES := $(PRGDIR)/datagen.c $(PRGDIR)/util.c seqgen.c zstreamtest.c +ZSTREAM_LOCAL_FILES := $(PRGDIR)/datagen.c $(PRGDIR)/util.c $(PRGDIR)/timefn.c seqgen.c zstreamtest.c ZSTREAM_PROPER_FILES := $(ZDICT_FILES) $(ZSTREAM_LOCAL_FILES) ZSTREAMFILES := $(ZSTD_FILES) $(ZSTREAM_PROPER_FILES) zstreamtest32 : CFLAGS += -m32 @@ -203,7 +203,7 @@ zstreamtest-dll : $(ZSTREAM_LOCAL_FILES) $(CC) $(CPPFLAGS) $(CFLAGS) $(filter %.c,$^) $(LDFLAGS) -o $@$(EXT) paramgrill : DEBUGFLAGS = # turn off assert() by default for speed measurements -paramgrill : $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/benchfn.c $(PRGDIR)/benchzstd.c $(PRGDIR)/datagen.c paramgrill.c +paramgrill : $(ZSTD_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c $(PRGDIR)/benchfn.c $(PRGDIR)/benchzstd.c $(PRGDIR)/datagen.c paramgrill.c $(CC) $(FLAGS) $^ -lm -o $@$(EXT) datagen : $(PRGDIR)/datagen.c datagencli.c @@ -222,7 +222,7 @@ legacy : CPPFLAGS += -I$(ZSTDDIR)/legacy -DZSTD_LEGACY_SUPPORT=4 legacy : $(ZSTD_FILES) $(wildcard $(ZSTDDIR)/legacy/*.c) legacy.c $(CC) $(FLAGS) $^ -o $@$(EXT) -decodecorpus : $(filter-out zstdc_zstd_compress.o, $(ZSTD_OBJECTS)) $(ZDICT_FILES) $(PRGDIR)/util.c decodecorpus.c +decodecorpus : $(filter-out zstdc_zstd_compress.o, $(ZSTD_OBJECTS)) $(ZDICT_FILES) $(PRGDIR)/util.c $(PRGDIR)/timefn.c decodecorpus.c $(CC) $(FLAGS) $^ -o $@$(EXT) -lm symbols : symbols.c zstd-dll @@ -233,7 +233,7 @@ else $(CC) $(FLAGS) $< -o $@$(EXT) -Wl,-rpath=$(ZSTDDIR) $(ZSTDDIR)/libzstd.so # broken on Mac endif -poolTests : $(PRGDIR)/util.c poolTests.c $(ZSTDDIR)/common/pool.c $(ZSTDDIR)/common/threading.c $(ZSTDDIR)/common/zstd_common.c $(ZSTDDIR)/common/error_private.c +poolTests : $(PRGDIR)/util.c $(PRGDIR)/timefn.c poolTests.c $(ZSTDDIR)/common/pool.c $(ZSTDDIR)/common/threading.c $(ZSTDDIR)/common/zstd_common.c $(ZSTDDIR)/common/error_private.c $(CC) $(FLAGS) $(MULTITHREAD) $^ -o $@$(EXT) .PHONY: versionsTest @@ -353,8 +353,12 @@ test-gzstd: gzstd $(RM) *.gz *.zst README2.md gz_zstd zstd_gz hello.txt test-zstdgrep: gzstd - @echo a | $(PRGDIR)/zstd | $(PRGDIR)/zstdgrep a - @echo a | $(PRGDIR)/zstd | $(PRGDIR)/zstdgrep b && return 1 || return 0 + -[ -f /tmp/zstdcat ] || ln -s $(PWD)/$(PRGDIR)/zstd /tmp/zstdcat + echo a | $(PRGDIR)/zstd | env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep a + echo a | $(PRGDIR)/zstd | env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep b && return 1 || return 0 + -echo 'hello world' > test.txt && $(PRGDIR)/zstd test.txt + env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep hello test.txt.zst + env ZCAT=/tmp/zstdcat $(PRGDIR)/zstdgrep weird test.txt.zst && return 1 || return 0 test-fullbench: fullbench datagen $(QEMU_SYS) ./fullbench -i1 diff --git a/tests/README.md b/tests/README.md index 7c6fb0db845c..f34501197478 100644 --- a/tests/README.md +++ b/tests/README.md @@ -72,7 +72,7 @@ Command line tool to generate test .zst files. This tool will generate .zst files with checksums, as well as optionally output the corresponding correct uncompressed data for -extra verfication. +extra verification. Example: ``` @@ -123,7 +123,7 @@ Full list of arguments Higher values will make optimizer run longer, more chances to find better solution. memLog : Limits the log of the size of each memotable (1 per strategy). Will use hash tables when state space is larger than max size. Setting memLog = 0 turns off memoization - --display= : specifiy which parameters are included in the output + --display= : specify which parameters are included in the output can use all --zstd parameter names and 'cParams' as a shorthand for all parameters used in ZSTD_compressionParameters (Default: display all params available) -P# : generated sample compressibility (when no file is provided) diff --git a/tests/decodecorpus.c b/tests/decodecorpus.c index 17c2c18991bc..9910d3c551a9 100644 --- a/tests/decodecorpus.c +++ b/tests/decodecorpus.c @@ -16,6 +16,7 @@ #include #include "util.h" +#include "timefn.h" /* UTIL_clockSpanMicro, SEC_TO_MICRO, UTIL_TIME_INITIALIZER */ #include "zstd.h" #include "zstd_internal.h" #include "mem.h" @@ -513,7 +514,7 @@ static size_t writeLiteralsBlockCompressed(U32* seed, frame_t* frame, size_t con if ((RAND(seed) & 3) || !frame->stats.hufInit) { do { if (RAND(seed) & 3) { - /* add 10 to ensure some compressability */ + /* add 10 to ensure some compressibility */ double const weight = ((RAND(seed) % 90) + 10) / 100.0; DISPLAYLEVEL(5, " distribution weight: %d%%\n", @@ -938,7 +939,9 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr, FSE_CState_t stateOffsetBits; FSE_CState_t stateLitLength; - CHECK_E(BIT_initCStream(&blockStream, op, oend-op), dstSize_tooSmall); /* not enough space remaining */ + RETURN_ERROR_IF( + ERR_isError(BIT_initCStream(&blockStream, op, oend-op)), + dstSize_tooSmall, "not enough space remaining"); /* first symbols */ FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]); diff --git a/tests/fullbench.c b/tests/fullbench.c index 8644a2e3a136..b06e2edc53a6 100644 --- a/tests/fullbench.c +++ b/tests/fullbench.c @@ -17,6 +17,7 @@ #include /* fprintf, fopen, ftello64 */ #include /* assert */ +#include "timefn.h" /* UTIL_clockSpanNano, UTIL_getTime */ #include "mem.h" /* U32 */ #ifndef ZSTD_DLL_IMPORT #include "zstd_internal.h" /* ZSTD_decodeSeqHeaders, ZSTD_blockHeaderSize, blockType_e, KB, MB */ @@ -67,12 +68,6 @@ static const size_t g_sampleSize = 10000000; static unsigned g_nbIterations = NBLOOPS; static double g_compressibility = COMPRESSIBILITY_DEFAULT; -static void BMK_SetNbIterations(unsigned nbLoops) -{ - g_nbIterations = nbLoops; - DISPLAY("- %i iterations -\n", g_nbIterations); -} - /*_******************************************************* * Private functions @@ -316,9 +311,9 @@ static size_t local_ZSTD_decompressContinue(const void* src, size_t srcSize, /*_******************************************************* * Bench functions *********************************************************/ -static size_t benchMem(unsigned benchNb, - const void* src, size_t srcSize, - int cLevel, ZSTD_compressionParameters cparams) +static int benchMem(unsigned benchNb, + const void* src, size_t srcSize, + int cLevel, ZSTD_compressionParameters cparams) { size_t dstBuffSize = ZSTD_compressBound(srcSize); BYTE* dstBuff; @@ -395,22 +390,22 @@ static size_t benchMem(unsigned benchNb, cparams->minMatch, cparams->targetLength, cparams->strategy); */ ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_compressionLevel, cLevel); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_windowLog, cparams.windowLog); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_hashLog, cparams.hashLog); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_chainLog, cparams.chainLog); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_searchLog, cparams.searchLog); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_minMatch, cparams.minMatch); - ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_targetLength, cparams.targetLength); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_windowLog, (int)cparams.windowLog); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_hashLog, (int)cparams.hashLog); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_chainLog, (int)cparams.chainLog); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_searchLog, (int)cparams.searchLog); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_minMatch, (int)cparams.minMatch); + ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_targetLength, (int)cparams.targetLength); ZSTD_CCtx_setParameter(g_zcc, ZSTD_c_strategy, cparams.strategy); ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_compressionLevel, cLevel); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_windowLog, cparams.windowLog); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_hashLog, cparams.hashLog); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_chainLog, cparams.chainLog); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_searchLog, cparams.searchLog); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_minMatch, cparams.minMatch); - ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_targetLength, cparams.targetLength); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_windowLog, (int)cparams.windowLog); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_hashLog, (int)cparams.hashLog); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_chainLog, (int)cparams.chainLog); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_searchLog, (int)cparams.searchLog); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_minMatch, (int)cparams.minMatch); + ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_targetLength, (int)cparams.targetLength); ZSTD_CCtx_setParameter(g_cstream, ZSTD_c_strategy, cparams.strategy); /* Preparation */ @@ -469,8 +464,9 @@ static size_t benchMem(unsigned benchNb, iend = ip + ZSTD_blockHeaderSize + cBlockSize; /* End of first block */ ip += ZSTD_blockHeaderSize; /* skip block header */ ZSTD_decompressBegin(g_zdc); - ip += ZSTD_decodeLiteralsBlock(g_zdc, ip, iend-ip); /* skip literal segment */ - g_cSize = iend-ip; + assert(iend > ip); + ip += ZSTD_decodeLiteralsBlock(g_zdc, ip, (size_t)(iend-ip)); /* skip literal segment */ + g_cSize = (size_t)(iend-ip); memcpy(buff2, ip, g_cSize); /* copy rest of block (it starts by SeqHeader) */ srcSize = srcSize > 128 KB ? 128 KB : srcSize; /* speed relative to block */ break; @@ -501,7 +497,7 @@ static size_t benchMem(unsigned benchNb, BMK_benchParams_t bp; BMK_runTime_t bestResult; bestResult.sumOfReturn = 0; - bestResult.nanoSecPerRun = (unsigned long long)(-1LL); + bestResult.nanoSecPerRun = (double)TIMELOOP_NANOSEC * 2000000000; /* hopefully large enough : must be larger than any potential measurement */ assert(tfs != NULL); bp.benchFn = benchFunction; @@ -654,7 +650,9 @@ static unsigned readU32FromChar(const char** stringPtr) while ((**stringPtr >='0') && (**stringPtr <='9')) { unsigned const max = (((unsigned)(-1)) / 10) - 1; if (result > max) ERROR_OUT(errorMsg); - result *= 10, result += **stringPtr - '0', (*stringPtr)++ ; + result *= 10; + result += (unsigned)(**stringPtr - '0'); + (*stringPtr)++ ; } if ((**stringPtr=='K') || (**stringPtr=='M')) { unsigned const maxK = ((unsigned)(-1)) >> 10; @@ -671,7 +669,7 @@ static unsigned readU32FromChar(const char** stringPtr) return result; } -static unsigned longCommandWArg(const char** stringPtr, const char* longCommand) +static int longCommandWArg(const char** stringPtr, const char* longCommand) { size_t const comSize = strlen(longCommand); int const result = !strncmp(*stringPtr, longCommand, comSize); @@ -772,7 +770,7 @@ int main(int argc, const char** argv) /* Modify Nb Iterations */ case 'i': argument++; - BMK_SetNbIterations((int)readU32FromChar(&argument)); + g_nbIterations = readU32FromChar(&argument); break; /* Select compressibility of synthetic sample */ @@ -782,7 +780,7 @@ int main(int argc, const char** argv) break; case 'l': argument++; - cLevel = readU32FromChar(&argument); + cLevel = (int)readU32FromChar(&argument); cparams = ZSTD_getCParams(cLevel, 0, 0); break; diff --git a/tests/fuzz/Makefile b/tests/fuzz/Makefile index 4130f18e330c..31b151b857b3 100644 --- a/tests/fuzz/Makefile +++ b/tests/fuzz/Makefile @@ -27,16 +27,16 @@ PRGDIR = ../../programs FUZZ_CPPFLAGS := -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \ -I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR) \ - $(CPPFLAGS) + -DZSTD_MULTITHREAD $(CPPFLAGS) FUZZ_EXTRA_FLAGS := -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \ - -Wstrict-prototypes -Wundef -Wformat-security \ + -Wstrict-prototypes -Wundef \ -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \ -Wredundant-decls \ -g -fno-omit-frame-pointer FUZZ_CFLAGS := $(FUZZ_EXTRA_FLAGS) $(CFLAGS) FUZZ_CXXFLAGS := $(FUZZ_EXTRA_FLAGS) -std=c++11 $(CXXFLAGS) -FUZZ_LDFLAGS := $(LDFLAGS) +FUZZ_LDFLAGS := -pthread $(LDFLAGS) FUZZ_ARFLAGS := $(ARFLAGS) FUZZ_TARGET_FLAGS = $(FUZZ_CPPFLAGS) $(FUZZ_CXXFLAGS) $(FUZZ_LDFLAGS) @@ -46,11 +46,13 @@ FUZZ_SRC := $(PRGDIR)/util.c zstd_helpers.c ZSTDCOMMON_SRC := $(ZSTDDIR)/common/*.c ZSTDCOMP_SRC := $(ZSTDDIR)/compress/*.c ZSTDDECOMP_SRC := $(ZSTDDIR)/decompress/*.c +ZSTDDICT_SRC := $(ZSTDDIR)/dictBuilder/*.c FUZZ_SRC := \ $(FUZZ_SRC) \ $(ZSTDDECOMP_SRC) \ $(ZSTDCOMMON_SRC) \ - $(ZSTDCOMP_SRC) + $(ZSTDCOMP_SRC) \ + $(ZSTDDICT_SRC) FUZZ_OBJ := $(patsubst %.c,%.o, $(wildcard $(FUZZ_SRC))) @@ -65,7 +67,9 @@ FUZZ_TARGETS := \ block_round_trip \ simple_decompress \ stream_decompress \ - block_decompress + block_decompress \ + dictionary_round_trip \ + dictionary_decompress all: $(FUZZ_TARGETS) @@ -90,11 +94,17 @@ stream_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) stream_decompress.o block_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) block_decompress.o $(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) block_decompress.o $(LIB_FUZZING_ENGINE) -o $@ +dictionary_round_trip: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_round_trip.o + $(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_round_trip.o $(LIB_FUZZING_ENGINE) -o $@ + +dictionary_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_decompress.o + $(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_decompress.o $(LIB_FUZZING_ENGINE) -o $@ + libregression.a: $(FUZZ_HEADERS) $(PRGDIR)/util.h $(PRGDIR)/util.c regression_driver.o $(AR) $(FUZZ_ARFLAGS) $@ regression_driver.o # Install libfuzzer (not usable for MSAN testing) -# Provided for convienence. To use this library run make libFuzzer and +# Provided for convenience. To use this library run make libFuzzer and # set LDFLAGS=-L. .PHONY: libFuzzer libFuzzer: diff --git a/tests/fuzz/README.md b/tests/fuzz/README.md index f184be646ef6..9e0bb259a9e7 100644 --- a/tests/fuzz/README.md +++ b/tests/fuzz/README.md @@ -37,8 +37,8 @@ The specific fuzzing engine is selected with `LIB_FUZZING_ENGINE` or `--lib-fuzzing-engine`, the default is `libregression.a`. It has flags that can easily set up sanitizers `--enable-{a,ub,m}san`, and coverage instrumentation `--enable-coverage`. -It sets sane defaults which can be overriden with flags `--debug`, -`--enable-ubsan-pointer-overlow`, etc. +It sets sane defaults which can be overridden with flags `--debug`, +`--enable-ubsan-pointer-overflow`, etc. Run `./fuzz.py build -h` for help. ### Running Fuzzers diff --git a/tests/fuzz/dictionary_decompress.c b/tests/fuzz/dictionary_decompress.c new file mode 100644 index 000000000000..7d3a7678adc6 --- /dev/null +++ b/tests/fuzz/dictionary_decompress.c @@ -0,0 +1,64 @@ +/* + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + */ + +/** + * This fuzz target attempts to decompress the fuzzed data with the dictionary + * decompression function to ensure the decompressor never crashes. It does not + * fuzz the dictionary. + */ + +#include +#include +#include +#include "fuzz_helpers.h" +#include "zstd_helpers.h" + +static ZSTD_DCtx *dctx = NULL; +static void* rBuf = NULL; +static size_t bufSize = 0; + +int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) +{ + FUZZ_dict_t dict; + size_t neededBufSize; + + uint32_t seed = FUZZ_seed(&src, &size); + neededBufSize = MAX(20 * size, (size_t)256 << 10); + + /* Allocate all buffers and contexts if not already allocated */ + if (neededBufSize > bufSize) { + free(rBuf); + rBuf = malloc(neededBufSize); + bufSize = neededBufSize; + FUZZ_ASSERT(rBuf); + } + if (!dctx) { + dctx = ZSTD_createDCtx(); + FUZZ_ASSERT(dctx); + } + dict = FUZZ_train(src, size, &seed); + if (FUZZ_rand32(&seed, 0, 1) == 0) { + ZSTD_decompress_usingDict(dctx, + rBuf, neededBufSize, + src, size, + dict.buff, dict.size); + } else { + FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced( + dctx, dict.buff, dict.size, + (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1), + (ZSTD_dictContentType_e)FUZZ_rand32(&seed, 0, 2))); + ZSTD_decompressDCtx(dctx, rBuf, neededBufSize, src, size); + } + + free(dict.buff); +#ifndef STATEFUL_FUZZING + ZSTD_freeDCtx(dctx); dctx = NULL; +#endif + return 0; +} diff --git a/tests/fuzz/dictionary_round_trip.c b/tests/fuzz/dictionary_round_trip.c new file mode 100644 index 000000000000..e28c65c98f06 --- /dev/null +++ b/tests/fuzz/dictionary_round_trip.c @@ -0,0 +1,106 @@ +/* + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + */ + +/** + * This fuzz target performs a zstd round-trip test (compress & decompress) with + * a dictionary, compares the result with the original, and calls abort() on + * corruption. + */ + +#include +#include +#include +#include +#include "fuzz_helpers.h" +#include "zstd_helpers.h" + +static const int kMaxClevel = 19; + +static ZSTD_CCtx *cctx = NULL; +static ZSTD_DCtx *dctx = NULL; +static uint32_t seed; + +static size_t roundTripTest(void *result, size_t resultCapacity, + void *compressed, size_t compressedCapacity, + const void *src, size_t srcSize) +{ + ZSTD_dictContentType_e dictContentType = ZSTD_dct_auto; + FUZZ_dict_t dict = FUZZ_train(src, srcSize, &seed); + size_t cSize; + if ((FUZZ_rand(&seed) & 15) == 0) { + int const cLevel = FUZZ_rand(&seed) % kMaxClevel; + + cSize = ZSTD_compress_usingDict(cctx, + compressed, compressedCapacity, + src, srcSize, + dict.buff, dict.size, + cLevel); + } else { + dictContentType = FUZZ_rand32(&seed, 0, 2); + FUZZ_setRandomParameters(cctx, srcSize, &seed); + /* Disable checksum so we can use sizes smaller than compress bound. */ + FUZZ_ZASSERT(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 0)); + FUZZ_ZASSERT(ZSTD_CCtx_loadDictionary_advanced( + cctx, dict.buff, dict.size, + (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1), + dictContentType)); + cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize); + } + FUZZ_ZASSERT(cSize); + FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced( + dctx, dict.buff, dict.size, + (ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1), + dictContentType)); + { + size_t const ret = ZSTD_decompressDCtx( + dctx, result, resultCapacity, compressed, cSize); + free(dict.buff); + return ret; + } +} + +int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) +{ + size_t const rBufSize = size; + void* rBuf = malloc(rBufSize); + size_t cBufSize = ZSTD_compressBound(size); + void* cBuf; + + seed = FUZZ_seed(&src, &size); + /* Half of the time fuzz with a 1 byte smaller output size. + * This will still succeed because we force the checksum to be disabled, + * giving us 4 bytes of overhead. + */ + cBufSize -= FUZZ_rand32(&seed, 0, 1); + cBuf = malloc(cBufSize); + + if (!cctx) { + cctx = ZSTD_createCCtx(); + FUZZ_ASSERT(cctx); + } + if (!dctx) { + dctx = ZSTD_createDCtx(); + FUZZ_ASSERT(dctx); + } + + { + size_t const result = + roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size); + FUZZ_ZASSERT(result); + FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size"); + FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!"); + } + free(rBuf); + free(cBuf); +#ifndef STATEFUL_FUZZING + ZSTD_freeCCtx(cctx); cctx = NULL; + ZSTD_freeDCtx(dctx); dctx = NULL; +#endif + return 0; +} diff --git a/tests/fuzz/fuzz.py b/tests/fuzz/fuzz.py index 8ce293a3a695..cd2a5b4d442e 100755 --- a/tests/fuzz/fuzz.py +++ b/tests/fuzz/fuzz.py @@ -34,6 +34,8 @@ def abs_join(a, *p): 'simple_decompress', 'stream_decompress', 'block_decompress', + 'dictionary_round_trip', + 'dictionary_decompress', ] ALL_TARGETS = TARGETS + ['all'] FUZZ_RNG_SEED_SIZE = 4 @@ -192,11 +194,21 @@ def build_parser(args): default=LIB_FUZZING_ENGINE, help=('The fuzzing engine to use e.g. /path/to/libFuzzer.a ' "(default: $LIB_FUZZING_ENGINE='{})".format(LIB_FUZZING_ENGINE))) - parser.add_argument( + + fuzz_group = parser.add_mutually_exclusive_group() + fuzz_group.add_argument( '--enable-coverage', dest='coverage', action='store_true', help='Enable coverage instrumentation (-fsanitize-coverage)') + fuzz_group.add_argument( + '--enable-fuzzer', + dest='fuzzer', + action='store_true', + help=('Enable clang fuzzer (-fsanitize=fuzzer). When enabled ' + 'LIB_FUZZING_ENGINE is ignored') + ) + parser.add_argument( '--enable-asan', dest='asan', action='store_true', help='Enable UBSAN') parser.add_argument( @@ -327,13 +339,13 @@ def build_parser(args): args = parse_env_flags(args, ' '.join( [args.cppflags, args.cflags, args.cxxflags, args.ldflags])) - # Check option sanitiy + # Check option sanity if args.msan and (args.asan or args.ubsan): raise RuntimeError('MSAN may not be used with any other sanitizers') if args.msan_track_origins and not args.msan: raise RuntimeError('--enable-msan-track-origins requires MSAN') if args.ubsan_pointer_overflow and not args.ubsan: - raise RuntimeError('--enable-ubsan-pointer-overlow requires UBSAN') + raise RuntimeError('--enable-ubsan-pointer-overflow requires UBSAN') if args.sanitize_recover and not args.sanitize: raise RuntimeError('--enable-sanitize-recover but no sanitizers used') @@ -364,13 +376,17 @@ def build(args): '-DFUZZ_RNG_SEED_SIZE={}'.format(args.fuzz_rng_seed_size), ] - mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)] - # Set flags for options + assert not (args.fuzzer and args.coverage) if args.coverage: common_flags += [ '-fsanitize-coverage=trace-pc-guard,indirect-calls,trace-cmp' ] + if args.fuzzer: + common_flags += ['-fsanitize=fuzzer'] + args.lib_fuzzing_engine = '' + + mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)] if args.sanitize_recover: recover_flags = ['-fsanitize-recover=all'] @@ -607,7 +623,7 @@ def regression(args): def gen_parser(args): description = """ - Generate a seed corpus appropiate for TARGET with data generated with + Generate a seed corpus appropriate for TARGET with data generated with decodecorpus. The fuzz inputs are prepended with a seed before the zstd data, so the output of decodecorpus shouldn't be used directly. diff --git a/tests/fuzz/fuzz_helpers.h b/tests/fuzz/fuzz_helpers.h index 468c39fb42d4..0cf79d0d7ce9 100644 --- a/tests/fuzz/fuzz_helpers.h +++ b/tests/fuzz/fuzz_helpers.h @@ -55,7 +55,7 @@ extern "C" { #endif /** - * Determininistically constructs a seed based on the fuzz input. + * Deterministically constructs a seed based on the fuzz input. * Consumes up to the first FUZZ_RNG_SEED_SIZE bytes of the input. */ FUZZ_STATIC uint32_t FUZZ_seed(uint8_t const **src, size_t* size) { diff --git a/tests/fuzz/regression_driver.c b/tests/fuzz/regression_driver.c index 1553d436ce03..658c685f4f89 100644 --- a/tests/fuzz/regression_driver.c +++ b/tests/fuzz/regression_driver.c @@ -40,8 +40,13 @@ int main(int argc, char const **argv) { size_t readSize; FILE *file; - /* Check that it is a regular file, and that the fileSize is valid */ - FUZZ_ASSERT_MSG(UTIL_isRegularFile(fileName), fileName); + /* Check that it is a regular file, and that the fileSize is valid. + * If it is not a regular file, then it may have been deleted since we + * constructed the list, so just skip it. + */ + if (!UTIL_isRegularFile(fileName)) { + continue; + } FUZZ_ASSERT_MSG(fileSize <= kMaxFileSize, fileName); /* Ensure we have a large enough buffer allocated */ if (fileSize > bufferSize) { diff --git a/tests/fuzz/simple_round_trip.c b/tests/fuzz/simple_round_trip.c index 83608b6e79ea..7e3b6609822f 100644 --- a/tests/fuzz/simple_round_trip.c +++ b/tests/fuzz/simple_round_trip.c @@ -25,9 +25,6 @@ static const int kMaxClevel = 19; static ZSTD_CCtx *cctx = NULL; static ZSTD_DCtx *dctx = NULL; -static void* cBuf = NULL; -static void* rBuf = NULL; -static size_t bufSize = 0; static uint32_t seed; static size_t roundTripTest(void *result, size_t resultCapacity, @@ -36,16 +33,8 @@ static size_t roundTripTest(void *result, size_t resultCapacity, { size_t cSize; if (FUZZ_rand(&seed) & 1) { - ZSTD_inBuffer in = {src, srcSize, 0}; - ZSTD_outBuffer out = {compressed, compressedCapacity, 0}; - size_t err; - - ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only); FUZZ_setRandomParameters(cctx, srcSize, &seed); - err = ZSTD_compressStream2(cctx, &out, &in, ZSTD_e_end); - FUZZ_ZASSERT(err); - FUZZ_ASSERT(err == 0); - cSize = out.pos; + cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize); } else { int const cLevel = FUZZ_rand(&seed) % kMaxClevel; cSize = ZSTD_compressCCtx( @@ -57,20 +46,21 @@ static size_t roundTripTest(void *result, size_t resultCapacity, int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) { - size_t neededBufSize; + size_t const rBufSize = size; + void* rBuf = malloc(rBufSize); + size_t cBufSize = ZSTD_compressBound(size); + void* cBuf; seed = FUZZ_seed(&src, &size); - neededBufSize = ZSTD_compressBound(size); + /* Half of the time fuzz with a 1 byte smaller output size. + * This will still succeed because we don't use a dictionary, so the dictID + * field is empty, giving us 4 bytes of overhead. + */ + cBufSize -= FUZZ_rand32(&seed, 0, 1); + cBuf = malloc(cBufSize); + + FUZZ_ASSERT(cBuf && rBuf); - /* Allocate all buffers and contexts if not already allocated */ - if (neededBufSize > bufSize) { - free(cBuf); - free(rBuf); - cBuf = malloc(neededBufSize); - rBuf = malloc(neededBufSize); - bufSize = neededBufSize; - FUZZ_ASSERT(cBuf && rBuf); - } if (!cctx) { cctx = ZSTD_createCCtx(); FUZZ_ASSERT(cctx); @@ -82,11 +72,13 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) { size_t const result = - roundTripTest(rBuf, neededBufSize, cBuf, neededBufSize, src, size); + roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size); FUZZ_ZASSERT(result); FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size"); FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!"); } + free(rBuf); + free(cBuf); #ifndef STATEFUL_FUZZING ZSTD_freeCCtx(cctx); cctx = NULL; ZSTD_freeDCtx(dctx); dctx = NULL; diff --git a/tests/fuzz/stream_decompress.c b/tests/fuzz/stream_decompress.c index 7ad571221dff..68e120d7ef6d 100644 --- a/tests/fuzz/stream_decompress.c +++ b/tests/fuzz/stream_decompress.c @@ -62,9 +62,8 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) if (!dstream) { dstream = ZSTD_createDStream(); FUZZ_ASSERT(dstream); - FUZZ_ASSERT(!ZSTD_isError(ZSTD_initDStream(dstream))); } else { - FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream))); + FUZZ_ZASSERT(ZSTD_DCtx_reset(dstream, ZSTD_reset_session_only)); } while (size > 0) { @@ -73,7 +72,6 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size) ZSTD_outBuffer out = makeOutBuffer(); size_t const rc = ZSTD_decompressStream(dstream, &out, &in); if (ZSTD_isError(rc)) goto error; - if (rc == 0) FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream))); } } diff --git a/tests/fuzz/stream_round_trip.c b/tests/fuzz/stream_round_trip.c index d903bcb29b11..d13c2dbe7e00 100644 --- a/tests/fuzz/stream_round_trip.c +++ b/tests/fuzz/stream_round_trip.c @@ -63,7 +63,7 @@ static size_t compress(uint8_t *dst, size_t capacity, ZSTD_inBuffer in = makeInBuffer(&src, &srcSize); /* Mode controls the action. If mode == -1 we pick a new mode */ int mode = -1; - while (in.pos < in.size) { + while (in.pos < in.size || mode != -1) { ZSTD_outBuffer out = makeOutBuffer(dst, capacity); /* Previous action finished, pick a new mode. */ if (mode == -1) mode = FUZZ_rand(&seed) % 10; diff --git a/tests/fuzz/zstd_helpers.c b/tests/fuzz/zstd_helpers.c index 10163e1512b0..9dff2895a9c0 100644 --- a/tests/fuzz/zstd_helpers.c +++ b/tests/fuzz/zstd_helpers.c @@ -8,10 +8,14 @@ */ #define ZSTD_STATIC_LINKING_ONLY +#define ZDICT_STATIC_LINKING_ONLY + +#include #include "zstd_helpers.h" #include "fuzz_helpers.h" #include "zstd.h" +#include "zdict.h" static void set(ZSTD_CCtx *cctx, ZSTD_cParameter param, int value) { @@ -71,8 +75,7 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state) setRand(cctx, ZSTD_c_contentSizeFlag, 0, 1, state); setRand(cctx, ZSTD_c_checksumFlag, 0, 1, state); setRand(cctx, ZSTD_c_dictIDFlag, 0, 1, state); - setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state); - /* Select long distance matchig parameters */ + /* Select long distance matching parameters */ setRand(cctx, ZSTD_c_enableLongDistanceMatching, 0, 1, state); setRand(cctx, ZSTD_c_ldmHashLog, ZSTD_HASHLOG_MIN, 16, state); setRand(cctx, ZSTD_c_ldmMinMatch, ZSTD_LDM_MINMATCH_MIN, @@ -81,4 +84,54 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state) state); setRand(cctx, ZSTD_c_ldmHashRateLog, ZSTD_LDM_HASHRATELOG_MIN, ZSTD_LDM_HASHRATELOG_MAX, state); + /* Set misc parameters */ + setRand(cctx, ZSTD_c_nbWorkers, 0, 2, state); + setRand(cctx, ZSTD_c_rsyncable, 0, 1, state); + setRand(cctx, ZSTD_c_forceMaxWindow, 0, 1, state); + setRand(cctx, ZSTD_c_literalCompressionMode, 0, 2, state); + setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state); +} + +FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state) +{ + size_t const dictSize = MAX(srcSize / 8, 1024); + size_t const totalSampleSize = dictSize * 11; + FUZZ_dict_t dict = { malloc(dictSize), dictSize }; + char* const samples = (char*)malloc(totalSampleSize); + unsigned nbSamples = 100; + size_t* const samplesSizes = (size_t*)malloc(sizeof(size_t) * nbSamples); + size_t pos = 0; + size_t sample = 0; + ZDICT_fastCover_params_t params; + FUZZ_ASSERT(dict.buff && samples && samplesSizes); + + for (sample = 0; sample < nbSamples; ++sample) { + size_t const remaining = totalSampleSize - pos; + size_t const offset = FUZZ_rand32(state, 0, MAX(srcSize, 1) - 1); + size_t const limit = MIN(srcSize - offset, remaining); + size_t const toCopy = MIN(limit, remaining / (nbSamples - sample)); + memcpy(samples + pos, src + offset, toCopy); + pos += toCopy; + samplesSizes[sample] = toCopy; + + } + memset(samples + pos, 0, totalSampleSize - pos); + + memset(¶ms, 0, sizeof(params)); + params.accel = 5; + params.k = 40; + params.d = 8; + params.f = 14; + params.zParams.compressionLevel = 1; + dict.size = ZDICT_trainFromBuffer_fastCover(dict.buff, dictSize, + samples, samplesSizes, nbSamples, params); + if (ZSTD_isError(dict.size)) { + free(dict.buff); + memset(&dict, 0, sizeof(dict)); + } + + free(samplesSizes); + free(samples); + + return dict; } diff --git a/tests/fuzz/zstd_helpers.h b/tests/fuzz/zstd_helpers.h index 3856bebecf7e..457e6e995f0d 100644 --- a/tests/fuzz/zstd_helpers.h +++ b/tests/fuzz/zstd_helpers.h @@ -14,6 +14,8 @@ #ifndef ZSTD_HELPERS_H #define ZSTD_HELPERS_H +#define ZSTD_STATIC_LINKING_ONLY + #include "zstd.h" #include @@ -27,6 +29,17 @@ ZSTD_compressionParameters FUZZ_randomCParams(size_t srcSize, uint32_t *state); ZSTD_frameParameters FUZZ_randomFParams(uint32_t *state); ZSTD_parameters FUZZ_randomParams(size_t srcSize, uint32_t *state); +typedef struct { + void* buff; + size_t size; +} FUZZ_dict_t; + +/* Quickly train a dictionary from a source for fuzzing. + * NOTE: Don't use this to train production dictionaries, it is only optimized + * for speed, and doesn't care about dictionary quality. + */ +FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state); + #ifdef __cplusplus } diff --git a/tests/fuzzer.c b/tests/fuzzer.c index 946844e1614a..1a31c78e2922 100644 --- a/tests/fuzzer.c +++ b/tests/fuzzer.c @@ -38,6 +38,7 @@ #define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ #include "xxhash.h" /* XXH64 */ #include "util.h" +#include "timefn.h" /* SEC_TO_MICRO, UTIL_time_t, UTIL_TIME_INITIALIZER, UTIL_clockSpanMicro, UTIL_getTime */ /*-************************************ @@ -124,12 +125,14 @@ static U32 FUZ_highbit32(U32 v32) #define CHECK(fn) { CHECK_V(err, fn); } #define CHECKPLUS(var, fn, more) { CHECK_V(var, fn); more; } -#define CHECK_EQ(lhs, rhs) { \ - if ((lhs) != (rhs)) { \ - DISPLAY("Error L%u => %s != %s ", __LINE__, #lhs, #rhs); \ +#define CHECK_OP(op, lhs, rhs) { \ + if (!((lhs) op (rhs))) { \ + DISPLAY("Error L%u => FAILED %s %s %s ", __LINE__, #lhs, #op, #rhs); \ goto _output_error; \ } \ } +#define CHECK_EQ(lhs, rhs) CHECK_OP(==, lhs, rhs) +#define CHECK_LT(lhs, rhs) CHECK_OP(<, lhs, rhs) /*============================================= @@ -374,6 +377,20 @@ static int basicUnitTests(U32 seed, double compressibility) } DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : tight ZSTD_decompressBound test : ", testNb++); + { + unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize); + if (bound != CNBuffSize) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with invalid srcSize : ", testNb++); + { + unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize - 1); + if (bound != ZSTD_CONTENTSIZE_ERROR) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : decompress %u bytes : ", testNb++, (unsigned)CNBuffSize); { size_t const r = ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize); if (r != CNBuffSize) goto _output_error; } @@ -429,6 +446,27 @@ static int basicUnitTests(U32 seed, double compressibility) if (ZSTD_getErrorCode(r) != ZSTD_error_srcSize_wrong) goto _output_error; } DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with content size missing : ", testNb++); + { /* create compressed buffer with content size missing */ + ZSTD_CCtx* cctx = ZSTD_createCCtx(); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_contentSizeFlag, 0) ); + CHECKPLUS(r, ZSTD_compress2(cctx, + compressedBuffer, compressedBufferSize, + CNBuffer, CNBuffSize), + cSize=r ); + ZSTD_freeCCtx(cctx); + } + { /* ensure frame content size is missing */ + ZSTD_frameHeader zfh; + size_t const ret = ZSTD_getFrameHeader(&zfh, compressedBuffer, compressedBufferSize); + if (ret != 0 || zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) goto _output_error; + } + { /* ensure CNBuffSize <= decompressBound */ + unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, compressedBufferSize); + if (CNBuffSize > bound) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3d : check CCtx size after compressing empty input : ", testNb++); { ZSTD_CCtx* const cctx = ZSTD_createCCtx(); size_t const r = ZSTD_compressCCtx(cctx, compressedBuffer, compressedBufferSize, NULL, 0, 19); @@ -828,6 +866,59 @@ static int basicUnitTests(U32 seed, double compressibility) ZSTDMT_freeCCtx(mtctx); } + DISPLAYLEVEL(3, "test%3i : compress -T2 with/without literals compression : ", testNb++) + { ZSTD_CCtx* cctx = ZSTD_createCCtx(); + size_t cSize1, cSize2; + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) ); + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 2) ); + cSize1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize); + CHECK(cSize1); + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_literalCompressionMode, ZSTD_lcm_uncompressed) ); + cSize2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize); + CHECK(cSize2); + CHECK_LT(cSize1, cSize2); + ZSTD_freeCCtx(cctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Multithreaded ZSTD_compress2() with rsyncable : ", testNb++) + { ZSTD_CCtx* cctx = ZSTD_createCCtx(); + /* Set rsyncable and don't give the ZSTD_compressBound(CNBuffSize) so + * ZSTDMT is forced to not take the shortcut. + */ + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) ); + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 1) ); + CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_rsyncable, 1) ); + CHECK( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize - 1, CNBuffer, CNBuffSize) ); + ZSTD_freeCCtx(cctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : setting multithreaded parameters : ", testNb++) + { ZSTD_CCtx_params* params = ZSTD_createCCtxParams(); + int value; + /* Check that the overlap log and job size are unset. */ + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) ); + CHECK_EQ(value, 0); + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) ); + CHECK_EQ(value, 0); + /* Set and check the overlap log and job size. */ + CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, 5) ); + CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, 2 MB) ); + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) ); + CHECK_EQ(value, 5); + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) ); + CHECK_EQ(value, 2 MB); + /* Set the number of workers and check the overlap log and job size. */ + CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, 2) ); + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) ); + CHECK_EQ(value, 5); + CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) ); + CHECK_EQ(value, 2 MB); + ZSTD_freeCCtxParams(params); + + } + DISPLAYLEVEL(3, "OK \n"); /* Simple API multiframe test */ DISPLAYLEVEL(3, "test%3i : compress multiple frames : ", testNb++); @@ -859,6 +950,11 @@ static int basicUnitTests(U32 seed, double compressibility) if (r != CNBuffSize / 2) goto _output_error; } DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : get tight decompressed bound of multiple frames : ", testNb++); + { unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, cSize); + if (bound != CNBuffSize / 2) goto _output_error; } + DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : decompress multiple frames : ", testNb++); { CHECK_V(r, ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize)); if (r != CNBuffSize / 2) goto _output_error; } @@ -1203,9 +1299,13 @@ static int basicUnitTests(U32 seed, double compressibility) { size_t ret; MEM_writeLE32((char*)dictBuffer+2, ZSTD_MAGIC_DICTIONARY); + /* Either operation is allowed to fail, but one must fail. */ ret = ZSTD_CCtx_loadDictionary_advanced( cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_auto); - if (!ZSTD_isError(ret)) goto _output_error; + if (!ZSTD_isError(ret)) { + ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)); + if (!ZSTD_isError(ret)) goto _output_error; + } } DISPLAYLEVEL(3, "OK \n"); @@ -1216,6 +1316,187 @@ static int basicUnitTests(U32 seed, double compressibility) ret = ZSTD_CCtx_loadDictionary_advanced( cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_rawContent); if (ZSTD_isError(ret)) goto _output_error; + ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)); + if (ZSTD_isError(ret)) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_CCtx_refCDict() then set parameters : ", testNb++); + { ZSTD_CDict* const cdict = ZSTD_createCDict(CNBuffer, dictSize, 1); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) ); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 )); + CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) ); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) ); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 )); + ZSTD_freeCDict(cdict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading dictionary before setting parameters is the same as loading after : ", testNb++); + { + size_t size1, size2; + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) ); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) ); + size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size1)) goto _output_error; + + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) ); + CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) ); + size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size2)) goto _output_error; + + if (size1 != size2) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the prefix : ", testNb++); + { + CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the cdict : ", testNb++); + { + ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1); + CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) ); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + ZSTD_freeCDict(cdict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the prefix : ", testNb++); + { + ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1); + CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + ZSTD_freeCDict(cdict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the dictionary : ", testNb++); + { + ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + ZSTD_freeCDict(cdict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the dictionary : ", testNb++); + { + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the cdict : ", testNb++); + { + ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1); + CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) ); + CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) ); + CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) ); + ZSTD_freeCDict(cdict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loaded dictionary persists across reset session : ", testNb++); + { + size_t size1, size2; + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) ); + size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size1)) goto _output_error; + + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only); + size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size2)) goto _output_error; + + if (size1 != size2) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : Loaded dictionary is cleared after resetting parameters : ", testNb++); + { + size_t size1, size2; + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) ); + size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size1)) goto _output_error; + + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + if (ZSTD_isError(size2)) goto _output_error; + + if (size1 == size2) goto _output_error; + } + DISPLAYLEVEL(3, "OK \n"); + + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, dictBuffer, dictSize) ); + cSize = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB)); + CHECK_Z(cSize); + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with dictionary : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + size_t ret; + /* We should fail to decompress without a dictionary. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize); + if (!ZSTD_isError(ret)) goto _output_error; + /* We should succeed to decompress with the dictionary. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictBuffer, dictSize) ); + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) ); + /* The dictionary should presist across calls. */ + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) ); + /* When we reset the context the dictionary is cleared. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize); + if (!ZSTD_isError(ret)) goto _output_error; + ZSTD_freeDCtx(dctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with ddict : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + ZSTD_DDict* ddict = ZSTD_createDDict(dictBuffer, dictSize); + size_t ret; + /* We should succeed to decompress with the ddict. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_refDDict(dctx, ddict) ); + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) ); + /* The ddict should presist across calls. */ + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) ); + /* When we reset the context the ddict is cleared. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize); + if (!ZSTD_isError(ret)) goto _output_error; + ZSTD_freeDCtx(dctx); + ZSTD_freeDDict(ddict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with prefix : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + size_t ret; + /* We should succeed to decompress with the prefix. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_refPrefix_advanced(dctx, dictBuffer, dictSize, ZSTD_dct_auto) ); + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) ); + /* The prefix should be cleared after the first compression. */ + ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize); + if (!ZSTD_isError(ret)) goto _output_error; + ZSTD_freeDCtx(dctx); } DISPLAYLEVEL(3, "OK \n"); diff --git a/tests/legacy.c b/tests/legacy.c index e1cf82f2f9d8..eb329203833f 100644 --- a/tests/legacy.c +++ b/tests/legacy.c @@ -16,10 +16,11 @@ /*=========================================== * Dependencies *==========================================*/ -#include /* size_t */ -#include /* malloc, free */ -#include /* fprintf */ -#include /* strlen */ +#include /* size_t */ +#include /* malloc, free */ +#include /* fprintf */ +#include /* strlen */ +#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_decompressBound */ #include "zstd.h" #include "zstd_errors.h" @@ -74,6 +75,7 @@ static int testSimpleAPI(void) static int testStreamingAPI(void) { + int error_code = 0; size_t const outBuffSize = ZSTD_DStreamOutSize(); char* const outBuff = malloc(outBuffSize); ZSTD_DStream* const stream = ZSTD_createDStream(); @@ -87,6 +89,7 @@ static int testStreamingAPI(void) } if (stream == NULL) { DISPLAY("ERROR: Could not create dstream\n"); + free(outBuff); return 1; } @@ -96,13 +99,15 @@ static int testStreamingAPI(void) size_t const ret = ZSTD_initDStream(stream); if (ZSTD_isError(ret)) { DISPLAY("ERROR: ZSTD_initDStream: %s\n", ZSTD_getErrorName(ret)); - return 1; + error_code = 1; + break; } } { size_t const ret = ZSTD_decompressStream(stream, &output, &input); if (ZSTD_isError(ret)) { DISPLAY("ERROR: ZSTD_decompressStream: %s\n", ZSTD_getErrorName(ret)); - return 1; + error_code = 1; + break; } if (ret == 0) { @@ -111,7 +116,8 @@ static int testStreamingAPI(void) if (memcmp(outBuff, EXPECTED + outputPos, output.pos) != 0) { DISPLAY("ERROR: Wrong decoded output produced\n"); - return 1; + error_code = 1; + break; } outputPos += output.pos; if (input.pos == input.size && output.pos < output.size) { @@ -121,7 +127,34 @@ static int testStreamingAPI(void) free(outBuff); ZSTD_freeDStream(stream); - DISPLAY("Streaming API OK\n"); + if (error_code == 0) DISPLAY("Streaming API OK\n"); + return error_code; +} + +static int testFrameDecoding(void) +{ + if (strlen(EXPECTED) > ZSTD_decompressBound(COMPRESSED, COMPRESSED_SIZE)) { + DISPLAY("ERROR: ZSTD_decompressBound: decompressed bound too small\n"); + return 1; + } + { const char* ip = COMPRESSED; + size_t remainingSize = COMPRESSED_SIZE; + while (1) { + size_t frameSize = ZSTD_findFrameCompressedSize(ip, remainingSize); + if (ZSTD_isError(frameSize)) { + DISPLAY("ERROR: ZSTD_findFrameCompressedSize: %s\n", ZSTD_getErrorName(frameSize)); + return 1; + } + if (frameSize > remainingSize) { + DISPLAY("ERROR: ZSTD_findFrameCompressedSize: expected frameSize to align with src buffer"); + return 1; + } + ip += frameSize; + remainingSize -= frameSize; + if (remainingSize == 0) break; + } + } + DISPLAY("Frame Decoding OK\n"); return 0; } @@ -131,6 +164,8 @@ int main(void) if (ret) return ret; } { int const ret = testStreamingAPI(); if (ret) return ret; } + { int const ret = testFrameDecoding(); + if (ret) return ret; } DISPLAY("OK\n"); return 0; diff --git a/tests/paramgrill.c b/tests/paramgrill.c index 415551b9578d..75c179a0ba0e 100644 --- a/tests/paramgrill.c +++ b/tests/paramgrill.c @@ -19,6 +19,7 @@ #include /* log */ #include +#include "timefn.h" /* SEC_TO_MICRO, UTIL_time_t, UTIL_clockSpanMicro, UTIL_clockSpanNano, UTIL_getTime */ #include "mem.h" #define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters, ZSTD_estimateCCtxSize */ #include "zstd.h" @@ -141,7 +142,7 @@ static const char* g_shortParamNames[NUM_PARAMS] = /* maps value from { 0 to rangetable[param] - 1 } to valid paramvalues */ static U32 rangeMap(varInds_t param, int ind) { - ind = MAX(MIN(ind, (int)rangetable[param] - 1), 0); + U32 const uind = (U32)MAX(MIN(ind, (int)rangetable[param] - 1), 0); switch(param) { case wlog_ind: /* using default: triggers -Wswitch-enum */ case clog_ind: @@ -149,11 +150,11 @@ static U32 rangeMap(varInds_t param, int ind) case slog_ind: case mml_ind: case strt_ind: - return mintable[param] + ind; + return mintable[param] + uind; case tlen_ind: - return tlen_table[ind]; + return tlen_table[uind]; case fadt_ind: /* 0, 1, 2 -> -1, 0, 1 */ - return ind - 1; + return uind - 1; case NUM_PARAMS: default:; } @@ -173,7 +174,7 @@ static int invRangeMap(varInds_t param, U32 value) case slog_ind: case mml_ind: case strt_ind: - return value - mintable[param]; + return (int)(value - mintable[param]); case tlen_ind: /* bin search */ { int lo = 0; @@ -493,13 +494,15 @@ static void paramVariation(paramValues_t* ptr, memoTable_t* mtAll, const U32 nbChanges) { paramValues_t p; - U32 validated = 0; + int validated = 0; while (!validated) { U32 i; p = *ptr; for (i = 0 ; i < nbChanges ; i++) { const U32 changeID = (U32)FUZ_rand(&g_rand) % (mtAll[p.vals[strt_ind]].varLen << 1); - paramVaryOnce(mtAll[p.vals[strt_ind]].varArray[changeID >> 1], ((changeID & 1) << 1) - 1, &p); + paramVaryOnce(mtAll[p.vals[strt_ind]].varArray[changeID >> 1], + (int)((changeID & 1) << 1) - 1, + &p); } validated = paramValid(p); } @@ -511,7 +514,7 @@ static paramValues_t randomParams(void) { varInds_t v; paramValues_t p; for(v = 0; v < NUM_PARAMS; v++) { - p.vals[v] = rangeMap(v, FUZ_rand(&g_rand) % rangetable[v]); + p.vals[v] = rangeMap(v, (int)(FUZ_rand(&g_rand) % rangetable[v])); } return p; } @@ -1232,7 +1235,7 @@ static int createBuffersFromMemory(buffers_t* buff, void * srcBuffer, const size return 0; } -/* allocates buffer's arguments. returns success / failuere */ +/* allocates buffer's arguments. returns success / failure */ static int createBuffers(buffers_t* buff, const char* const * const fileNamesTable, size_t nbFiles) { size_t pos = 0; @@ -1505,7 +1508,7 @@ createMemoTableArray(const paramValues_t p, } /* Sets pc to random unmeasured set of parameters */ -/* specifiy strategy */ +/* specify strategy */ static void randomConstrainedParams(paramValues_t* pc, const memoTable_t* memoTableArray, const ZSTD_strategy st) { size_t j; @@ -1570,7 +1573,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx, display_params_tested(*comprParams); memset(&bResult, 0, sizeof(bResult)); - /* warmimg up memory */ + /* warming up memory */ for (i = 0; i < buf.nbBlocks; i++) { if (mode != BMK_decodeOnly) { RDG_genBuffer(dstPtrs[i], dstCapacities[i], 0.10, 0.50, 1); @@ -1638,7 +1641,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx, return bOut; } { BMK_runTime_t const rResult = BMK_extract_runTime(cOutcome); - bResult.cSpeed = (srcSize * TIMELOOP_NANOSEC) / rResult.nanoSecPerRun; + bResult.cSpeed = (unsigned long long)((double)srcSize * TIMELOOP_NANOSEC / rResult.nanoSecPerRun); bResult.cSize = rResult.sumOfReturn; } compressionCompleted = BMK_isCompleted_TimedFn(timeStateCompress); @@ -1656,7 +1659,7 @@ BMK_benchMemInvertible( buffers_t buf, contexts_t ctx, return bOut; } { BMK_runTime_t const rResult = BMK_extract_runTime(dOutcome); - bResult.dSpeed = (srcSize * TIMELOOP_NANOSEC) / rResult.nanoSecPerRun; + bResult.dSpeed = (unsigned long long)((double)srcSize * TIMELOOP_NANOSEC / rResult.nanoSecPerRun); } decompressionCompleted = BMK_isCompleted_TimedFn(timeStateDecompress); } @@ -1989,7 +1992,7 @@ BMK_selectRandomStart( FILE* f, /* BMK_generate_cLevelTable() : * test a large number of configurations - * and distribute them accross compression levels according to speed conditions. + * and distribute them across compression levels according to speed conditions. * display and save all intermediate results into rfName = "grillResults.txt". * the function automatically stops after g_timeLimit_s. * this function cannot error, it directly exit() in case of problem. @@ -2199,7 +2202,9 @@ static winnerInfo_t climbOnce(const constraint_t target, for (offset = -1; offset <= 1; offset += 2) { CHECKTIME(winnerInfo); candidateInfo.params = cparam; - paramVaryOnce(mtAll[cparam.vals[strt_ind]].varArray[i], offset, &candidateInfo.params); + paramVaryOnce(mtAll[cparam.vals[strt_ind]].varArray[i], + offset, + &candidateInfo.params); if(paramValid(candidateInfo.params)) { int res; @@ -2265,7 +2270,7 @@ static winnerInfo_t climbOnce(const constraint_t target, /* Optimizes for a fixed strategy */ -/* flexible parameters: iterations of failed climbing (or if we do non-random, maybe this is when everything is close to visitied) +/* flexible parameters: iterations of failed climbing (or if we do non-random, maybe this is when everything is close to visited) weight more on visit for bad results, less on good results/more on later results / ones with more failures. allocate memoTable here. */ @@ -2351,7 +2356,7 @@ static int nextStrategy(const int currentStrategy, const int bestStrategy) * cLevel - compression level to exceed (all solutions must be > lvl in cSpeed + ratio) */ -static int g_maxTries = 5; +static unsigned g_maxTries = 5; #define TRY_DECAY 1 static int @@ -2561,7 +2566,7 @@ optimizeForSize(const char* const * const fileNamesTable, const size_t nbFiles, * @return 0 and doesn't modify *stringPtr otherwise. * from zstdcli.c */ -static unsigned longCommandWArg(const char** stringPtr, const char* longCommand) +static int longCommandWArg(const char** stringPtr, const char* longCommand) { size_t const comSize = strlen(longCommand); int const result = !strncmp(*stringPtr, longCommand, comSize); @@ -2588,7 +2593,10 @@ static unsigned readU32FromChar(const char** stringPtr) while ((**stringPtr >='0') && (**stringPtr <='9')) { unsigned const max = (((unsigned)(-1)) / 10) - 1; if (result > max) errorOut(errorMsg); - result *= 10, result += **stringPtr - '0', (*stringPtr)++ ; + result *= 10; + assert(**stringPtr >= '0'); + result += (unsigned)(**stringPtr - '0'); + (*stringPtr)++ ; } if ((**stringPtr=='K') || (**stringPtr=='M')) { unsigned const maxK = ((unsigned)(-1)) >> 10; @@ -2726,7 +2734,7 @@ int main(int argc, const char** argv) PARSE_SUB_ARGS("strict=", "stc=", g_strictness); PARSE_SUB_ARGS("maxTries=", "tries=", g_maxTries); PARSE_SUB_ARGS("memoLimitLog=", "memLog=", memoTableLog); - if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelOpt = readU32FromChar(&argument); g_optmode = 1; if (argument[0]==',') { argument++; continue; } else break; } + if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelOpt = (int)readU32FromChar(&argument); g_optmode = 1; if (argument[0]==',') { argument++; continue; } else break; } if (longCommandWArg(&argument, "speedForRatio=") || longCommandWArg(&argument, "speedRatio=")) { g_ratioMultiplier = readDoubleFromChar(&argument); if (argument[0]==',') { argument++; continue; } else break; } DISPLAY("invalid optimization parameter \n"); @@ -2743,7 +2751,7 @@ int main(int argc, const char** argv) g_singleRun = 1; for ( ; ;) { if(parse_params(&argument, &g_params)) { if(argument[0] == ',') { argument++; continue; } else break; } - if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelRun = readU32FromChar(&argument); g_params = emptyParams(); if (argument[0]==',') { argument++; continue; } else break; } + if (longCommandWArg(&argument, "level=") || longCommandWArg(&argument, "lvl=")) { cLevelRun = (int)readU32FromChar(&argument); g_params = emptyParams(); if (argument[0]==',') { argument++; continue; } else break; } DISPLAY("invalid compression parameter \n"); return 1; @@ -2855,7 +2863,7 @@ int main(int argc, const char** argv) continue; case 'L': { argument++; - cLevelRun = readU32FromChar(&argument); + cLevelRun = (int)readU32FromChar(&argument); g_params = emptyParams(); continue; } @@ -2944,7 +2952,8 @@ int main(int argc, const char** argv) } } else { if (g_optimizer) { - result = optimizeForSize(argv+filenamesStart, argc-filenamesStart, dictFileName, target, paramTarget, cLevelOpt, cLevelRun, memoTableLog); + assert(filenamesStart < argc); + result = optimizeForSize(argv+filenamesStart, (size_t)(argc-filenamesStart), dictFileName, target, paramTarget, cLevelOpt, cLevelRun, memoTableLog); } else { result = benchFiles(argv+filenamesStart, argc-filenamesStart, dictFileName, cLevelRun); } diff --git a/tests/playTests.sh b/tests/playTests.sh index ef4861b52917..bce2710159ed 100755 --- a/tests/playTests.sh +++ b/tests/playTests.sh @@ -49,7 +49,7 @@ fileRoundTripTest() { } truncateLastByte() { - dd bs=1 count=$(($(wc -c < "$1") - 1)) if="$1" status=none + dd bs=1 count=$(($(wc -c < "$1") - 1)) if="$1" } UNAME=$(uname) @@ -200,6 +200,15 @@ $ZSTD tmp -fo tmp && die "zstd compression overwrote the input file" $ZSTD tmp.zst -dfo tmp.zst && die "zstd decompression overwrote the input file" $ECHO "test: detect that input file does not exist" $ZSTD nothere && die "zstd hasn't detected that input file does not exist" +$ECHO "test: --[no-]compress-literals" +$ZSTD tmp -c --no-compress-literals -1 | $ZSTD -t +$ZSTD tmp -c --no-compress-literals --fast=1 | $ZSTD -t +$ZSTD tmp -c --no-compress-literals -19 | $ZSTD -t +$ZSTD tmp -c --compress-literals -1 | $ZSTD -t +$ZSTD tmp -c --compress-literals --fast=1 | $ZSTD -t +$ZSTD tmp -c --compress-literals -19 | $ZSTD -t +$ZSTD -b --fast=1 -i1e1 tmp --compress-literals +$ZSTD -b --fast=1 -i1e1 tmp --no-compress-literals $ECHO "test : file removal" $ZSTD -f --rm tmp @@ -314,18 +323,28 @@ $ECHO foo | $ZSTD > /dev/full && die "write error not detected!" $ECHO "$ECHO foo | $ZSTD | $ZSTD -d > /dev/full" $ECHO foo | $ZSTD | $ZSTD -d > /dev/full && die "write error not detected!" +fi + + +if [ "$isWindows" = false ] && [ "$UNAME" != 'SunOS' ] ; then $ECHO "\n===> symbolic link test " -rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst +rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst $ECHO "hello world" > hello.tmp ln -s hello.tmp world.tmp -$ZSTD world.tmp hello.tmp +ln -s hello.tmp world2.tmp +$ZSTD world.tmp hello.tmp || true test -f hello.tmp.zst # regular file should have been compressed! test ! -f world.tmp.zst # symbolic link should not have been compressed! +$ZSTD world.tmp || true +test ! -f world.tmp.zst # symbolic link should not have been compressed! +$ZSTD world.tmp world2.tmp || true +test ! -f world.tmp.zst # symbolic link should not have been compressed! +test ! -f world2.tmp.zst # symbolic link should not have been compressed! $ZSTD world.tmp hello.tmp -f test -f world.tmp.zst # symbolic link should have been compressed with --force -rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst +rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst fi @@ -391,6 +410,8 @@ $ECHO "- Create first dictionary " TESTFILE=../programs/zstdcli.c $ZSTD --train *.c ../programs/*.c -o tmpDict cp $TESTFILE tmp +$ECHO "- Test dictionary compression with tmpDict as an input file and dictionary" +$ZSTD -f tmpDict -D tmpDict && die "compression error not detected!" $ECHO "- Dictionary compression roundtrip" $ZSTD -f tmp -D tmpDict $ZSTD -d tmp.zst -D tmpDict -fo result @@ -809,6 +830,19 @@ $ZSTD --list tmp* && die "-l must fail on non-zstd file" $ZSTD -lv tmp1* && die "-l must fail on non-zstd file" $ZSTD --list -v tmp2 tmp12.zst && die "-l must fail on non-zstd file" +$ECHO "test : detect truncated compressed file " +TEST_DATA_FILE=truncatable-input.txt +FULL_COMPRESSED_FILE=${TEST_DATA_FILE}.zst +TRUNCATED_COMPRESSED_FILE=truncated-input.txt.zst +./datagen -g50000 > $TEST_DATA_FILE +$ZSTD -f $TEST_DATA_FILE -o $FULL_COMPRESSED_FILE +dd bs=1 count=100 if=$FULL_COMPRESSED_FILE of=$TRUNCATED_COMPRESSED_FILE +$ZSTD --list $TRUNCATED_COMPRESSED_FILE && die "-l must fail on truncated file" + +rm $TEST_DATA_FILE +rm $FULL_COMPRESSED_FILE +rm $TRUNCATED_COMPRESSED_FILE + $ECHO "\n===> zstd --list/-l errors when presented with stdin / no files" $ZSTD -l && die "-l must fail on empty list of files" $ZSTD -l - && die "-l does not work on stdin" diff --git a/tests/poolTests.c b/tests/poolTests.c index 8b9a4700229d..272e961d3800 100644 --- a/tests/poolTests.c +++ b/tests/poolTests.c @@ -12,6 +12,7 @@ #include "pool.h" #include "threading.h" #include "util.h" +#include "timefn.h" #include #include @@ -25,25 +26,27 @@ #define ASSERT_EQ(lhs, rhs) ASSERT_TRUE((lhs) == (rhs)) struct data { - pthread_mutex_t mutex; + ZSTD_pthread_mutex_t mutex; unsigned data[16]; size_t i; }; -static void fn(void *opaque) { +static void fn(void *opaque) +{ struct data *data = (struct data *)opaque; ZSTD_pthread_mutex_lock(&data->mutex); - data->data[data->i] = data->i; + data->data[data->i] = (unsigned)(data->i); ++data->i; ZSTD_pthread_mutex_unlock(&data->mutex); } -static int testOrder(size_t numThreads, size_t queueSize) { +static int testOrder(size_t numThreads, size_t queueSize) +{ struct data data; - POOL_ctx *ctx = POOL_create(numThreads, queueSize); + POOL_ctx* const ctx = POOL_create(numThreads, queueSize); ASSERT_TRUE(ctx); data.i = 0; - ZSTD_pthread_mutex_init(&data.mutex, NULL); + (void)ZSTD_pthread_mutex_init(&data.mutex, NULL); { size_t i; for (i = 0; i < 16; ++i) { POOL_add(ctx, &fn, &data); @@ -71,7 +74,7 @@ static void waitFn(void *opaque) { /* Tests for deadlock */ static int testWait(size_t numThreads, size_t queueSize) { struct data data; - POOL_ctx *ctx = POOL_create(numThreads, queueSize); + POOL_ctx* const ctx = POOL_create(numThreads, queueSize); ASSERT_TRUE(ctx); { size_t i; for (i = 0; i < 16; ++i) { @@ -93,7 +96,7 @@ typedef struct { } poolTest_t; static void waitLongFn(void *opaque) { - poolTest_t* test = (poolTest_t*) opaque; + poolTest_t* const test = (poolTest_t*) opaque; UTIL_sleepMilli(10); ZSTD_pthread_mutex_lock(&test->mut); test->val = test->val + 1; diff --git a/tests/regression/config.c b/tests/regression/config.c index 8a6103b2929e..b82482f46123 100644 --- a/tests/regression/config.c +++ b/tests/regression/config.c @@ -90,6 +90,17 @@ static config_t mt_ldm = { .param_values = PARAM_VALUES(mt_ldm_param_values), }; +static param_value_t mt_advanced_param_values[] = { + {.param = ZSTD_c_nbWorkers, .value = 2}, + {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed}, +}; + +static config_t mt_advanced = { + .name = "multithreaded with advanced params", + .cli_args = "-T2 --no-compress-literals", + .param_values = PARAM_VALUES(mt_advanced_param_values), +}; + static param_value_t const small_wlog_param_values[] = { {.param = ZSTD_c_windowLog, .value = 10}, }; @@ -122,6 +133,39 @@ static config_t small_clog = { .param_values = PARAM_VALUES(small_clog_param_values), }; +static param_value_t const uncompressed_literals_param_values[] = { + {.param = ZSTD_c_compressionLevel, .value = 3}, + {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed}, +}; + +static config_t uncompressed_literals = { + .name = "uncompressed literals", + .cli_args = "-3 --no-compress-literals", + .param_values = PARAM_VALUES(uncompressed_literals_param_values), +}; + +static param_value_t const uncompressed_literals_opt_param_values[] = { + {.param = ZSTD_c_compressionLevel, .value = 19}, + {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed}, +}; + +static config_t uncompressed_literals_opt = { + .name = "uncompressed literals optimal", + .cli_args = "-19 --no-compress-literals", + .param_values = PARAM_VALUES(uncompressed_literals_opt_param_values), +}; + +static param_value_t const huffman_literals_param_values[] = { + {.param = ZSTD_c_compressionLevel, .value = -1}, + {.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_huffman}, +}; + +static config_t huffman_literals = { + .name = "huffman literals", + .cli_args = "--fast=1 --compress-literals", + .param_values = PARAM_VALUES(huffman_literals_param_values), +}; + static param_value_t const explicit_params_param_values[] = { {.param = ZSTD_c_checksumFlag, .value = 1}, {.param = ZSTD_c_contentSizeFlag, .value = 0}, @@ -155,6 +199,10 @@ static config_t const* g_configs[] = { &small_hlog, &small_clog, &explicit_params, + &uncompressed_literals, + &uncompressed_literals_opt, + &huffman_literals, + &mt_advanced, NULL, }; diff --git a/tests/regression/method.c b/tests/regression/method.c index 51a0fb9d14f0..1e84021c3ef3 100644 --- a/tests/regression/method.c +++ b/tests/regression/method.c @@ -175,8 +175,8 @@ static result_t compress_cctx_compress( state->compressed.capacity, input.data, input.size, - state->dictionary.data, - state->dictionary.size, + config->use_dictionary ? state->dictionary.data : NULL, + config->use_dictionary ? state->dictionary.size : 0, params); else if (config->use_dictionary) state->compressed.size = ZSTD_compress_usingDict( @@ -432,77 +432,158 @@ static result_t advanced_streaming_compress( return result; } -static result_t old_streaming_compress( - method_state_t* base, - config_t const* config) { - buffer_state_t* state = container_of(base, buffer_state_t, base); - - if (buffer_state_bad(state, config)) - return result_error(result_error_system_error); - - int const level = config_get_level(config); - if (level == CONFIG_NO_LEVEL) - return result_error(result_error_skip); - - ZSTD_CStream* zcs = ZSTD_createCStream(); - result_t result; - if (zcs == NULL) { - result = result_error(result_error_compression_error); - goto out; - } +static int init_cstream( + buffer_state_t* state, + ZSTD_CStream* zcs, + config_t const* config, + int const advanced, + ZSTD_CDict** cdict) +{ size_t zret; - if (config->use_dictionary) { - zret = ZSTD_initCStream_usingDict( - zcs, state->dictionary.data, state->dictionary.size, level); + if (advanced) { + ZSTD_parameters const params = config_get_zstd_params(config, 0, 0); + ZSTD_CDict* dict = NULL; + if (cdict) { + *cdict = ZSTD_createCDict_advanced( + state->dictionary.data, + state->dictionary.size, + ZSTD_dlm_byRef, + ZSTD_dct_auto, + params.cParams, + ZSTD_defaultCMem); + if (!*cdict) { + return 1; + } + zret = ZSTD_initCStream_usingCDict_advanced( + zcs, *cdict, params.fParams, ZSTD_CONTENTSIZE_UNKNOWN); + } else { + zret = ZSTD_initCStream_advanced( + zcs, + state->dictionary.data, + state->dictionary.size, + params, + ZSTD_CONTENTSIZE_UNKNOWN); + } } else { - zret = ZSTD_initCStream(zcs, level); + int const level = config_get_level(config); + if (cdict) { + *cdict = ZSTD_createCDict( + state->dictionary.data, + state->dictionary.size, + level); + if (!*cdict) { + return 1; + } + zret = ZSTD_initCStream_usingCDict(zcs, *cdict); + } else if (config->use_dictionary) { + zret = ZSTD_initCStream_usingDict( + zcs, state->dictionary.data, state->dictionary.size, level); + } else { + zret = ZSTD_initCStream(zcs, level); + } } if (ZSTD_isError(zret)) { - result = result_error(result_error_compression_error); - goto out; + return 1; + } + return 0; +} + +static result_t old_streaming_compress_internal( + method_state_t* base, + config_t const* config, + int const advanced, + int const cdict) { + buffer_state_t* state = container_of(base, buffer_state_t, base); + + if (buffer_state_bad(state, config)) + return result_error(result_error_system_error); + + + ZSTD_CStream* zcs = ZSTD_createCStream(); + ZSTD_CDict* cd = NULL; + result_t result; + if (zcs == NULL) { + result = result_error(result_error_compression_error); + goto out; + } + if (init_cstream(state, zcs, config, advanced, cdict ? &cd : NULL)) { + result = result_error(result_error_compression_error); + goto out; + } + + result_data_t data = {.total_size = 0}; + for (size_t i = 0; i < state->inputs.size; ++i) { + data_buffer_t input = state->inputs.buffers[i]; + size_t zret = ZSTD_resetCStream( + zcs, + config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN : input.size); + if (ZSTD_isError(zret)) { + result = result_error(result_error_compression_error); + goto out; } - result_data_t data = {.total_size = 0}; - for (size_t i = 0; i < state->inputs.size; ++i) { - data_buffer_t input = state->inputs.buffers[i]; - zret = ZSTD_resetCStream( - zcs, - config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN - : input.size); + while (input.size > 0) { + ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)}; + input.data += in.size; + input.size -= in.size; + ZSTD_EndDirective const op = + input.size > 0 ? ZSTD_e_continue : ZSTD_e_end; + zret = 0; + while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) { + ZSTD_outBuffer out = {state->compressed.data, + MIN(state->compressed.capacity, 1024)}; + if (op == ZSTD_e_continue || in.pos < in.size) + zret = ZSTD_compressStream(zcs, &out, &in); + else + zret = ZSTD_endStream(zcs, &out); if (ZSTD_isError(zret)) { - result = result_error(result_error_compression_error); - goto out; - } - - while (input.size > 0) { - ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)}; - input.data += in.size; - input.size -= in.size; - ZSTD_EndDirective const op = - input.size > 0 ? ZSTD_e_continue : ZSTD_e_end; - zret = 0; - while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) { - ZSTD_outBuffer out = {state->compressed.data, - MIN(state->compressed.capacity, 1024)}; - if (op == ZSTD_e_continue || in.pos < in.size) - zret = ZSTD_compressStream(zcs, &out, &in); - else - zret = ZSTD_endStream(zcs, &out); - if (ZSTD_isError(zret)) { - result = result_error(result_error_compression_error); - goto out; - } - data.total_size += out.pos; - } + result = result_error(result_error_compression_error); + goto out; } + data.total_size += out.pos; + } } + } - result = result_data(data); + result = result_data(data); out: ZSTD_freeCStream(zcs); + ZSTD_freeCDict(cd); return result; } +static result_t old_streaming_compress( + method_state_t* base, + config_t const* config) +{ + return old_streaming_compress_internal( + base, config, /* advanced */ 0, /* cdict */ 0); +} + +static result_t old_streaming_compress_advanced( + method_state_t* base, + config_t const* config) +{ + return old_streaming_compress_internal( + base, config, /* advanced */ 1, /* cdict */ 0); +} + +static result_t old_streaming_compress_cdict( + method_state_t* base, + config_t const* config) +{ + return old_streaming_compress_internal( + base, config, /* advanced */ 0, /* cdict */ 1); +} + +static result_t old_streaming_compress_cdict_advanced( + method_state_t* base, + config_t const* config) +{ + return old_streaming_compress_internal( + base, config, /* advanced */ 1, /* cdict */ 1); +} + method_t const simple = { .name = "compress simple", .create = buffer_state_create, @@ -545,6 +626,27 @@ method_t const old_streaming = { .destroy = buffer_state_destroy, }; +method_t const old_streaming_advanced = { + .name = "old streaming advanced", + .create = buffer_state_create, + .compress = old_streaming_compress, + .destroy = buffer_state_destroy, +}; + +method_t const old_streaming_cdict = { + .name = "old streaming cdcit", + .create = buffer_state_create, + .compress = old_streaming_compress, + .destroy = buffer_state_destroy, +}; + +method_t const old_streaming_advanced_cdict = { + .name = "old streaming advanced cdict", + .create = buffer_state_create, + .compress = old_streaming_compress, + .destroy = buffer_state_destroy, +}; + method_t const cli = { .name = "zstdcli", .create = method_state_create, @@ -560,6 +662,9 @@ static method_t const* g_methods[] = { &advanced_one_pass_small_out, &advanced_streaming, &old_streaming, + &old_streaming_advanced, + &old_streaming_cdict, + &old_streaming_advanced_cdict, NULL, }; diff --git a/tests/regression/results.csv b/tests/regression/results.csv index a62178d6ed0c..7ac94f207a6c 100644 --- a/tests/regression/results.csv +++ b/tests/regression/results.csv @@ -1,448 +1,816 @@ -Data, Config, Method, Total compressed size -silesia.tar, level -5, compress simple, 7160438 -silesia.tar, level -3, compress simple, 6789024 -silesia.tar, level -1, compress simple, 6195462 -silesia.tar, level 0, compress simple, 4875008 -silesia.tar, level 1, compress simple, 5339697 -silesia.tar, level 3, compress simple, 4875008 -silesia.tar, level 4, compress simple, 4813507 -silesia.tar, level 5, compress simple, 4722235 -silesia.tar, level 6, compress simple, 4672194 -silesia.tar, level 7, compress simple, 4606658 -silesia.tar, level 9, compress simple, 4554098 -silesia.tar, level 13, compress simple, 4491702 -silesia.tar, level 16, compress simple, 4381277 -silesia.tar, level 19, compress simple, 4281514 -silesia, level -5, compress cctx, 7152294 -silesia, level -3, compress cctx, 6789969 -silesia, level -1, compress cctx, 6191548 -silesia, level 0, compress cctx, 4862377 -silesia, level 1, compress cctx, 5318036 -silesia, level 3, compress cctx, 4862377 -silesia, level 4, compress cctx, 4800629 -silesia, level 5, compress cctx, 4710178 -silesia, level 6, compress cctx, 4659996 -silesia, level 7, compress cctx, 4596234 -silesia, level 9, compress cctx, 4543862 -silesia, level 13, compress cctx, 4482073 -silesia, level 16, compress cctx, 4377391 -silesia, level 19, compress cctx, 4293262 -silesia, long distance mode, compress cctx, 4862377 -silesia, multithreaded, compress cctx, 4862377 -silesia, multithreaded long distance mode, compress cctx, 4862377 -silesia, small window log, compress cctx, 7115734 -silesia, small hash log, compress cctx, 6554898 -silesia, small chain log, compress cctx, 4931093 -silesia, explicit params, compress cctx, 4813352 -github, level -5, compress cctx, 232744 -github, level -5 with dict, compress cctx, 47294 -github, level -3, compress cctx, 220611 -github, level -3 with dict, compress cctx, 48047 -github, level -1, compress cctx, 176575 -github, level -1 with dict, compress cctx, 43527 -github, level 0, compress cctx, 136397 -github, level 0 with dict, compress cctx, 41536 -github, level 1, compress cctx, 143457 -github, level 1 with dict, compress cctx, 42157 -github, level 3, compress cctx, 136397 -github, level 3 with dict, compress cctx, 41536 -github, level 4, compress cctx, 136144 -github, level 4 with dict, compress cctx, 41721 -github, level 5, compress cctx, 135106 -github, level 5 with dict, compress cctx, 38934 -github, level 6, compress cctx, 135108 -github, level 6 with dict, compress cctx, 38628 -github, level 7, compress cctx, 135108 -github, level 7 with dict, compress cctx, 38741 -github, level 9, compress cctx, 135108 -github, level 9 with dict, compress cctx, 39335 -github, level 13, compress cctx, 133717 -github, level 13 with dict, compress cctx, 39923 -github, level 16, compress cctx, 133717 -github, level 16 with dict, compress cctx, 37568 -github, level 19, compress cctx, 133717 -github, level 19 with dict, compress cctx, 37567 -github, long distance mode, compress cctx, decompression error -github, multithreaded, compress cctx, decompression error -github, multithreaded long distance mode, compress cctx, decompression error -github, small window log, compress cctx, decompression error -github, small hash log, compress cctx, decompression error -github, small chain log, compress cctx, decompression error -github, explicit params, compress cctx, decompression error -silesia, level -5, zstdcli, 7152342 -silesia, level -3, zstdcli, 6790021 -silesia, level -1, zstdcli, 6191597 -silesia, level 0, zstdcli, 4862425 -silesia, level 1, zstdcli, 5318084 -silesia, level 3, zstdcli, 4862425 -silesia, level 4, zstdcli, 4800677 -silesia, level 5, zstdcli, 4710226 -silesia, level 6, zstdcli, 4660044 -silesia, level 7, zstdcli, 4596282 -silesia, level 9, zstdcli, 4543910 -silesia, level 13, zstdcli, 4482121 -silesia, level 16, zstdcli, 4377439 -silesia, level 19, zstdcli, 4293310 -silesia, long distance mode, zstdcli, 4853437 -silesia, multithreaded, zstdcli, 4862425 -silesia, multithreaded long distance mode, zstdcli, 4853437 -silesia, small window log, zstdcli, 7126434 -silesia, small hash log, zstdcli, 6554946 -silesia, small chain log, zstdcli, 4931141 -silesia, explicit params, zstdcli, 4815380 -silesia.tar, level -5, zstdcli, 7161160 -silesia.tar, level -3, zstdcli, 6789865 -silesia.tar, level -1, zstdcli, 6196433 -silesia.tar, level 0, zstdcli, 4875136 -silesia.tar, level 1, zstdcli, 5340573 -silesia.tar, level 3, zstdcli, 4875136 -silesia.tar, level 4, zstdcli, 4814531 -silesia.tar, level 5, zstdcli, 4723284 -silesia.tar, level 6, zstdcli, 4673591 -silesia.tar, level 7, zstdcli, 4608342 -silesia.tar, level 9, zstdcli, 4554700 -silesia.tar, level 13, zstdcli, 4491706 -silesia.tar, level 16, zstdcli, 4381281 -silesia.tar, level 19, zstdcli, 4281518 -silesia.tar, no source size, zstdcli, 4875132 -silesia.tar, long distance mode, zstdcli, 4866975 -silesia.tar, multithreaded, zstdcli, 4875136 -silesia.tar, multithreaded long distance mode, zstdcli, 4866975 -silesia.tar, small window log, zstdcli, 7130434 -silesia.tar, small hash log, zstdcli, 6587841 -silesia.tar, small chain log, zstdcli, 4943259 -silesia.tar, explicit params, zstdcli, 4839202 -github, level -5, zstdcli, 234744 -github, level -5 with dict, zstdcli, 48718 -github, level -3, zstdcli, 222611 -github, level -3 with dict, zstdcli, 47395 -github, level -1, zstdcli, 178575 -github, level -1 with dict, zstdcli, 45170 -github, level 0, zstdcli, 138397 -github, level 0 with dict, zstdcli, 43170 -github, level 1, zstdcli, 145457 -github, level 1 with dict, zstdcli, 43682 -github, level 3, zstdcli, 138397 -github, level 3 with dict, zstdcli, 43170 -github, level 4, zstdcli, 138144 -github, level 4 with dict, zstdcli, 43306 -github, level 5, zstdcli, 137106 -github, level 5 with dict, zstdcli, 40938 -github, level 6, zstdcli, 137108 -github, level 6 with dict, zstdcli, 40632 -github, level 7, zstdcli, 137108 -github, level 7 with dict, zstdcli, 40766 -github, level 9, zstdcli, 137108 -github, level 9 with dict, zstdcli, 41326 -github, level 13, zstdcli, 135717 -github, level 13 with dict, zstdcli, 41716 -github, level 16, zstdcli, 135717 -github, level 16 with dict, zstdcli, 39577 -github, level 19, zstdcli, 135717 -github, level 19 with dict, zstdcli, 39576 -github, long distance mode, zstdcli, 138397 -github, multithreaded, zstdcli, 138397 -github, multithreaded long distance mode, zstdcli, 138397 -github, small window log, zstdcli, 138397 -github, small hash log, zstdcli, 137467 -github, small chain log, zstdcli, 138314 -github, explicit params, zstdcli, 136140 -silesia, level -5, advanced one pass, 7152294 -silesia, level -3, advanced one pass, 6789969 -silesia, level -1, advanced one pass, 6191548 -silesia, level 0, advanced one pass, 4862377 -silesia, level 1, advanced one pass, 5318036 -silesia, level 3, advanced one pass, 4862377 -silesia, level 4, advanced one pass, 4800629 -silesia, level 5, advanced one pass, 4710178 -silesia, level 6, advanced one pass, 4659996 -silesia, level 7, advanced one pass, 4596234 -silesia, level 9, advanced one pass, 4543862 -silesia, level 13, advanced one pass, 4482073 -silesia, level 16, advanced one pass, 4377391 -silesia, level 19, advanced one pass, 4293262 -silesia, no source size, advanced one pass, 4862377 -silesia, long distance mode, advanced one pass, 4853389 -silesia, multithreaded, advanced one pass, 4862377 -silesia, multithreaded long distance mode, advanced one pass, 4853389 -silesia, small window log, advanced one pass, 7126386 -silesia, small hash log, advanced one pass, 6554898 -silesia, small chain log, advanced one pass, 4931093 -silesia, explicit params, advanced one pass, 4815369 -silesia.tar, level -5, advanced one pass, 7160438 -silesia.tar, level -3, advanced one pass, 6789024 -silesia.tar, level -1, advanced one pass, 6195462 -silesia.tar, level 0, advanced one pass, 4875008 -silesia.tar, level 1, advanced one pass, 5339697 -silesia.tar, level 3, advanced one pass, 4875008 -silesia.tar, level 4, advanced one pass, 4813507 -silesia.tar, level 5, advanced one pass, 4722235 -silesia.tar, level 6, advanced one pass, 4672194 -silesia.tar, level 7, advanced one pass, 4606658 -silesia.tar, level 9, advanced one pass, 4554098 -silesia.tar, level 13, advanced one pass, 4491702 -silesia.tar, level 16, advanced one pass, 4381277 -silesia.tar, level 19, advanced one pass, 4281514 -silesia.tar, no source size, advanced one pass, 4875008 -silesia.tar, long distance mode, advanced one pass, 4861218 -silesia.tar, multithreaded, advanced one pass, 4874631 -silesia.tar, multithreaded long distance mode, advanced one pass, 4860683 -silesia.tar, small window log, advanced one pass, 7130394 -silesia.tar, small hash log, advanced one pass, 6587833 -silesia.tar, small chain log, advanced one pass, 4943255 -silesia.tar, explicit params, advanced one pass, 4829974 -github, level -5, advanced one pass, 232744 -github, level -5 with dict, advanced one pass, 46718 -github, level -3, advanced one pass, 220611 -github, level -3 with dict, advanced one pass, 45395 -github, level -1, advanced one pass, 176575 -github, level -1 with dict, advanced one pass, 43170 -github, level 0, advanced one pass, 136397 -github, level 0 with dict, advanced one pass, 41170 -github, level 1, advanced one pass, 143457 -github, level 1 with dict, advanced one pass, 41682 -github, level 3, advanced one pass, 136397 -github, level 3 with dict, advanced one pass, 41170 -github, level 4, advanced one pass, 136144 -github, level 4 with dict, advanced one pass, 41306 -github, level 5, advanced one pass, 135106 -github, level 5 with dict, advanced one pass, 38938 -github, level 6, advanced one pass, 135108 -github, level 6 with dict, advanced one pass, 38632 -github, level 7, advanced one pass, 135108 -github, level 7 with dict, advanced one pass, 38766 -github, level 9, advanced one pass, 135108 -github, level 9 with dict, advanced one pass, 39326 -github, level 13, advanced one pass, 133717 -github, level 13 with dict, advanced one pass, 39716 -github, level 16, advanced one pass, 133717 -github, level 16 with dict, advanced one pass, 37577 -github, level 19, advanced one pass, 133717 -github, level 19 with dict, advanced one pass, 37576 -github, no source size, advanced one pass, 136397 -github, long distance mode, advanced one pass, 136397 -github, multithreaded, advanced one pass, 136397 -github, multithreaded long distance mode, advanced one pass, 136397 -github, small window log, advanced one pass, 136397 -github, small hash log, advanced one pass, 135467 -github, small chain log, advanced one pass, 136314 -github, explicit params, advanced one pass, 137670 -silesia, level -5, advanced one pass small out, 7152294 -silesia, level -3, advanced one pass small out, 6789969 -silesia, level -1, advanced one pass small out, 6191548 -silesia, level 0, advanced one pass small out, 4862377 -silesia, level 1, advanced one pass small out, 5318036 -silesia, level 3, advanced one pass small out, 4862377 -silesia, level 4, advanced one pass small out, 4800629 -silesia, level 5, advanced one pass small out, 4710178 -silesia, level 6, advanced one pass small out, 4659996 -silesia, level 7, advanced one pass small out, 4596234 -silesia, level 9, advanced one pass small out, 4543862 -silesia, level 13, advanced one pass small out, 4482073 -silesia, level 16, advanced one pass small out, 4377391 -silesia, level 19, advanced one pass small out, 4293262 -silesia, no source size, advanced one pass small out, 4862377 -silesia, long distance mode, advanced one pass small out, 4853389 -silesia, multithreaded, advanced one pass small out, 4862377 -silesia, multithreaded long distance mode, advanced one pass small out, 4853389 -silesia, small window log, advanced one pass small out, 7126386 -silesia, small hash log, advanced one pass small out, 6554898 -silesia, small chain log, advanced one pass small out, 4931093 -silesia, explicit params, advanced one pass small out, 4815369 -silesia.tar, level -5, advanced one pass small out, 7160438 -silesia.tar, level -3, advanced one pass small out, 6789024 -silesia.tar, level -1, advanced one pass small out, 6195462 -silesia.tar, level 0, advanced one pass small out, 4875008 -silesia.tar, level 1, advanced one pass small out, 5339697 -silesia.tar, level 3, advanced one pass small out, 4875008 -silesia.tar, level 4, advanced one pass small out, 4813507 -silesia.tar, level 5, advanced one pass small out, 4722235 -silesia.tar, level 6, advanced one pass small out, 4672194 -silesia.tar, level 7, advanced one pass small out, 4606658 -silesia.tar, level 9, advanced one pass small out, 4554098 -silesia.tar, level 13, advanced one pass small out, 4491702 -silesia.tar, level 16, advanced one pass small out, 4381277 -silesia.tar, level 19, advanced one pass small out, 4281514 -silesia.tar, no source size, advanced one pass small out, 4875008 -silesia.tar, long distance mode, advanced one pass small out, 4861218 -silesia.tar, multithreaded, advanced one pass small out, 4874631 -silesia.tar, multithreaded long distance mode, advanced one pass small out, 4860683 -silesia.tar, small window log, advanced one pass small out, 7130394 -silesia.tar, small hash log, advanced one pass small out, 6587833 -silesia.tar, small chain log, advanced one pass small out, 4943255 -silesia.tar, explicit params, advanced one pass small out, 4829974 -github, level -5, advanced one pass small out, 232744 -github, level -5 with dict, advanced one pass small out, 46718 -github, level -3, advanced one pass small out, 220611 -github, level -3 with dict, advanced one pass small out, 45395 -github, level -1, advanced one pass small out, 176575 -github, level -1 with dict, advanced one pass small out, 43170 -github, level 0, advanced one pass small out, 136397 -github, level 0 with dict, advanced one pass small out, 41170 -github, level 1, advanced one pass small out, 143457 -github, level 1 with dict, advanced one pass small out, 41682 -github, level 3, advanced one pass small out, 136397 -github, level 3 with dict, advanced one pass small out, 41170 -github, level 4, advanced one pass small out, 136144 -github, level 4 with dict, advanced one pass small out, 41306 -github, level 5, advanced one pass small out, 135106 -github, level 5 with dict, advanced one pass small out, 38938 -github, level 6, advanced one pass small out, 135108 -github, level 6 with dict, advanced one pass small out, 38632 -github, level 7, advanced one pass small out, 135108 -github, level 7 with dict, advanced one pass small out, 38766 -github, level 9, advanced one pass small out, 135108 -github, level 9 with dict, advanced one pass small out, 39326 -github, level 13, advanced one pass small out, 133717 -github, level 13 with dict, advanced one pass small out, 39716 -github, level 16, advanced one pass small out, 133717 -github, level 16 with dict, advanced one pass small out, 37577 -github, level 19, advanced one pass small out, 133717 -github, level 19 with dict, advanced one pass small out, 37576 -github, no source size, advanced one pass small out, 136397 -github, long distance mode, advanced one pass small out, 136397 -github, multithreaded, advanced one pass small out, 136397 -github, multithreaded long distance mode, advanced one pass small out, 136397 -github, small window log, advanced one pass small out, 136397 -github, small hash log, advanced one pass small out, 135467 -github, small chain log, advanced one pass small out, 136314 -github, explicit params, advanced one pass small out, 137670 -silesia, level -5, advanced streaming, 7152294 -silesia, level -3, advanced streaming, 6789973 -silesia, level -1, advanced streaming, 6191549 -silesia, level 0, advanced streaming, 4862377 -silesia, level 1, advanced streaming, 5318036 -silesia, level 3, advanced streaming, 4862377 -silesia, level 4, advanced streaming, 4800629 -silesia, level 5, advanced streaming, 4710178 -silesia, level 6, advanced streaming, 4659996 -silesia, level 7, advanced streaming, 4596234 -silesia, level 9, advanced streaming, 4543862 -silesia, level 13, advanced streaming, 4482073 -silesia, level 16, advanced streaming, 4377391 -silesia, level 19, advanced streaming, 4293262 -silesia, no source size, advanced streaming, 4862341 -silesia, long distance mode, advanced streaming, 4853389 -silesia, multithreaded, advanced streaming, 4862377 -silesia, multithreaded long distance mode, advanced streaming, 4853389 -silesia, small window log, advanced streaming, 7126389 -silesia, small hash log, advanced streaming, 6554898 -silesia, small chain log, advanced streaming, 4931093 -silesia, explicit params, advanced streaming, 4815380 -silesia.tar, level -5, advanced streaming, 7160440 -silesia.tar, level -3, advanced streaming, 6789026 -silesia.tar, level -1, advanced streaming, 6195465 -silesia.tar, level 0, advanced streaming, 4875010 -silesia.tar, level 1, advanced streaming, 5339701 -silesia.tar, level 3, advanced streaming, 4875010 -silesia.tar, level 4, advanced streaming, 4813507 -silesia.tar, level 5, advanced streaming, 4722240 -silesia.tar, level 6, advanced streaming, 4672203 -silesia.tar, level 7, advanced streaming, 4606658 -silesia.tar, level 9, advanced streaming, 4554105 -silesia.tar, level 13, advanced streaming, 4491703 -silesia.tar, level 16, advanced streaming, 4381277 -silesia.tar, level 19, advanced streaming, 4281514 -silesia.tar, no source size, advanced streaming, 4875006 -silesia.tar, long distance mode, advanced streaming, 4861218 -silesia.tar, multithreaded, advanced streaming, 4875132 -silesia.tar, multithreaded long distance mode, advanced streaming, 4866971 -silesia.tar, small window log, advanced streaming, 7130394 -silesia.tar, small hash log, advanced streaming, 6587834 -silesia.tar, small chain log, advanced streaming, 4943260 -silesia.tar, explicit params, advanced streaming, 4830002 -github, level -5, advanced streaming, 232744 -github, level -5 with dict, advanced streaming, 46718 -github, level -3, advanced streaming, 220611 -github, level -3 with dict, advanced streaming, 45395 -github, level -1, advanced streaming, 176575 -github, level -1 with dict, advanced streaming, 43170 -github, level 0, advanced streaming, 136397 -github, level 0 with dict, advanced streaming, 41170 -github, level 1, advanced streaming, 143457 -github, level 1 with dict, advanced streaming, 41682 -github, level 3, advanced streaming, 136397 -github, level 3 with dict, advanced streaming, 41170 -github, level 4, advanced streaming, 136144 -github, level 4 with dict, advanced streaming, 41306 -github, level 5, advanced streaming, 135106 -github, level 5 with dict, advanced streaming, 38938 -github, level 6, advanced streaming, 135108 -github, level 6 with dict, advanced streaming, 38632 -github, level 7, advanced streaming, 135108 -github, level 7 with dict, advanced streaming, 38766 -github, level 9, advanced streaming, 135108 -github, level 9 with dict, advanced streaming, 39326 -github, level 13, advanced streaming, 133717 -github, level 13 with dict, advanced streaming, 39716 -github, level 16, advanced streaming, 133717 -github, level 16 with dict, advanced streaming, 37577 -github, level 19, advanced streaming, 133717 -github, level 19 with dict, advanced streaming, 37576 -github, no source size, advanced streaming, 136397 -github, long distance mode, advanced streaming, 136397 -github, multithreaded, advanced streaming, 136397 -github, multithreaded long distance mode, advanced streaming, 136397 -github, small window log, advanced streaming, 136397 -github, small hash log, advanced streaming, 135467 -github, small chain log, advanced streaming, 136314 -github, explicit params, advanced streaming, 137670 -silesia, level -5, old streaming, 7152294 -silesia, level -3, old streaming, 6789973 -silesia, level -1, old streaming, 6191549 -silesia, level 0, old streaming, 4862377 -silesia, level 1, old streaming, 5318036 -silesia, level 3, old streaming, 4862377 -silesia, level 4, old streaming, 4800629 -silesia, level 5, old streaming, 4710178 -silesia, level 6, old streaming, 4659996 -silesia, level 7, old streaming, 4596234 -silesia, level 9, old streaming, 4543862 -silesia, level 13, old streaming, 4482073 -silesia, level 16, old streaming, 4377391 -silesia, level 19, old streaming, 4293262 -silesia, no source size, old streaming, 4862341 -silesia.tar, level -5, old streaming, 7160440 -silesia.tar, level -3, old streaming, 6789026 -silesia.tar, level -1, old streaming, 6195465 -silesia.tar, level 0, old streaming, 4875010 -silesia.tar, level 1, old streaming, 5339701 -silesia.tar, level 3, old streaming, 4875010 -silesia.tar, level 4, old streaming, 4813507 -silesia.tar, level 5, old streaming, 4722240 -silesia.tar, level 6, old streaming, 4672203 -silesia.tar, level 7, old streaming, 4606658 -silesia.tar, level 9, old streaming, 4554105 -silesia.tar, level 13, old streaming, 4491703 -silesia.tar, level 16, old streaming, 4381277 -silesia.tar, level 19, old streaming, 4281514 -silesia.tar, no source size, old streaming, 4875006 -github, level -5, old streaming, 232744 -github, level -5 with dict, old streaming, 46718 -github, level -3, old streaming, 220611 -github, level -3 with dict, old streaming, 45395 -github, level -1, old streaming, 176575 -github, level -1 with dict, old streaming, 43170 -github, level 0, old streaming, 136397 -github, level 0 with dict, old streaming, 41170 -github, level 1, old streaming, 143457 -github, level 1 with dict, old streaming, 41682 -github, level 3, old streaming, 136397 -github, level 3 with dict, old streaming, 41170 -github, level 4, old streaming, 136144 -github, level 4 with dict, old streaming, 41306 -github, level 5, old streaming, 135106 -github, level 5 with dict, old streaming, 38938 -github, level 6, old streaming, 135108 -github, level 6 with dict, old streaming, 38632 -github, level 7, old streaming, 135108 -github, level 7 with dict, old streaming, 38766 -github, level 9, old streaming, 135108 -github, level 9 with dict, old streaming, 39326 -github, level 13, old streaming, 133717 -github, level 13 with dict, old streaming, 39716 -github, level 16, old streaming, 133717 -github, level 16 with dict, old streaming, 37577 -github, level 19, old streaming, 133717 -github, level 19 with dict, old streaming, 37576 -github, no source size, old streaming, 141003 +Data, Config, Method, Total compressed size +silesia.tar, level -5, compress simple, 6738558 +silesia.tar, level -3, compress simple, 6446362 +silesia.tar, level -1, compress simple, 6186038 +silesia.tar, level 0, compress simple, 4875008 +silesia.tar, level 1, compress simple, 5334825 +silesia.tar, level 3, compress simple, 4875008 +silesia.tar, level 4, compress simple, 4813507 +silesia.tar, level 5, compress simple, 4722235 +silesia.tar, level 6, compress simple, 4672194 +silesia.tar, level 7, compress simple, 4606658 +silesia.tar, level 9, compress simple, 4554098 +silesia.tar, level 13, compress simple, 4491702 +silesia.tar, level 16, compress simple, 4381277 +silesia.tar, level 19, compress simple, 4281514 +silesia.tar, uncompressed literals, compress simple, 4875008 +silesia.tar, uncompressed literals optimal, compress simple, 4281514 +silesia.tar, huffman literals, compress simple, 6186038 +silesia, level -5, compress cctx, 6737567 +silesia, level -3, compress cctx, 6444663 +silesia, level -1, compress cctx, 6178442 +silesia, level 0, compress cctx, 4862377 +silesia, level 1, compress cctx, 5313144 +silesia, level 3, compress cctx, 4862377 +silesia, level 4, compress cctx, 4800629 +silesia, level 5, compress cctx, 4710178 +silesia, level 6, compress cctx, 4659996 +silesia, level 7, compress cctx, 4596234 +silesia, level 9, compress cctx, 4543862 +silesia, level 13, compress cctx, 4482073 +silesia, level 16, compress cctx, 4377391 +silesia, level 19, compress cctx, 4293262 +silesia, long distance mode, compress cctx, 4862377 +silesia, multithreaded, compress cctx, 4862377 +silesia, multithreaded long distance mode, compress cctx, 4862377 +silesia, small window log, compress cctx, 7115734 +silesia, small hash log, compress cctx, 6554898 +silesia, small chain log, compress cctx, 4931093 +silesia, explicit params, compress cctx, 4813352 +silesia, uncompressed literals, compress cctx, 4862377 +silesia, uncompressed literals optimal, compress cctx, 4293262 +silesia, huffman literals, compress cctx, 6178442 +silesia, multithreaded with advanced params, compress cctx, 4862377 +github, level -5, compress cctx, 205285 +github, level -5 with dict, compress cctx, 47294 +github, level -3, compress cctx, 190643 +github, level -3 with dict, compress cctx, 48047 +github, level -1, compress cctx, 175568 +github, level -1 with dict, compress cctx, 43527 +github, level 0, compress cctx, 136397 +github, level 0 with dict, compress cctx, 41536 +github, level 1, compress cctx, 142450 +github, level 1 with dict, compress cctx, 42157 +github, level 3, compress cctx, 136397 +github, level 3 with dict, compress cctx, 41536 +github, level 4, compress cctx, 136144 +github, level 4 with dict, compress cctx, 41721 +github, level 5, compress cctx, 135106 +github, level 5 with dict, compress cctx, 38934 +github, level 6, compress cctx, 135108 +github, level 6 with dict, compress cctx, 38628 +github, level 7, compress cctx, 135108 +github, level 7 with dict, compress cctx, 38741 +github, level 9, compress cctx, 135108 +github, level 9 with dict, compress cctx, 39335 +github, level 13, compress cctx, 133717 +github, level 13 with dict, compress cctx, 39923 +github, level 16, compress cctx, 133717 +github, level 16 with dict, compress cctx, 37568 +github, level 19, compress cctx, 133717 +github, level 19 with dict, compress cctx, 37567 +github, long distance mode, compress cctx, 141473 +github, multithreaded, compress cctx, 141473 +github, multithreaded long distance mode, compress cctx, 141473 +github, small window log, compress cctx, 141473 +github, small hash log, compress cctx, 138943 +github, small chain log, compress cctx, 139239 +github, explicit params, compress cctx, 140924 +github, uncompressed literals, compress cctx, 136397 +github, uncompressed literals optimal, compress cctx, 133717 +github, huffman literals, compress cctx, 175568 +github, multithreaded with advanced params, compress cctx, 141473 +silesia, level -5, zstdcli, 6882514 +silesia, level -3, zstdcli, 6568406 +silesia, level -1, zstdcli, 6183433 +silesia, level 0, zstdcli, 4862425 +silesia, level 1, zstdcli, 5314157 +silesia, level 3, zstdcli, 4862425 +silesia, level 4, zstdcli, 4800677 +silesia, level 5, zstdcli, 4710226 +silesia, level 6, zstdcli, 4660044 +silesia, level 7, zstdcli, 4596282 +silesia, level 9, zstdcli, 4543910 +silesia, level 13, zstdcli, 4482121 +silesia, level 16, zstdcli, 4377439 +silesia, level 19, zstdcli, 4293310 +silesia, long distance mode, zstdcli, 4853437 +silesia, multithreaded, zstdcli, 4862425 +silesia, multithreaded long distance mode, zstdcli, 4853437 +silesia, small window log, zstdcli, 7126434 +silesia, small hash log, zstdcli, 6554946 +silesia, small chain log, zstdcli, 4931141 +silesia, explicit params, zstdcli, 4815380 +silesia, uncompressed literals, zstdcli, 5155472 +silesia, uncompressed literals optimal, zstdcli, 4325475 +silesia, huffman literals, zstdcli, 5331158 +silesia, multithreaded with advanced params, zstdcli, 5155472 +silesia.tar, level -5, zstdcli, 6738906 +silesia.tar, level -3, zstdcli, 6448409 +silesia.tar, level -1, zstdcli, 6186908 +silesia.tar, level 0, zstdcli, 4875136 +silesia.tar, level 1, zstdcli, 5336255 +silesia.tar, level 3, zstdcli, 4875136 +silesia.tar, level 4, zstdcli, 4814531 +silesia.tar, level 5, zstdcli, 4723284 +silesia.tar, level 6, zstdcli, 4673591 +silesia.tar, level 7, zstdcli, 4608342 +silesia.tar, level 9, zstdcli, 4554700 +silesia.tar, level 13, zstdcli, 4491706 +silesia.tar, level 16, zstdcli, 4381281 +silesia.tar, level 19, zstdcli, 4281518 +silesia.tar, no source size, zstdcli, 4875132 +silesia.tar, long distance mode, zstdcli, 4866975 +silesia.tar, multithreaded, zstdcli, 4875136 +silesia.tar, multithreaded long distance mode, zstdcli, 4866975 +silesia.tar, small window log, zstdcli, 7130434 +silesia.tar, small hash log, zstdcli, 6587841 +silesia.tar, small chain log, zstdcli, 4943259 +silesia.tar, explicit params, zstdcli, 4839202 +silesia.tar, uncompressed literals, zstdcli, 5158134 +silesia.tar, uncompressed literals optimal, zstdcli, 4321098 +silesia.tar, huffman literals, zstdcli, 5347560 +silesia.tar, multithreaded with advanced params, zstdcli, 5158134 +github, level -5, zstdcli, 207285 +github, level -5 with dict, zstdcli, 48718 +github, level -3, zstdcli, 192643 +github, level -3 with dict, zstdcli, 47395 +github, level -1, zstdcli, 177568 +github, level -1 with dict, zstdcli, 45170 +github, level 0, zstdcli, 138397 +github, level 0 with dict, zstdcli, 43170 +github, level 1, zstdcli, 144450 +github, level 1 with dict, zstdcli, 43682 +github, level 3, zstdcli, 138397 +github, level 3 with dict, zstdcli, 43170 +github, level 4, zstdcli, 138144 +github, level 4 with dict, zstdcli, 43306 +github, level 5, zstdcli, 137106 +github, level 5 with dict, zstdcli, 40938 +github, level 6, zstdcli, 137108 +github, level 6 with dict, zstdcli, 40632 +github, level 7, zstdcli, 137108 +github, level 7 with dict, zstdcli, 40766 +github, level 9, zstdcli, 137108 +github, level 9 with dict, zstdcli, 41326 +github, level 13, zstdcli, 135717 +github, level 13 with dict, zstdcli, 41716 +github, level 16, zstdcli, 135717 +github, level 16 with dict, zstdcli, 39577 +github, level 19, zstdcli, 135717 +github, level 19 with dict, zstdcli, 39576 +github, long distance mode, zstdcli, 138397 +github, multithreaded, zstdcli, 138397 +github, multithreaded long distance mode, zstdcli, 138397 +github, small window log, zstdcli, 138397 +github, small hash log, zstdcli, 137467 +github, small chain log, zstdcli, 138314 +github, explicit params, zstdcli, 136140 +github, uncompressed literals, zstdcli, 169004 +github, uncompressed literals optimal, zstdcli, 158824 +github, huffman literals, zstdcli, 144450 +github, multithreaded with advanced params, zstdcli, 169004 +silesia, level -5, advanced one pass, 6737567 +silesia, level -3, advanced one pass, 6444663 +silesia, level -1, advanced one pass, 6178442 +silesia, level 0, advanced one pass, 4862377 +silesia, level 1, advanced one pass, 5313144 +silesia, level 3, advanced one pass, 4862377 +silesia, level 4, advanced one pass, 4800629 +silesia, level 5, advanced one pass, 4710178 +silesia, level 6, advanced one pass, 4659996 +silesia, level 7, advanced one pass, 4596234 +silesia, level 9, advanced one pass, 4543862 +silesia, level 13, advanced one pass, 4482073 +silesia, level 16, advanced one pass, 4377391 +silesia, level 19, advanced one pass, 4293262 +silesia, no source size, advanced one pass, 4862377 +silesia, long distance mode, advanced one pass, 4853389 +silesia, multithreaded, advanced one pass, 4862377 +silesia, multithreaded long distance mode, advanced one pass, 4853389 +silesia, small window log, advanced one pass, 7126386 +silesia, small hash log, advanced one pass, 6554898 +silesia, small chain log, advanced one pass, 4931093 +silesia, explicit params, advanced one pass, 4815369 +silesia, uncompressed literals, advanced one pass, 5155424 +silesia, uncompressed literals optimal, advanced one pass, 4325427 +silesia, huffman literals, advanced one pass, 5326210 +silesia, multithreaded with advanced params, advanced one pass, 5155424 +silesia.tar, level -5, advanced one pass, 6738558 +silesia.tar, level -3, advanced one pass, 6446362 +silesia.tar, level -1, advanced one pass, 6186038 +silesia.tar, level 0, advanced one pass, 4875008 +silesia.tar, level 1, advanced one pass, 5334825 +silesia.tar, level 3, advanced one pass, 4875008 +silesia.tar, level 4, advanced one pass, 4813507 +silesia.tar, level 5, advanced one pass, 4722235 +silesia.tar, level 6, advanced one pass, 4672194 +silesia.tar, level 7, advanced one pass, 4606658 +silesia.tar, level 9, advanced one pass, 4554098 +silesia.tar, level 13, advanced one pass, 4491702 +silesia.tar, level 16, advanced one pass, 4381277 +silesia.tar, level 19, advanced one pass, 4281514 +silesia.tar, no source size, advanced one pass, 4875008 +silesia.tar, long distance mode, advanced one pass, 4861218 +silesia.tar, multithreaded, advanced one pass, 4874631 +silesia.tar, multithreaded long distance mode, advanced one pass, 4860683 +silesia.tar, small window log, advanced one pass, 7130394 +silesia.tar, small hash log, advanced one pass, 6587833 +silesia.tar, small chain log, advanced one pass, 4943255 +silesia.tar, explicit params, advanced one pass, 4829974 +silesia.tar, uncompressed literals, advanced one pass, 5157992 +silesia.tar, uncompressed literals optimal, advanced one pass, 4321094 +silesia.tar, huffman literals, advanced one pass, 5347283 +silesia.tar, multithreaded with advanced params, advanced one pass, 5158545 +github, level -5, advanced one pass, 205285 +github, level -5 with dict, advanced one pass, 46718 +github, level -3, advanced one pass, 190643 +github, level -3 with dict, advanced one pass, 45395 +github, level -1, advanced one pass, 175568 +github, level -1 with dict, advanced one pass, 43170 +github, level 0, advanced one pass, 136397 +github, level 0 with dict, advanced one pass, 41170 +github, level 1, advanced one pass, 142450 +github, level 1 with dict, advanced one pass, 41682 +github, level 3, advanced one pass, 136397 +github, level 3 with dict, advanced one pass, 41170 +github, level 4, advanced one pass, 136144 +github, level 4 with dict, advanced one pass, 41306 +github, level 5, advanced one pass, 135106 +github, level 5 with dict, advanced one pass, 38938 +github, level 6, advanced one pass, 135108 +github, level 6 with dict, advanced one pass, 38632 +github, level 7, advanced one pass, 135108 +github, level 7 with dict, advanced one pass, 38766 +github, level 9, advanced one pass, 135108 +github, level 9 with dict, advanced one pass, 39326 +github, level 13, advanced one pass, 133717 +github, level 13 with dict, advanced one pass, 39716 +github, level 16, advanced one pass, 133717 +github, level 16 with dict, advanced one pass, 37577 +github, level 19, advanced one pass, 133717 +github, level 19 with dict, advanced one pass, 37576 +github, no source size, advanced one pass, 136397 +github, long distance mode, advanced one pass, 136397 +github, multithreaded, advanced one pass, 136397 +github, multithreaded long distance mode, advanced one pass, 136397 +github, small window log, advanced one pass, 136397 +github, small hash log, advanced one pass, 135467 +github, small chain log, advanced one pass, 136314 +github, explicit params, advanced one pass, 137670 +github, uncompressed literals, advanced one pass, 167004 +github, uncompressed literals optimal, advanced one pass, 156824 +github, huffman literals, advanced one pass, 142450 +github, multithreaded with advanced params, advanced one pass, 167004 +silesia, level -5, advanced one pass small out, 6737567 +silesia, level -3, advanced one pass small out, 6444663 +silesia, level -1, advanced one pass small out, 6178442 +silesia, level 0, advanced one pass small out, 4862377 +silesia, level 1, advanced one pass small out, 5313144 +silesia, level 3, advanced one pass small out, 4862377 +silesia, level 4, advanced one pass small out, 4800629 +silesia, level 5, advanced one pass small out, 4710178 +silesia, level 6, advanced one pass small out, 4659996 +silesia, level 7, advanced one pass small out, 4596234 +silesia, level 9, advanced one pass small out, 4543862 +silesia, level 13, advanced one pass small out, 4482073 +silesia, level 16, advanced one pass small out, 4377391 +silesia, level 19, advanced one pass small out, 4293262 +silesia, no source size, advanced one pass small out, 4862377 +silesia, long distance mode, advanced one pass small out, 4853389 +silesia, multithreaded, advanced one pass small out, 4862377 +silesia, multithreaded long distance mode, advanced one pass small out, 4853389 +silesia, small window log, advanced one pass small out, 7126386 +silesia, small hash log, advanced one pass small out, 6554898 +silesia, small chain log, advanced one pass small out, 4931093 +silesia, explicit params, advanced one pass small out, 4815369 +silesia, uncompressed literals, advanced one pass small out, 5155424 +silesia, uncompressed literals optimal, advanced one pass small out, 4325427 +silesia, huffman literals, advanced one pass small out, 5326210 +silesia, multithreaded with advanced params, advanced one pass small out, 5155424 +silesia.tar, level -5, advanced one pass small out, 6738558 +silesia.tar, level -3, advanced one pass small out, 6446362 +silesia.tar, level -1, advanced one pass small out, 6186038 +silesia.tar, level 0, advanced one pass small out, 4875008 +silesia.tar, level 1, advanced one pass small out, 5334825 +silesia.tar, level 3, advanced one pass small out, 4875008 +silesia.tar, level 4, advanced one pass small out, 4813507 +silesia.tar, level 5, advanced one pass small out, 4722235 +silesia.tar, level 6, advanced one pass small out, 4672194 +silesia.tar, level 7, advanced one pass small out, 4606658 +silesia.tar, level 9, advanced one pass small out, 4554098 +silesia.tar, level 13, advanced one pass small out, 4491702 +silesia.tar, level 16, advanced one pass small out, 4381277 +silesia.tar, level 19, advanced one pass small out, 4281514 +silesia.tar, no source size, advanced one pass small out, 4875008 +silesia.tar, long distance mode, advanced one pass small out, 4861218 +silesia.tar, multithreaded, advanced one pass small out, 4874631 +silesia.tar, multithreaded long distance mode, advanced one pass small out, 4860683 +silesia.tar, small window log, advanced one pass small out, 7130394 +silesia.tar, small hash log, advanced one pass small out, 6587833 +silesia.tar, small chain log, advanced one pass small out, 4943255 +silesia.tar, explicit params, advanced one pass small out, 4829974 +silesia.tar, uncompressed literals, advanced one pass small out, 5157992 +silesia.tar, uncompressed literals optimal, advanced one pass small out, 4321094 +silesia.tar, huffman literals, advanced one pass small out, 5347283 +silesia.tar, multithreaded with advanced params, advanced one pass small out, 5158545 +github, level -5, advanced one pass small out, 205285 +github, level -5 with dict, advanced one pass small out, 46718 +github, level -3, advanced one pass small out, 190643 +github, level -3 with dict, advanced one pass small out, 45395 +github, level -1, advanced one pass small out, 175568 +github, level -1 with dict, advanced one pass small out, 43170 +github, level 0, advanced one pass small out, 136397 +github, level 0 with dict, advanced one pass small out, 41170 +github, level 1, advanced one pass small out, 142450 +github, level 1 with dict, advanced one pass small out, 41682 +github, level 3, advanced one pass small out, 136397 +github, level 3 with dict, advanced one pass small out, 41170 +github, level 4, advanced one pass small out, 136144 +github, level 4 with dict, advanced one pass small out, 41306 +github, level 5, advanced one pass small out, 135106 +github, level 5 with dict, advanced one pass small out, 38938 +github, level 6, advanced one pass small out, 135108 +github, level 6 with dict, advanced one pass small out, 38632 +github, level 7, advanced one pass small out, 135108 +github, level 7 with dict, advanced one pass small out, 38766 +github, level 9, advanced one pass small out, 135108 +github, level 9 with dict, advanced one pass small out, 39326 +github, level 13, advanced one pass small out, 133717 +github, level 13 with dict, advanced one pass small out, 39716 +github, level 16, advanced one pass small out, 133717 +github, level 16 with dict, advanced one pass small out, 37577 +github, level 19, advanced one pass small out, 133717 +github, level 19 with dict, advanced one pass small out, 37576 +github, no source size, advanced one pass small out, 136397 +github, long distance mode, advanced one pass small out, 136397 +github, multithreaded, advanced one pass small out, 136397 +github, multithreaded long distance mode, advanced one pass small out, 136397 +github, small window log, advanced one pass small out, 136397 +github, small hash log, advanced one pass small out, 135467 +github, small chain log, advanced one pass small out, 136314 +github, explicit params, advanced one pass small out, 137670 +github, uncompressed literals, advanced one pass small out, 167004 +github, uncompressed literals optimal, advanced one pass small out, 156824 +github, huffman literals, advanced one pass small out, 142450 +github, multithreaded with advanced params, advanced one pass small out, 167004 +silesia, level -5, advanced streaming, 6882466 +silesia, level -3, advanced streaming, 6568358 +silesia, level -1, advanced streaming, 6183385 +silesia, level 0, advanced streaming, 4862377 +silesia, level 1, advanced streaming, 5314109 +silesia, level 3, advanced streaming, 4862377 +silesia, level 4, advanced streaming, 4800629 +silesia, level 5, advanced streaming, 4710178 +silesia, level 6, advanced streaming, 4659996 +silesia, level 7, advanced streaming, 4596234 +silesia, level 9, advanced streaming, 4543862 +silesia, level 13, advanced streaming, 4482073 +silesia, level 16, advanced streaming, 4377391 +silesia, level 19, advanced streaming, 4293262 +silesia, no source size, advanced streaming, 4862341 +silesia, long distance mode, advanced streaming, 4853389 +silesia, multithreaded, advanced streaming, 4862377 +silesia, multithreaded long distance mode, advanced streaming, 4853389 +silesia, small window log, advanced streaming, 7126389 +silesia, small hash log, advanced streaming, 6554898 +silesia, small chain log, advanced streaming, 4931093 +silesia, explicit params, advanced streaming, 4815380 +silesia, uncompressed literals, advanced streaming, 5155424 +silesia, uncompressed literals optimal, advanced streaming, 4325427 +silesia, huffman literals, advanced streaming, 5331110 +silesia, multithreaded with advanced params, advanced streaming, 5155424 +silesia.tar, level -5, advanced streaming, 6982738 +silesia.tar, level -3, advanced streaming, 6641264 +silesia.tar, level -1, advanced streaming, 6190789 +silesia.tar, level 0, advanced streaming, 4875010 +silesia.tar, level 1, advanced streaming, 5336879 +silesia.tar, level 3, advanced streaming, 4875010 +silesia.tar, level 4, advanced streaming, 4813507 +silesia.tar, level 5, advanced streaming, 4722240 +silesia.tar, level 6, advanced streaming, 4672203 +silesia.tar, level 7, advanced streaming, 4606658 +silesia.tar, level 9, advanced streaming, 4554105 +silesia.tar, level 13, advanced streaming, 4491703 +silesia.tar, level 16, advanced streaming, 4381277 +silesia.tar, level 19, advanced streaming, 4281514 +silesia.tar, no source size, advanced streaming, 4875006 +silesia.tar, long distance mode, advanced streaming, 4861218 +silesia.tar, multithreaded, advanced streaming, 4875132 +silesia.tar, multithreaded long distance mode, advanced streaming, 4866971 +silesia.tar, small window log, advanced streaming, 7130394 +silesia.tar, small hash log, advanced streaming, 6587834 +silesia.tar, small chain log, advanced streaming, 4943260 +silesia.tar, explicit params, advanced streaming, 4830002 +silesia.tar, uncompressed literals, advanced streaming, 5157995 +silesia.tar, uncompressed literals optimal, advanced streaming, 4321094 +silesia.tar, huffman literals, advanced streaming, 5352306 +silesia.tar, multithreaded with advanced params, advanced streaming, 5158130 +github, level -5, advanced streaming, 205285 +github, level -5 with dict, advanced streaming, 46718 +github, level -3, advanced streaming, 190643 +github, level -3 with dict, advanced streaming, 45395 +github, level -1, advanced streaming, 175568 +github, level -1 with dict, advanced streaming, 43170 +github, level 0, advanced streaming, 136397 +github, level 0 with dict, advanced streaming, 41170 +github, level 1, advanced streaming, 142450 +github, level 1 with dict, advanced streaming, 41682 +github, level 3, advanced streaming, 136397 +github, level 3 with dict, advanced streaming, 41170 +github, level 4, advanced streaming, 136144 +github, level 4 with dict, advanced streaming, 41306 +github, level 5, advanced streaming, 135106 +github, level 5 with dict, advanced streaming, 38938 +github, level 6, advanced streaming, 135108 +github, level 6 with dict, advanced streaming, 38632 +github, level 7, advanced streaming, 135108 +github, level 7 with dict, advanced streaming, 38766 +github, level 9, advanced streaming, 135108 +github, level 9 with dict, advanced streaming, 39326 +github, level 13, advanced streaming, 133717 +github, level 13 with dict, advanced streaming, 39716 +github, level 16, advanced streaming, 133717 +github, level 16 with dict, advanced streaming, 37577 +github, level 19, advanced streaming, 133717 +github, level 19 with dict, advanced streaming, 37576 +github, no source size, advanced streaming, 136397 +github, long distance mode, advanced streaming, 136397 +github, multithreaded, advanced streaming, 136397 +github, multithreaded long distance mode, advanced streaming, 136397 +github, small window log, advanced streaming, 136397 +github, small hash log, advanced streaming, 135467 +github, small chain log, advanced streaming, 136314 +github, explicit params, advanced streaming, 137670 +github, uncompressed literals, advanced streaming, 167004 +github, uncompressed literals optimal, advanced streaming, 156824 +github, huffman literals, advanced streaming, 142450 +github, multithreaded with advanced params, advanced streaming, 167004 +silesia, level -5, old streaming, 6882466 +silesia, level -3, old streaming, 6568358 +silesia, level -1, old streaming, 6183385 +silesia, level 0, old streaming, 4862377 +silesia, level 1, old streaming, 5314109 +silesia, level 3, old streaming, 4862377 +silesia, level 4, old streaming, 4800629 +silesia, level 5, old streaming, 4710178 +silesia, level 6, old streaming, 4659996 +silesia, level 7, old streaming, 4596234 +silesia, level 9, old streaming, 4543862 +silesia, level 13, old streaming, 4482073 +silesia, level 16, old streaming, 4377391 +silesia, level 19, old streaming, 4293262 +silesia, no source size, old streaming, 4862341 +silesia, long distance mode, old streaming, 12000408 +silesia, multithreaded, old streaming, 12000408 +silesia, multithreaded long distance mode, old streaming, 12000408 +silesia, small window log, old streaming, 12000408 +silesia, small hash log, old streaming, 12000408 +silesia, small chain log, old streaming, 12000408 +silesia, explicit params, old streaming, 12000408 +silesia, uncompressed literals, old streaming, 4862377 +silesia, uncompressed literals optimal, old streaming, 4293262 +silesia, huffman literals, old streaming, 6183385 +silesia, multithreaded with advanced params, old streaming, 12000408 +silesia.tar, level -5, old streaming, 6982738 +silesia.tar, level -3, old streaming, 6641264 +silesia.tar, level -1, old streaming, 6190789 +silesia.tar, level 0, old streaming, 4875010 +silesia.tar, level 1, old streaming, 5336879 +silesia.tar, level 3, old streaming, 4875010 +silesia.tar, level 4, old streaming, 4813507 +silesia.tar, level 5, old streaming, 4722240 +silesia.tar, level 6, old streaming, 4672203 +silesia.tar, level 7, old streaming, 4606658 +silesia.tar, level 9, old streaming, 4554105 +silesia.tar, level 13, old streaming, 4491703 +silesia.tar, level 16, old streaming, 4381277 +silesia.tar, level 19, old streaming, 4281514 +silesia.tar, no source size, old streaming, 4875006 +silesia.tar, long distance mode, old streaming, 12022046 +silesia.tar, multithreaded, old streaming, 12022046 +silesia.tar, multithreaded long distance mode, old streaming, 12022046 +silesia.tar, small window log, old streaming, 12022046 +silesia.tar, small hash log, old streaming, 12022046 +silesia.tar, small chain log, old streaming, 12022046 +silesia.tar, explicit params, old streaming, 12022046 +silesia.tar, uncompressed literals, old streaming, 4875010 +silesia.tar, uncompressed literals optimal, old streaming, 4281514 +silesia.tar, huffman literals, old streaming, 6190789 +silesia.tar, multithreaded with advanced params, old streaming, 12022046 +github, level -5, old streaming, 205285 +github, level -5 with dict, old streaming, 46718 +github, level -3, old streaming, 190643 +github, level -3 with dict, old streaming, 45395 +github, level -1, old streaming, 175568 +github, level -1 with dict, old streaming, 43170 +github, level 0, old streaming, 136397 +github, level 0 with dict, old streaming, 41170 +github, level 1, old streaming, 142450 +github, level 1 with dict, old streaming, 41682 +github, level 3, old streaming, 136397 +github, level 3 with dict, old streaming, 41170 +github, level 4, old streaming, 136144 +github, level 4 with dict, old streaming, 41306 +github, level 5, old streaming, 135106 +github, level 5 with dict, old streaming, 38938 +github, level 6, old streaming, 135108 +github, level 6 with dict, old streaming, 38632 +github, level 7, old streaming, 135108 +github, level 7 with dict, old streaming, 38766 +github, level 9, old streaming, 135108 +github, level 9 with dict, old streaming, 39326 +github, level 13, old streaming, 133717 +github, level 13 with dict, old streaming, 39716 +github, level 16, old streaming, 133717 +github, level 16 with dict, old streaming, 37577 +github, level 19, old streaming, 133717 +github, level 19 with dict, old streaming, 37576 +github, no source size, old streaming, 141003 +github, long distance mode, old streaming, 412933 +github, multithreaded, old streaming, 412933 +github, multithreaded long distance mode, old streaming, 412933 +github, small window log, old streaming, 412933 +github, small hash log, old streaming, 412933 +github, small chain log, old streaming, 412933 +github, explicit params, old streaming, 412933 +github, uncompressed literals, old streaming, 136397 +github, uncompressed literals optimal, old streaming, 133717 +github, huffman literals, old streaming, 175568 +github, multithreaded with advanced params, old streaming, 412933 +silesia, level -5, old streaming advanced, 6882466 +silesia, level -3, old streaming advanced, 6568358 +silesia, level -1, old streaming advanced, 6183385 +silesia, level 0, old streaming advanced, 4862377 +silesia, level 1, old streaming advanced, 5314109 +silesia, level 3, old streaming advanced, 4862377 +silesia, level 4, old streaming advanced, 4800629 +silesia, level 5, old streaming advanced, 4710178 +silesia, level 6, old streaming advanced, 4659996 +silesia, level 7, old streaming advanced, 4596234 +silesia, level 9, old streaming advanced, 4543862 +silesia, level 13, old streaming advanced, 4482073 +silesia, level 16, old streaming advanced, 4377391 +silesia, level 19, old streaming advanced, 4293262 +silesia, no source size, old streaming advanced, 4862341 +silesia, long distance mode, old streaming advanced, 12000408 +silesia, multithreaded, old streaming advanced, 12000408 +silesia, multithreaded long distance mode, old streaming advanced, 12000408 +silesia, small window log, old streaming advanced, 12000408 +silesia, small hash log, old streaming advanced, 12000408 +silesia, small chain log, old streaming advanced, 12000408 +silesia, explicit params, old streaming advanced, 12000408 +silesia, uncompressed literals, old streaming advanced, 4862377 +silesia, uncompressed literals optimal, old streaming advanced, 4293262 +silesia, huffman literals, old streaming advanced, 6183385 +silesia, multithreaded with advanced params, old streaming advanced, 12000408 +silesia.tar, level -5, old streaming advanced, 6982738 +silesia.tar, level -3, old streaming advanced, 6641264 +silesia.tar, level -1, old streaming advanced, 6190789 +silesia.tar, level 0, old streaming advanced, 4875010 +silesia.tar, level 1, old streaming advanced, 5336879 +silesia.tar, level 3, old streaming advanced, 4875010 +silesia.tar, level 4, old streaming advanced, 4813507 +silesia.tar, level 5, old streaming advanced, 4722240 +silesia.tar, level 6, old streaming advanced, 4672203 +silesia.tar, level 7, old streaming advanced, 4606658 +silesia.tar, level 9, old streaming advanced, 4554105 +silesia.tar, level 13, old streaming advanced, 4491703 +silesia.tar, level 16, old streaming advanced, 4381277 +silesia.tar, level 19, old streaming advanced, 4281514 +silesia.tar, no source size, old streaming advanced, 4875006 +silesia.tar, long distance mode, old streaming advanced, 12022046 +silesia.tar, multithreaded, old streaming advanced, 12022046 +silesia.tar, multithreaded long distance mode, old streaming advanced, 12022046 +silesia.tar, small window log, old streaming advanced, 12022046 +silesia.tar, small hash log, old streaming advanced, 12022046 +silesia.tar, small chain log, old streaming advanced, 12022046 +silesia.tar, explicit params, old streaming advanced, 12022046 +silesia.tar, uncompressed literals, old streaming advanced, 4875010 +silesia.tar, uncompressed literals optimal, old streaming advanced, 4281514 +silesia.tar, huffman literals, old streaming advanced, 6190789 +silesia.tar, multithreaded with advanced params, old streaming advanced, 12022046 +github, level -5, old streaming advanced, 205285 +github, level -5 with dict, old streaming advanced, 46718 +github, level -3, old streaming advanced, 190643 +github, level -3 with dict, old streaming advanced, 45395 +github, level -1, old streaming advanced, 175568 +github, level -1 with dict, old streaming advanced, 43170 +github, level 0, old streaming advanced, 136397 +github, level 0 with dict, old streaming advanced, 41170 +github, level 1, old streaming advanced, 142450 +github, level 1 with dict, old streaming advanced, 41682 +github, level 3, old streaming advanced, 136397 +github, level 3 with dict, old streaming advanced, 41170 +github, level 4, old streaming advanced, 136144 +github, level 4 with dict, old streaming advanced, 41306 +github, level 5, old streaming advanced, 135106 +github, level 5 with dict, old streaming advanced, 38938 +github, level 6, old streaming advanced, 135108 +github, level 6 with dict, old streaming advanced, 38632 +github, level 7, old streaming advanced, 135108 +github, level 7 with dict, old streaming advanced, 38766 +github, level 9, old streaming advanced, 135108 +github, level 9 with dict, old streaming advanced, 39326 +github, level 13, old streaming advanced, 133717 +github, level 13 with dict, old streaming advanced, 39716 +github, level 16, old streaming advanced, 133717 +github, level 16 with dict, old streaming advanced, 37577 +github, level 19, old streaming advanced, 133717 +github, level 19 with dict, old streaming advanced, 37576 +github, no source size, old streaming advanced, 141003 +github, long distance mode, old streaming advanced, 412933 +github, multithreaded, old streaming advanced, 412933 +github, multithreaded long distance mode, old streaming advanced, 412933 +github, small window log, old streaming advanced, 412933 +github, small hash log, old streaming advanced, 412933 +github, small chain log, old streaming advanced, 412933 +github, explicit params, old streaming advanced, 412933 +github, uncompressed literals, old streaming advanced, 136397 +github, uncompressed literals optimal, old streaming advanced, 133717 +github, huffman literals, old streaming advanced, 175568 +github, multithreaded with advanced params, old streaming advanced, 412933 +silesia, level -5, old streaming cdcit, 6882466 +silesia, level -3, old streaming cdcit, 6568358 +silesia, level -1, old streaming cdcit, 6183385 +silesia, level 0, old streaming cdcit, 4862377 +silesia, level 1, old streaming cdcit, 5314109 +silesia, level 3, old streaming cdcit, 4862377 +silesia, level 4, old streaming cdcit, 4800629 +silesia, level 5, old streaming cdcit, 4710178 +silesia, level 6, old streaming cdcit, 4659996 +silesia, level 7, old streaming cdcit, 4596234 +silesia, level 9, old streaming cdcit, 4543862 +silesia, level 13, old streaming cdcit, 4482073 +silesia, level 16, old streaming cdcit, 4377391 +silesia, level 19, old streaming cdcit, 4293262 +silesia, no source size, old streaming cdcit, 4862341 +silesia, long distance mode, old streaming cdcit, 12000408 +silesia, multithreaded, old streaming cdcit, 12000408 +silesia, multithreaded long distance mode, old streaming cdcit, 12000408 +silesia, small window log, old streaming cdcit, 12000408 +silesia, small hash log, old streaming cdcit, 12000408 +silesia, small chain log, old streaming cdcit, 12000408 +silesia, explicit params, old streaming cdcit, 12000408 +silesia, uncompressed literals, old streaming cdcit, 4862377 +silesia, uncompressed literals optimal, old streaming cdcit, 4293262 +silesia, huffman literals, old streaming cdcit, 6183385 +silesia, multithreaded with advanced params, old streaming cdcit, 12000408 +silesia.tar, level -5, old streaming cdcit, 6982738 +silesia.tar, level -3, old streaming cdcit, 6641264 +silesia.tar, level -1, old streaming cdcit, 6190789 +silesia.tar, level 0, old streaming cdcit, 4875010 +silesia.tar, level 1, old streaming cdcit, 5336879 +silesia.tar, level 3, old streaming cdcit, 4875010 +silesia.tar, level 4, old streaming cdcit, 4813507 +silesia.tar, level 5, old streaming cdcit, 4722240 +silesia.tar, level 6, old streaming cdcit, 4672203 +silesia.tar, level 7, old streaming cdcit, 4606658 +silesia.tar, level 9, old streaming cdcit, 4554105 +silesia.tar, level 13, old streaming cdcit, 4491703 +silesia.tar, level 16, old streaming cdcit, 4381277 +silesia.tar, level 19, old streaming cdcit, 4281514 +silesia.tar, no source size, old streaming cdcit, 4875006 +silesia.tar, long distance mode, old streaming cdcit, 12022046 +silesia.tar, multithreaded, old streaming cdcit, 12022046 +silesia.tar, multithreaded long distance mode, old streaming cdcit, 12022046 +silesia.tar, small window log, old streaming cdcit, 12022046 +silesia.tar, small hash log, old streaming cdcit, 12022046 +silesia.tar, small chain log, old streaming cdcit, 12022046 +silesia.tar, explicit params, old streaming cdcit, 12022046 +silesia.tar, uncompressed literals, old streaming cdcit, 4875010 +silesia.tar, uncompressed literals optimal, old streaming cdcit, 4281514 +silesia.tar, huffman literals, old streaming cdcit, 6190789 +silesia.tar, multithreaded with advanced params, old streaming cdcit, 12022046 +github, level -5, old streaming cdcit, 205285 +github, level -5 with dict, old streaming cdcit, 46718 +github, level -3, old streaming cdcit, 190643 +github, level -3 with dict, old streaming cdcit, 45395 +github, level -1, old streaming cdcit, 175568 +github, level -1 with dict, old streaming cdcit, 43170 +github, level 0, old streaming cdcit, 136397 +github, level 0 with dict, old streaming cdcit, 41170 +github, level 1, old streaming cdcit, 142450 +github, level 1 with dict, old streaming cdcit, 41682 +github, level 3, old streaming cdcit, 136397 +github, level 3 with dict, old streaming cdcit, 41170 +github, level 4, old streaming cdcit, 136144 +github, level 4 with dict, old streaming cdcit, 41306 +github, level 5, old streaming cdcit, 135106 +github, level 5 with dict, old streaming cdcit, 38938 +github, level 6, old streaming cdcit, 135108 +github, level 6 with dict, old streaming cdcit, 38632 +github, level 7, old streaming cdcit, 135108 +github, level 7 with dict, old streaming cdcit, 38766 +github, level 9, old streaming cdcit, 135108 +github, level 9 with dict, old streaming cdcit, 39326 +github, level 13, old streaming cdcit, 133717 +github, level 13 with dict, old streaming cdcit, 39716 +github, level 16, old streaming cdcit, 133717 +github, level 16 with dict, old streaming cdcit, 37577 +github, level 19, old streaming cdcit, 133717 +github, level 19 with dict, old streaming cdcit, 37576 +github, no source size, old streaming cdcit, 141003 +github, long distance mode, old streaming cdcit, 412933 +github, multithreaded, old streaming cdcit, 412933 +github, multithreaded long distance mode, old streaming cdcit, 412933 +github, small window log, old streaming cdcit, 412933 +github, small hash log, old streaming cdcit, 412933 +github, small chain log, old streaming cdcit, 412933 +github, explicit params, old streaming cdcit, 412933 +github, uncompressed literals, old streaming cdcit, 136397 +github, uncompressed literals optimal, old streaming cdcit, 133717 +github, huffman literals, old streaming cdcit, 175568 +github, multithreaded with advanced params, old streaming cdcit, 412933 +silesia, level -5, old streaming advanced cdict, 6882466 +silesia, level -3, old streaming advanced cdict, 6568358 +silesia, level -1, old streaming advanced cdict, 6183385 +silesia, level 0, old streaming advanced cdict, 4862377 +silesia, level 1, old streaming advanced cdict, 5314109 +silesia, level 3, old streaming advanced cdict, 4862377 +silesia, level 4, old streaming advanced cdict, 4800629 +silesia, level 5, old streaming advanced cdict, 4710178 +silesia, level 6, old streaming advanced cdict, 4659996 +silesia, level 7, old streaming advanced cdict, 4596234 +silesia, level 9, old streaming advanced cdict, 4543862 +silesia, level 13, old streaming advanced cdict, 4482073 +silesia, level 16, old streaming advanced cdict, 4377391 +silesia, level 19, old streaming advanced cdict, 4293262 +silesia, no source size, old streaming advanced cdict, 4862341 +silesia, long distance mode, old streaming advanced cdict, 12000408 +silesia, multithreaded, old streaming advanced cdict, 12000408 +silesia, multithreaded long distance mode, old streaming advanced cdict, 12000408 +silesia, small window log, old streaming advanced cdict, 12000408 +silesia, small hash log, old streaming advanced cdict, 12000408 +silesia, small chain log, old streaming advanced cdict, 12000408 +silesia, explicit params, old streaming advanced cdict, 12000408 +silesia, uncompressed literals, old streaming advanced cdict, 4862377 +silesia, uncompressed literals optimal, old streaming advanced cdict, 4293262 +silesia, huffman literals, old streaming advanced cdict, 6183385 +silesia, multithreaded with advanced params, old streaming advanced cdict, 12000408 +silesia.tar, level -5, old streaming advanced cdict, 6982738 +silesia.tar, level -3, old streaming advanced cdict, 6641264 +silesia.tar, level -1, old streaming advanced cdict, 6190789 +silesia.tar, level 0, old streaming advanced cdict, 4875010 +silesia.tar, level 1, old streaming advanced cdict, 5336879 +silesia.tar, level 3, old streaming advanced cdict, 4875010 +silesia.tar, level 4, old streaming advanced cdict, 4813507 +silesia.tar, level 5, old streaming advanced cdict, 4722240 +silesia.tar, level 6, old streaming advanced cdict, 4672203 +silesia.tar, level 7, old streaming advanced cdict, 4606658 +silesia.tar, level 9, old streaming advanced cdict, 4554105 +silesia.tar, level 13, old streaming advanced cdict, 4491703 +silesia.tar, level 16, old streaming advanced cdict, 4381277 +silesia.tar, level 19, old streaming advanced cdict, 4281514 +silesia.tar, no source size, old streaming advanced cdict, 4875006 +silesia.tar, long distance mode, old streaming advanced cdict, 12022046 +silesia.tar, multithreaded, old streaming advanced cdict, 12022046 +silesia.tar, multithreaded long distance mode, old streaming advanced cdict, 12022046 +silesia.tar, small window log, old streaming advanced cdict, 12022046 +silesia.tar, small hash log, old streaming advanced cdict, 12022046 +silesia.tar, small chain log, old streaming advanced cdict, 12022046 +silesia.tar, explicit params, old streaming advanced cdict, 12022046 +silesia.tar, uncompressed literals, old streaming advanced cdict, 4875010 +silesia.tar, uncompressed literals optimal, old streaming advanced cdict, 4281514 +silesia.tar, huffman literals, old streaming advanced cdict, 6190789 +silesia.tar, multithreaded with advanced params, old streaming advanced cdict, 12022046 +github, level -5, old streaming advanced cdict, 205285 +github, level -5 with dict, old streaming advanced cdict, 46718 +github, level -3, old streaming advanced cdict, 190643 +github, level -3 with dict, old streaming advanced cdict, 45395 +github, level -1, old streaming advanced cdict, 175568 +github, level -1 with dict, old streaming advanced cdict, 43170 +github, level 0, old streaming advanced cdict, 136397 +github, level 0 with dict, old streaming advanced cdict, 41170 +github, level 1, old streaming advanced cdict, 142450 +github, level 1 with dict, old streaming advanced cdict, 41682 +github, level 3, old streaming advanced cdict, 136397 +github, level 3 with dict, old streaming advanced cdict, 41170 +github, level 4, old streaming advanced cdict, 136144 +github, level 4 with dict, old streaming advanced cdict, 41306 +github, level 5, old streaming advanced cdict, 135106 +github, level 5 with dict, old streaming advanced cdict, 38938 +github, level 6, old streaming advanced cdict, 135108 +github, level 6 with dict, old streaming advanced cdict, 38632 +github, level 7, old streaming advanced cdict, 135108 +github, level 7 with dict, old streaming advanced cdict, 38766 +github, level 9, old streaming advanced cdict, 135108 +github, level 9 with dict, old streaming advanced cdict, 39326 +github, level 13, old streaming advanced cdict, 133717 +github, level 13 with dict, old streaming advanced cdict, 39716 +github, level 16, old streaming advanced cdict, 133717 +github, level 16 with dict, old streaming advanced cdict, 37577 +github, level 19, old streaming advanced cdict, 133717 +github, level 19 with dict, old streaming advanced cdict, 37576 +github, no source size, old streaming advanced cdict, 141003 +github, long distance mode, old streaming advanced cdict, 412933 +github, multithreaded, old streaming advanced cdict, 412933 +github, multithreaded long distance mode, old streaming advanced cdict, 412933 +github, small window log, old streaming advanced cdict, 412933 +github, small hash log, old streaming advanced cdict, 412933 +github, small chain log, old streaming advanced cdict, 412933 +github, explicit params, old streaming advanced cdict, 412933 +github, uncompressed literals, old streaming advanced cdict, 136397 +github, uncompressed literals optimal, old streaming advanced cdict, 133717 +github, huffman literals, old streaming advanced cdict, 175568 +github, multithreaded with advanced params, old streaming advanced cdict, 412933 diff --git a/tests/regression/test.c b/tests/regression/test.c index 9e7b83c19daf..812893b2730e 100644 --- a/tests/regression/test.c +++ b/tests/regression/test.c @@ -153,7 +153,7 @@ static void print_help(void) { } } -/** Parse the arguments. Teturn 0 on success. Print help on failure. */ +/** Parse the arguments. Return 0 on success. Print help on failure. */ static int parse_args(int argc, char** argv) { int option_index = 0; int c; diff --git a/tests/roundTripCrash.c b/tests/roundTripCrash.c index 3f4ace8c9800..3de5933185d5 100644 --- a/tests/roundTripCrash.c +++ b/tests/roundTripCrash.c @@ -93,9 +93,9 @@ static size_t cctxParamRoundTripTest(void* resultBuff, size_t resultBuffCapacity int const cLevel = h32 % maxClevel; /* Set parameters */ - CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) ); - CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) ); - CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_overlapLog, 5) ); + CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) ); + CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) ); + CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_overlapLog, 5) ); /* Apply parameters */ diff --git a/tests/symbols.c b/tests/symbols.c index 600d81670a55..4d9c6fc0c9e2 100644 --- a/tests/symbols.c +++ b/tests/symbols.c @@ -31,6 +31,7 @@ static const void *symbols[] = { &ZSTD_getFrameContentSize, &ZSTD_maxCLevel, &ZSTD_compressBound, + &ZSTD_decompressBound, &ZSTD_isError, &ZSTD_getErrorName, &ZSTD_createCCtx, diff --git a/tests/zbufftest.c b/tests/zbufftest.c index 9b6f7bad6dc6..8cbde3f4f38e 100644 --- a/tests/zbufftest.c +++ b/tests/zbufftest.c @@ -25,6 +25,7 @@ #include /* free */ #include /* fgets, sscanf */ #include /* strcmp */ +#include "timefn.h" /* UTIL_time_t */ #include "mem.h" #define ZSTD_STATIC_LINKING_ONLY /* ZSTD_maxCLevel */ #include "zstd.h" /* ZSTD_compressBound */ diff --git a/tests/zstreamtest.c b/tests/zstreamtest.c index ac300890415f..55c14ad5995f 100644 --- a/tests/zstreamtest.c +++ b/tests/zstreamtest.c @@ -26,6 +26,7 @@ #include /* fgets, sscanf */ #include /* strcmp */ #include /* assert */ +#include "timefn.h" /* UTIL_time_t, UTIL_getTime */ #include "mem.h" #define ZSTD_STATIC_LINKING_ONLY /* ZSTD_maxCLevel, ZSTD_customMem, ZSTD_getDictID_fromFrame */ #include "zstd.h" /* ZSTD_compressBound */ @@ -37,6 +38,7 @@ #include "xxhash.h" /* XXH64_* */ #include "seqgen.h" #include "util.h" +#include "timefn.h" /* UTIL_time_t, UTIL_clockSpanMicro, UTIL_getTime */ /*-************************************ @@ -344,6 +346,20 @@ static int basicUnitTests(U32 seed, double compressibility) DISPLAYLEVEL(3, "OK (%u bytes) \n", (unsigned)(cstreamSize + cdictSize)); } + /* context size functions */ + DISPLAYLEVEL(3, "test%3i : estimate CStream size using CCtxParams : ", testNb++); + { ZSTD_CCtx_params* const params = ZSTD_createCCtxParams(); + size_t cstreamSize, cctxSize; + CHECK_Z( ZSTD_CCtxParams_setParameter(params, ZSTD_c_compressionLevel, 19) ); + cstreamSize = ZSTD_estimateCStreamSize_usingCCtxParams(params); + CHECK_Z(cstreamSize); + cctxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params); + CHECK_Z(cctxSize); + if (cstreamSize <= cctxSize + 2 * ZSTD_BLOCKSIZE_MAX) goto _output_error; + ZSTD_freeCCtxParams(params); + DISPLAYLEVEL(3, "OK \n"); + } + DISPLAYLEVEL(3, "test%3i : check actual CStream size : ", testNb++); { size_t const s = ZSTD_sizeof_CStream(zc); if (ZSTD_isError(s)) goto _output_error; @@ -495,7 +511,7 @@ static int basicUnitTests(U32 seed, double compressibility) /* _srcSize compression test */ DISPLAYLEVEL(3, "test%3i : compress_srcSize %u bytes : ", testNb++, COMPRESSIBLE_NOISE_LENGTH); - ZSTD_initCStream_srcSize(zc, 1, CNBufferSize); + CHECK_Z( ZSTD_initCStream_srcSize(zc, 1, CNBufferSize) ); outBuff.dst = (char*)(compressedBuffer); outBuff.size = compressedBufferSize; outBuff.pos = 0; @@ -503,11 +519,14 @@ static int basicUnitTests(U32 seed, double compressibility) inBuff.size = CNBufferSize; inBuff.pos = 0; CHECK_Z( ZSTD_compressStream(zc, &outBuff, &inBuff) ); - if (inBuff.pos != inBuff.size) goto _output_error; /* entire input should be consumed */ - { size_t const r = ZSTD_endStream(zc, &outBuff); - if (r != 0) goto _output_error; } /* error, or some data not flushed */ - { unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos); - if ((size_t)origSize != CNBufferSize) goto _output_error; } /* exact original size must be present */ + CHECK(inBuff.pos != inBuff.size, "Entire input should be consumed"); + { size_t const r = ZSTD_endStream(zc, &outBuff); + CHECK(r != 0, "Error or some data not flushed (ret=%zu)", r); + } + { unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos); + CHECK(origSize == ZSTD_CONTENTSIZE_UNKNOWN, "Unknown!"); + CHECK((size_t)origSize != CNBufferSize, "Exact original size must be present (got %llu)", origSize); + } DISPLAYLEVEL(3, "OK (%u bytes : %.2f%%)\n", (unsigned)cSize, (double)cSize/COMPRESSIBLE_NOISE_LENGTH*100); /* wrong _srcSize compression test */ @@ -706,6 +725,156 @@ static int basicUnitTests(U32 seed, double compressibility) } DISPLAYLEVEL(3, "OK\n"); + ZSTD_CCtx_reset(zc, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_CCtx_loadDictionary(zc, dictionary.start, dictionary.filled) ); + cSize = ZSTD_compress2(zc, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBufferSize, 100 KB)); + CHECK_Z(cSize); + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressStream() with dictionary : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + /* We should fail to decompress without a dictionary. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + size_t const ret = ZSTD_decompressStream(dctx, &out, &in); + if (!ZSTD_isError(ret)) goto _output_error; + } + /* We should succeed to decompress with the dictionary. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictionary.start, dictionary.filled) ); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The dictionary should presist across calls. */ + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The dictionary should not be cleared by ZSTD_reset_session_only. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* When we reset the context the dictionary is cleared. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + size_t const ret = ZSTD_decompressStream(dctx, &out, &in); + if (!ZSTD_isError(ret)) goto _output_error; + } + ZSTD_freeDCtx(dctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_resetDStream() with dictionary : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + /* We should succeed to decompress with the dictionary. */ + ZSTD_resetDStream(dctx); + CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictionary.start, dictionary.filled) ); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The dictionary should not be cleared by ZSTD_resetDStream(). */ + ZSTD_resetDStream(dctx); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The dictionary should be cleared by ZSTD_initDStream(). */ + CHECK_Z( ZSTD_initDStream(dctx) ); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + size_t const ret = ZSTD_decompressStream(dctx, &out, &in); + if (!ZSTD_isError(ret)) goto _output_error; + } + ZSTD_freeDCtx(dctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressStream() with ddict : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + ZSTD_DDict* ddict = ZSTD_createDDict(dictionary.start, dictionary.filled); + /* We should succeed to decompress with the ddict. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_refDDict(dctx, ddict) ); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The ddict should presist across calls. */ + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* When we reset the context the ddict is cleared. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + size_t const ret = ZSTD_decompressStream(dctx, &out, &in); + if (!ZSTD_isError(ret)) goto _output_error; + } + ZSTD_freeDCtx(dctx); + ZSTD_freeDDict(ddict); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with prefix : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + /* We should succeed to decompress with the prefix. */ + ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters); + CHECK_Z( ZSTD_DCtx_refPrefix_advanced(dctx, dictionary.start, dictionary.filled, ZSTD_dct_auto) ); + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + if (ZSTD_decompressStream(dctx, &out, &in) != 0) goto _output_error; + if (in.pos != in.size) goto _output_error; + } + /* The prefix should be cleared after the first compression. */ + { ZSTD_outBuffer out = {decodedBuffer, decodedBufferSize, 0}; + ZSTD_inBuffer in = {compressedBuffer, cSize, 0}; + size_t const ret = ZSTD_decompressStream(dctx, &out, &in); + if (!ZSTD_isError(ret)) goto _output_error; + } + ZSTD_freeDCtx(dctx); + } + DISPLAYLEVEL(3, "OK \n"); + + DISPLAYLEVEL(3, "test%3i : ZSTD_initDStream*() with dictionary : ", testNb++); + { + ZSTD_DCtx* dctx = ZSTD_createDCtx(); + ZSTD_DDict* ddict = ZSTD_createDDict(dictionary.start, dictionary.filled); + size_t ret; + /* We should succeed to decompress with the dictionary. */ + CHECK_Z( ZSTD_initDStream_usingDict(dctx, dictionary.start, dictionary.filled) ); + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) ); + /* The dictionary should presist across calls. */ + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) ); + /* We should succeed to decompress with the ddict. */ + CHECK_Z( ZSTD_initDStream_usingDDict(dctx, ddict) ); + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) ); + /* The ddict should presist across calls. */ + CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize) ); + /* When we reset the context the ddict is cleared. */ + CHECK_Z( ZSTD_initDStream(dctx) ); + ret = ZSTD_decompressDCtx(dctx, decodedBuffer, decodedBufferSize, compressedBuffer, cSize); + if (!ZSTD_isError(ret)) goto _output_error; + ZSTD_freeDCtx(dctx); + ZSTD_freeDDict(ddict); + } + DISPLAYLEVEL(3, "OK \n"); + DISPLAYLEVEL(3, "test%3i : ZSTD_initCStream_usingCDict_advanced with masked dictID : ", testNb++); { ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBufferSize, dictionary.filled); ZSTD_frameParameters const fParams = { 1 /* contentSize */, 1 /* checksum */, 1 /* noDictID */}; @@ -882,7 +1051,7 @@ static int basicUnitTests(U32 seed, double compressibility) inBuff.size = srcSize; assert(srcSize < COMPRESSIBLE_NOISE_LENGTH); inBuff.pos = 0; } - { ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, 4 KB, dictionary.filled); /* intentionnally lies on estimatedSrcSize, to push cdict into targeting a small window size */ + { ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, 4 KB, dictionary.filled); /* intentionally lies on estimatedSrcSize, to push cdict into targeting a small window size */ ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictionary.start, dictionary.filled, ZSTD_dlm_byRef, ZSTD_dct_fullDict, cParams, ZSTD_defaultCMem); DISPLAYLEVEL(5, "cParams.windowLog = %u : ", cParams.windowLog); CHECK_Z( ZSTD_CCtx_refCDict(zc, cdict) ); @@ -1703,7 +1872,7 @@ static size_t setCCtxParameter(ZSTD_CCtx* zc, ZSTD_CCtx_params* cctxParams, int useOpaqueAPI) { if (useOpaqueAPI) { - return ZSTD_CCtxParam_setParameter(cctxParams, param, value); + return ZSTD_CCtxParams_setParameter(cctxParams, param, value); } else { return ZSTD_CCtx_setParameter(zc, param, value); } @@ -1900,7 +2069,7 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest, CHECK_Z( ZSTD_CCtx_setPledgedSrcSize(zc, pledgedSrcSize) ); } - /* multi-threading parameters. Only adjust ocassionally for small tests. */ + /* multi-threading parameters. Only adjust occasionally for small tests. */ if (bigTests || (FUZ_rand(&lseed) & 0xF) == 0xF) { U32 const nbThreadsCandidate = (FUZ_rand(&lseed) & 4) + 1; U32 const nbThreadsAdjusted = (windowLogMalus < nbThreadsCandidate) ? nbThreadsCandidate - windowLogMalus : 1; @@ -1930,16 +2099,6 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest, } else { CHECK_Z( ZSTD_CCtx_loadDictionary_byReference(zc, dict, dictSize) ); } - if (dict && dictSize) { - /* test that compression parameters are rejected (correctly) after loading a non-NULL dictionary */ - if (opaqueAPI) { - size_t const setError = ZSTD_CCtx_setParametersUsingCCtxParams(zc, cctxParams); - CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParametersUsingCCtxParams should have failed"); - } else { - size_t const setError = ZSTD_CCtx_setParameter(zc, ZSTD_c_windowLog, cParams.windowLog-1); - CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParameter should have failed"); - } - } } else { CHECK_Z( ZSTD_CCtx_refPrefix(zc, dict, dictSize) ); } diff --git a/zlibWrapper/Makefile b/zlibWrapper/Makefile index 0c19107b3e6f..d4fc33b51e7b 100644 --- a/zlibWrapper/Makefile +++ b/zlibWrapper/Makefile @@ -88,7 +88,7 @@ fitblk: $(EXAMPLE_PATH)/fitblk.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(ZSTDLI fitblk_zstd: $(EXAMPLE_PATH)/fitblk.o $(ZLIBWRAPPER_PATH)/zstdTurnedOn_zlibwrapper.o $(ZSTDLIBRARY) $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $^ $(ZLIB_LIBRARY) -o $@ -zwrapbench: $(EXAMPLE_PATH)/zwrapbench.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(PROGRAMS_PATH)/util.o $(PROGRAMS_PATH)/datagen.o $(ZSTDLIBRARY) +zwrapbench: $(EXAMPLE_PATH)/zwrapbench.o $(ZLIBWRAPPER_PATH)/zstd_zlibwrapper.o $(PROGRAMS_PATH)/util.o $(PROGRAMS_PATH)/timefn.o $(PROGRAMS_PATH)/datagen.o $(ZSTDLIBRARY) $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $^ $(ZLIB_LIBRARY) -o $@ diff --git a/zlibWrapper/README.md b/zlibWrapper/README.md index 164b69ace81f..e61767c468fb 100644 --- a/zlibWrapper/README.md +++ b/zlibWrapper/README.md @@ -71,7 +71,7 @@ inflate with dictionary: hello, hello! The script used for compilation can be found at [zlibWrapper/Makefile](Makefile). -#### The measurement of performace of Zstandard wrapper for zlib +#### The measurement of performance of Zstandard wrapper for zlib The zstd distribution contains a tool called `zwrapbench` which can measure speed and ratio of zlib, zstd, and the wrapper. The benchmark is conducted using given filenames or synthetic data if filenames are not provided. @@ -96,8 +96,8 @@ as this case is automatically detected. #### Reusing contexts The ordinary zlib compression of two files/streams allocates two contexts: -- for the 1st file calls `deflateInit`, `deflate`, `...`, `deflate`, `defalateEnd` -- for the 2nd file calls `deflateInit`, `deflate`, `...`, `deflate`, `defalateEnd` +- for the 1st file calls `deflateInit`, `deflate`, `...`, `deflate`, `deflateEnd` +- for the 2nd file calls `deflateInit`, `deflate`, `...`, `deflate`, `deflateEnd` The speed of compression can be improved with reusing a single context with following steps: - initialize the context with `deflateInit` diff --git a/zlibWrapper/examples/fitblk.c b/zlibWrapper/examples/fitblk.c index ee413c3ae916..6418ca38763c 100644 --- a/zlibWrapper/examples/fitblk.c +++ b/zlibWrapper/examples/fitblk.c @@ -21,7 +21,7 @@ data in order to determine how much of that input will compress to nearly the requested output block size. The first pass generates enough deflate blocks to produce output to fill the requested - output size plus a specfied excess amount (see the EXCESS define + output size plus a specified excess amount (see the EXCESS define below). The last deflate block may go quite a bit past that, but is discarded. The second pass decompresses and recompresses just the compressed data that fit in the requested plus excess sized @@ -217,7 +217,7 @@ int main(int argc, char **argv) if (ret == Z_MEM_ERROR) quit("out of memory"); - /* set up for next reocmpression */ + /* set up for next recompression */ ret = inflateReset(&inf); assert(ret != Z_STREAM_ERROR); ret = deflateReset(&def); diff --git a/zlibWrapper/examples/fitblk_original.c b/zlibWrapper/examples/fitblk_original.c index c61de5c99672..20f351bfaf22 100644 --- a/zlibWrapper/examples/fitblk_original.c +++ b/zlibWrapper/examples/fitblk_original.c @@ -17,7 +17,7 @@ data in order to determine how much of that input will compress to nearly the requested output block size. The first pass generates enough deflate blocks to produce output to fill the requested - output size plus a specfied excess amount (see the EXCESS define + output size plus a specified excess amount (see the EXCESS define below). The last deflate block may go quite a bit past that, but is discarded. The second pass decompresses and recompresses just the compressed data that fit in the requested plus excess sized @@ -198,7 +198,7 @@ int main(int argc, char **argv) if (ret == Z_MEM_ERROR) quit("out of memory"); - /* set up for next reocmpression */ + /* set up for next recompression */ ret = inflateReset(&inf); assert(ret != Z_STREAM_ERROR); ret = deflateReset(&def); diff --git a/zlibWrapper/examples/zwrapbench.c b/zlibWrapper/examples/zwrapbench.c index e071c3098525..61031b9de798 100644 --- a/zlibWrapper/examples/zwrapbench.c +++ b/zlibWrapper/examples/zwrapbench.c @@ -19,6 +19,7 @@ #include /* toupper */ #include /* errno */ +#include "timefn.h" /* UTIL_time_t, UTIL_getTime, UTIL_clockSpanMicro, UTIL_waitForNextTick */ #include "mem.h" #define ZSTD_STATIC_LINKING_ONLY #include "zstd.h" @@ -192,7 +193,7 @@ static int BMK_benchMem(z_const void* srcBuffer, size_t srcSize, remaining -= thisBlockSize; } } } - /* warmimg up memory */ + /* warming up memory */ RDG_genBuffer(compressedBuffer, maxCompressedSize, 0.10, 0.50, 1); /* Bench */ diff --git a/zlibWrapper/gzguts.h b/zlibWrapper/gzguts.h index 05bf4d9f4c31..b639b4be85f4 100644 --- a/zlibWrapper/gzguts.h +++ b/zlibWrapper/gzguts.h @@ -38,6 +38,8 @@ #ifdef _WIN32 # include +#else +# include #endif #if defined(__TURBOC__) || defined(_MSC_VER) || defined(_WIN32)