ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #4 from facebook/dev

Browse Source 
pull from facebook/zstd
This commit is contained in:
Paul Cruz
2017-06-26 09:24:13 -07:00
committed by GitHub
parent d549254d3b 379f9d874d
commit d2e2441179
43 changed files with 4288 additions and 1837 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Makefile
+4 -3
View File
@@ -108,7 +108,7 @@ clean:
#------------------------------------------------------------------------------
# make install is validated only for Linux, OSX, Hurd and some BSD targets
#------------------------------------------------------------------------------
ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU FreeBSD DragonFly NetBSD))
ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU FreeBSD DragonFly NetBSD MSYS_NT))
HOST_OS = POSIX
CMAKE_PARAMS = -DZSTD_BUILD_CONTRIB:BOOL=ON -DZSTD_BUILD_STATIC:BOOL=ON -DZSTD_BUILD_TESTS:BOOL=ON -DZSTD_ZLIB_SUPPORT:BOOL=ON -DZSTD_LZMA_SUPPORT:BOOL=ON
@@ -227,7 +227,7 @@ msan: clean
$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=memory -fno-omit-frame-pointer" # datagen.c fails this test for no obvious reason
msan-%: clean
LDFLAGS=-fuse-ld=gold MOREFLAGS="-fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer" $(MAKE) -C $(TESTDIR) $*
LDFLAGS=-fuse-ld=gold MOREFLAGS="-fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer" FUZZER_FLAGS=--no-big-tests $(MAKE) -C $(TESTDIR) $*
asan32: clean
$(MAKE) -C $(TESTDIR) test32 CC=clang MOREFLAGS="-g -fsanitize=address"
@@ -239,7 +239,8 @@ uasan-%: clean
LDFLAGS=-fuse-ld=gold MOREFLAGS="-Og -fno-sanitize-recover=all -fsanitize-recover=signed-integer-overflow -fsanitize=address,undefined" $(MAKE) -C $(TESTDIR) $*
tsan-%: clean
LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=thread" $(MAKE) -C $(TESTDIR) $*
LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=thread" $(MAKE) -C $(TESTDIR) $* FUZZER_FLAGS=--no-big-tests
apt-install:
sudo apt-get -yq --no-install-suggests --no-install-recommends --force-yes install $(APT_PACKAGES)
NEWS
+12
View File
@@ -1,3 +1,15 @@
v1.3.0
cli : new : `--list` command, by Paul Cruz
cli : changed : `-t *` continue processing list after a decompression error
API : added : ZSTD_versionString()
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 : changed : strongest strategy renamed ZSTD_btultra, fastest strategy ZSTD_fast set to 1
API exp : clarified presentation of memory estimation / measurement functions.
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
build/VS2008/fullbench/fullbench.vcproj
+39 -23
View File
@@ -328,10 +328,6 @@
Filter="cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx"
UniqueIdentifier="{4FC737F1-C7A5-4376-A066-2A32D752A2FF}"
>
<File
RelativePath="..\..\..\programs\datagen.c"
>
</File>
<File
RelativePath="..\..\..\lib\common\entropy_common.c"
>
@@ -340,10 +336,6 @@
RelativePath="..\..\..\lib\common\error_private.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\fse_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\common\fse_decompress.c"
>
@@ -352,36 +344,60 @@
RelativePath="..\..\..\lib\common\xxhash.c"
>
</File>
<File
RelativePath="..\..\..\tests\fullbench.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\huf_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\decompress\huf_decompress.c"
>
</File>
<File
RelativePath="..\..\..\lib\common\zstd_common.c"
>
</File>
<File
RelativePath="..\..\..\lib\common\pool.c"
>
</File>
<File
RelativePath="..\..\..\lib\common\threading.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\zstdmt_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\fse_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\compress\huf_compress.c"
>
</File>
<File
RelativePath="..\..\..\lib\decompress\zstd_decompress.c"
>
</File>
<File
RelativePath="..\..\..\lib\decompress\huf_decompress.c"
>
</File>
<File
RelativePath="..\..\..\programs\datagen.c"
>
</File>
<File
RelativePath="..\..\..\tests\fullbench.c"
>
</File>
</Filter>
<Filter
Name="Header Files"
Filter="h;hpp;hxx;hm;inl;inc;xsd"
UniqueIdentifier="{93995380-89BD-4b04-88EB-625FBE52EBFB}"
>
<File
RelativePath="..\..\..\lib\zstd.h"
>
</File>
<File
RelativePath="..\..\..\lib\common\bitstream.h"
>
@@ -419,11 +435,11 @@
>
</File>
<File
RelativePath="..\..\..\lib\zstd.h"
RelativePath="..\..\..\lib\common\zstd_internal.h"
>
</File>
<File
RelativePath="..\..\..\lib\common\zstd_internal.h"
RelativePath="..\..\..\lib\common\zstd_static.h"
>
</File>
<File
@@ -431,7 +447,7 @@
>
</File>
<File
RelativePath="..\..\..\lib\common\zstd_static.h"
RelativePath="..\..\..\lib\compress\zstdmt_compress.h"
>
</File>
</Filter>
build/VS2010/fullbench/fullbench.vcxproj
+9 -3
View File
@@ -156,26 +156,32 @@
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="..\..\..\lib\common\entropy_common.c" />
<ClCompile Include="..\..\..\lib\common\fse_decompress.c" />
<ClCompile Include="..\..\..\lib\common\zstd_common.c" />
<ClCompile Include="..\..\..\lib\common\error_private.c" />
<ClCompile Include="..\..\..\lib\common\pool.c" />
<ClCompile Include="..\..\..\lib\common\threading.c" />
<ClCompile Include="..\..\..\lib\common\xxhash.c" />
<ClCompile Include="..\..\..\lib\common\fse_decompress.c" />
<ClCompile Include="..\..\..\lib\compress\fse_compress.c" />
<ClCompile Include="..\..\..\lib\compress\huf_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstd_compress.c" />
<ClCompile Include="..\..\..\lib\compress\zstdmt_compress.c" />
<ClCompile Include="..\..\..\lib\decompress\huf_decompress.c" />
<ClCompile Include="..\..\..\lib\decompress\zstd_decompress.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />
<ClCompile Include="..\..\..\tests\fullbench.c" />
</ItemGroup>
<ItemGroup>
<ClInclude Include="..\..\..\lib\zstd.h" />
<ClInclude Include="..\..\..\lib\common\fse.h" />
<ClInclude Include="..\..\..\lib\common\huf.h" />
<ClInclude Include="..\..\..\lib\common\xxhash.h" />
<ClInclude Include="..\..\..\lib\common\zstd_errors.h" />
<ClInclude Include="..\..\..\lib\zstd.h" />
<ClInclude Include="..\..\..\lib\common\zstd_internal.h" />
<ClInclude Include="..\..\..\lib\common\pool.h" />
<ClInclude Include="..\..\..\lib\common\threading.h" />
<ClInclude Include="..\..\..\lib\common\xxhash.h" />
<ClInclude Include="..\..\..\lib\compress\zstd_opt.h" />
<ClInclude Include="..\..\..\lib\compress\zstdmt_compress.h" />
<ClInclude Include="..\..\..\lib\legacy\zstd_legacy.h" />
<ClInclude Include="..\..\..\programs\datagen.h" />
<ClInclude Include="..\..\..\programs\util.h" />
contrib/linux-kernel/xxhash.diff → contrib/linux-kernel/0001-lib-Add-xxhash-module.patch
+88 -2
View File
@@ -1,3 +1,86 @@
From e75beb7c2e05550b2846e31ad8a0082c188504da Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Wed, 21 Jun 2017 17:27:42 -0700
Subject: [PATCH 1/4] lib: Add xxhash module
Adds xxhash kernel module with xxh32 and xxh64 hashes. xxhash is an
extremely fast non-cryptographic hash algorithm for checksumming.
The zstd compression and decompression modules added in the next patch
require xxhash. I extracted it out from zstd since it is useful on its
own. I copied the code from the upstream XXHash source repository and
translated it into kernel style. I ran benchmarks and tests in the kernel
and tests in userland.
I benchmarked xxhash as a special character device. I ran in four modes,
no-op, xxh32, xxh64, and crc32. The no-op mode simply copies the data to
kernel space and ignores it. The xxh32, xxh64, and crc32 modes compute
hashes on the copied data. I also ran it with four different buffer sizes.
The benchmark file is located in the upstream zstd source repository under
`contrib/linux-kernel/xxhash_test.c` [1].
I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD. I benchmarked using the file `filesystem.squashfs`
from `ubuntu-16.10-desktop-amd64.iso`, which is 1,536,217,088 B large.
Run the following commands for the benchmark:
modprobe xxhash_test
mknod xxhash_test c 245 0
time cp filesystem.squashfs xxhash_test
The time is reported by the time of the userland `cp`.
The GB/s is computed with
1,536,217,008 B / time(buffer size, hash)
which includes the time to copy from userland.
The Normalized GB/s is computed with
1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)).
| Buffer Size (B) | Hash | Time (s) | GB/s | Adjusted GB/s |
|-----------------|-------|----------|------|---------------|
| 1024 | none | 0.408 | 3.77 | - |
| 1024 | xxh32 | 0.649 | 2.37 | 6.37 |
| 1024 | xxh64 | 0.542 | 2.83 | 11.46 |
| 1024 | crc32 | 1.290 | 1.19 | 1.74 |
| 4096 | none | 0.380 | 4.04 | - |
| 4096 | xxh32 | 0.645 | 2.38 | 5.79 |
| 4096 | xxh64 | 0.500 | 3.07 | 12.80 |
| 4096 | crc32 | 1.168 | 1.32 | 1.95 |
| 8192 | none | 0.351 | 4.38 | - |
| 8192 | xxh32 | 0.614 | 2.50 | 5.84 |
| 8192 | xxh64 | 0.464 | 3.31 | 13.60 |
| 8192 | crc32 | 1.163 | 1.32 | 1.89 |
| 16384 | none | 0.346 | 4.43 | - |
| 16384 | xxh32 | 0.590 | 2.60 | 6.30 |
| 16384 | xxh64 | 0.466 | 3.30 | 12.80 |
| 16384 | crc32 | 1.183 | 1.30 | 1.84 |
Tested in userland using the test-suite in the zstd repo under
`contrib/linux-kernel/test/XXHashUserlandTest.cpp` [2] by mocking the
kernel functions. A line in each branch of every function in `xxhash.c`
was commented out to ensure that the test-suite fails. Additionally
tested while testing zstd and with SMHasher [3].
[1] https://phabricator.intern.facebook.com/P57526246
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/XXHashUserlandTest.cpp
[3] https://github.com/aappleby/smhasher
zstd source repository: https://github.com/facebook/zstd
XXHash source repository: https://github.com/cyan4973/xxhash
Signed-off-by: Nick Terrell <terrelln@fb.com>
---
include/linux/xxhash.h | 236 +++++++++++++++++++++++
lib/Kconfig | 3 +
lib/Makefile | 1 +
lib/xxhash.c | 500 +++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 740 insertions(+)
create mode 100644 include/linux/xxhash.h
create mode 100644 lib/xxhash.c
diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h
new file mode 100644
index 0000000..9e1f42c
@@ -255,10 +338,10 @@ index 0c8b78a..b6009d7 100644
bool
depends on AUDIT && !AUDIT_ARCH
diff --git a/lib/Makefile b/lib/Makefile
index 320ac46..e16f94a 100644
index 0166fbc..1338226 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o
@@ -102,6 +102,7 @@ obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o
obj-$(CONFIG_CRC7) += crc7.o
obj-$(CONFIG_LIBCRC32C) += libcrc32c.o
obj-$(CONFIG_CRC8) += crc8.o
@@ -772,3 +855,6 @@ index 0000000..dc94904
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("xxHash");
--
2.9.3
contrib/linux-kernel/zstd.diff → contrib/linux-kernel/0002-lib-Add-zstd-modules.patch
+149 -5
View File
@@ -1,3 +1,145 @@
From b52ae824ae6c0f7c7786380b34da9daaa54bfc26 Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Wed, 21 Jun 2017 17:31:24 -0700
Subject: [PATCH 2/4] lib: Add zstd modules
Add zstd compression and decompression kernel modules.
zstd offers a wide varity of compression speed and quality trade-offs.
It can compress at speeds approaching lz4, and quality approaching lzma.
zstd decompressions at speeds more than twice as fast as zlib, and
decompression speed remains roughly the same across all compression levels.
The code was ported from the upstream zstd source repository. The
`linux/zstd.h` header was modified to match linux kernel style.
The cross-platform and allocation code was stripped out. Instead zstd
requires the caller to pass a preallocated workspace. The source files
were clang-formatted [1] to match the Linux Kernel style as much as
possible. Otherwise, the code was unmodified. We would like to avoid
as much further manual modification to the source code as possible, so it
will be easier to keep the kernel zstd up to date.
I benchmarked zstd compression as a special character device. I ran zstd
and zlib compression at several levels, as well as performing no
compression, which measure the time spent copying the data to kernel space.
Data is passed to the compresser 4096 B at a time. The benchmark file is
located in the upstream zstd source repository under
`contrib/linux-kernel/zstd_compress_test.c` [2].
I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD. I benchmarked using `silesia.tar` [3], which is
211,988,480 B large. Run the following commands for the benchmark:
sudo modprobe zstd_compress_test
sudo mknod zstd_compress_test c 245 0
sudo cp silesia.tar zstd_compress_test
The time is reported by the time of the userland `cp`.
The MB/s is computed with
1,536,217,008 B / time(buffer size, hash)
which includes the time to copy from userland.
The Adjusted MB/s is computed with
1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)).
The memory reported is the amount of memory the compressor requests.
| Method | Size (B) | Time (s) | Ratio | MB/s | Adj MB/s | Mem (MB) |
|----------|----------|----------|-------|---------|----------|----------|
| none | 11988480 | 0.100 | 1 | 2119.88 | - | - |
| zstd -1 | 73645762 | 1.044 | 2.878 | 203.05 | 224.56 | 1.23 |
| zstd -3 | 66988878 | 1.761 | 3.165 | 120.38 | 127.63 | 2.47 |
| zstd -5 | 65001259 | 2.563 | 3.261 | 82.71 | 86.07 | 2.86 |
| zstd -10 | 60165346 | 13.242 | 3.523 | 16.01 | 16.13 | 13.22 |
| zstd -15 | 58009756 | 47.601 | 3.654 | 4.45 | 4.46 | 21.61 |
| zstd -19 | 54014593 | 102.835 | 3.925 | 2.06 | 2.06 | 60.15 |
| zlib -1 | 77260026 | 2.895 | 2.744 | 73.23 | 75.85 | 0.27 |
| zlib -3 | 72972206 | 4.116 | 2.905 | 51.50 | 52.79 | 0.27 |
| zlib -6 | 68190360 | 9.633 | 3.109 | 22.01 | 22.24 | 0.27 |
| zlib -9 | 67613382 | 22.554 | 3.135 | 9.40 | 9.44 | 0.27 |
I benchmarked zstd decompression using the same method on the same machine.
The benchmark file is located in the upstream zstd repo under
`contrib/linux-kernel/zstd_decompress_test.c` [4]. The memory reported is
the amount of memory required to decompress data compressed with the given
compression level. If you know the maximum size of your input, you can
reduce the memory usage of decompression irrespective of the compression
level.
| Method | Time (s) | MB/s | Adjusted MB/s | Memory (MB) |
|----------|----------|---------|---------------|-------------|
| none | 0.025 | 8479.54 | - | - |
| zstd -1 | 0.358 | 592.15 | 636.60 | 0.84 |
| zstd -3 | 0.396 | 535.32 | 571.40 | 1.46 |
| zstd -5 | 0.396 | 535.32 | 571.40 | 1.46 |
| zstd -10 | 0.374 | 566.81 | 607.42 | 2.51 |
| zstd -15 | 0.379 | 559.34 | 598.84 | 4.61 |
| zstd -19 | 0.412 | 514.54 | 547.77 | 8.80 |
| zlib -1 | 0.940 | 225.52 | 231.68 | 0.04 |
| zlib -3 | 0.883 | 240.08 | 247.07 | 0.04 |
| zlib -6 | 0.844 | 251.17 | 258.84 | 0.04 |
| zlib -9 | 0.837 | 253.27 | 287.64 | 0.04 |
Tested in userland using the test-suite in the zstd repo under
`contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel
functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under
`contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8]
with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the
BtrFS and SquashFS patches coming next.
[1] https://clang.llvm.org/docs/ClangFormat.html
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_compress_test.c
[3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
[4] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_decompress_test.c
[5] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/UserlandTest.cpp
[6] http://llvm.org/docs/LibFuzzer.html
[7] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/RoundTripCrash.c
[8] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/DecompressCrash.c
zstd source repository: https://github.com/facebook/zstd
Signed-off-by: Nick Terrell <terrelln@fb.com>
---
include/linux/zstd.h | 1157 +++++++++++++++
lib/Kconfig | 8 +
lib/Makefile | 2 +
lib/zstd/Makefile | 18 +
lib/zstd/bitstream.h | 374 +++++
lib/zstd/compress.c | 3468 +++++++++++++++++++++++++++++++++++++++++++++
lib/zstd/decompress.c | 2514 ++++++++++++++++++++++++++++++++
lib/zstd/entropy_common.c | 244 ++++
lib/zstd/error_private.h | 53 +
lib/zstd/fse.h | 584 ++++++++
lib/zstd/fse_compress.c | 857 +++++++++++
lib/zstd/fse_decompress.c | 313 ++++
lib/zstd/huf.h | 203 +++
lib/zstd/huf_compress.c | 731 ++++++++++
lib/zstd/huf_decompress.c | 920 ++++++++++++
lib/zstd/mem.h | 151 ++
lib/zstd/zstd_common.c | 75 +
lib/zstd/zstd_internal.h | 269 ++++
lib/zstd/zstd_opt.h | 1014 +++++++++++++
19 files changed, 12955 insertions(+)
create mode 100644 include/linux/zstd.h
create mode 100644 lib/zstd/Makefile
create mode 100644 lib/zstd/bitstream.h
create mode 100644 lib/zstd/compress.c
create mode 100644 lib/zstd/decompress.c
create mode 100644 lib/zstd/entropy_common.c
create mode 100644 lib/zstd/error_private.h
create mode 100644 lib/zstd/fse.h
create mode 100644 lib/zstd/fse_compress.c
create mode 100644 lib/zstd/fse_decompress.c
create mode 100644 lib/zstd/huf.h
create mode 100644 lib/zstd/huf_compress.c
create mode 100644 lib/zstd/huf_decompress.c
create mode 100644 lib/zstd/mem.h
create mode 100644 lib/zstd/zstd_common.c
create mode 100644 lib/zstd/zstd_internal.h
create mode 100644 lib/zstd/zstd_opt.h
diff --git a/include/linux/zstd.h b/include/linux/zstd.h
new file mode 100644
index 0000000..249575e
@@ -1168,7 +1310,7 @@ index b6009d7..f00ddab 100644
@@ -241,6 +241,14 @@ config LZ4HC_COMPRESS
config LZ4_DECOMPRESS
tristate
+config ZSTD_COMPRESS
+ select XXHASH
+ tristate
@@ -1178,13 +1320,13 @@ index b6009d7..f00ddab 100644
+ tristate
+
source "lib/xz/Kconfig"
#
diff --git a/lib/Makefile b/lib/Makefile
index e16f94a..0cfd529 100644
index 1338226..4fcef16 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -115,6 +115,8 @@ obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
@@ -116,6 +116,8 @@ obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
obj-$(CONFIG_LZ4_COMPRESS) += lz4/
obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
@@ -1192,7 +1334,7 @@ index e16f94a..0cfd529 100644
+obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
obj-$(CONFIG_XZ_DEC) += xz/
obj-$(CONFIG_RAID6_PQ) += raid6/
diff --git a/lib/zstd/Makefile b/lib/zstd/Makefile
new file mode 100644
index 0000000..dd0a359
@@ -13077,3 +13219,5 @@ index 0000000..55e1b4c
+}
+
+#endif /* ZSTD_OPT_H_91842398743 */
--
2.9.3
contrib/linux-kernel/btrfs.diff → contrib/linux-kernel/0003-btrfs-Add-zstd-support.patch
+106 -24
View File
@@ -1,3 +1,83 @@
From 599f8f2aaace3df939cb145368574a52268d82d0 Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Wed, 21 Jun 2017 17:31:39 -0700
Subject: [PATCH 3/4] btrfs: Add zstd support
Add zstd compression and decompression support to BtrFS. zstd at its
fastest level compresses almost as well as zlib, while offering much
faster compression and decompression, approaching lzo speeds.
I benchmarked btrfs with zstd compression against no compression, lzo
compression, and zlib compression. I benchmarked two scenarios. Copying
a set of files to btrfs, and then reading the files. Copying a tarball
to btrfs, extracting it to btrfs, and then reading the extracted files.
After every operation, I call `sync` and include the sync time.
Between every pair of operations I unmount and remount the filesystem
to avoid caching. The benchmark files can be found in the upstream
zstd source repository under
`contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}`
[1] [2].
I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD.
The first compression benchmark is copying 10 copies of the unzipped
Silesia corpus [3] into a BtrFS filesystem mounted with
`-o compress-force=Method`. The decompression benchmark times how long
it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is
measured by comparing the output of `df` and `du`. See the benchmark file
[1] for details. I benchmarked multiple zstd compression levels, although
the patch uses zstd level 1.
| Method | Ratio | Compression MB/s | Decompression speed |
|---------|-------|------------------|---------------------|
| None | 0.99 | 504 | 686 |
| lzo | 1.66 | 398 | 442 |
| zlib | 2.58 | 65 | 241 |
| zstd 1 | 2.57 | 260 | 383 |
| zstd 3 | 2.71 | 174 | 408 |
| zstd 6 | 2.87 | 70 | 398 |
| zstd 9 | 2.92 | 43 | 406 |
| zstd 12 | 2.93 | 21 | 408 |
| zstd 15 | 3.01 | 11 | 354 |
The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it
measures the compression ratio, extracts the tar, and deletes the tar.
Then it measures the compression ratio again, and `tar`s the extracted
files into `/dev/null`. See the benchmark file [2] for details.
| Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) |
|--------|-----------|---------------|----------|------------|----------|
| None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 |
| lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 |
| zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 |
| zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 |
[1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh
[3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
[4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz
zstd source repository: https://github.com/facebook/zstd
Signed-off-by: Nick Terrell <terrelln@fb.com>
---
fs/btrfs/Kconfig | 2 +
fs/btrfs/Makefile | 2 +-
fs/btrfs/compression.c | 1 +
fs/btrfs/compression.h | 6 +-
fs/btrfs/ctree.h | 1 +
fs/btrfs/disk-io.c | 2 +
fs/btrfs/ioctl.c | 6 +-
fs/btrfs/props.c | 6 +
fs/btrfs/super.c | 12 +-
fs/btrfs/sysfs.c | 2 +
fs/btrfs/zstd.c | 433 +++++++++++++++++++++++++++++++++++++++++++++
include/uapi/linux/btrfs.h | 8 +-
12 files changed, 469 insertions(+), 12 deletions(-)
create mode 100644 fs/btrfs/zstd.c
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 80e9c18..a26c63b 100644
--- a/fs/btrfs/Kconfig
@@ -25,7 +105,7 @@ index 128ce17..962a95a 100644
reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
uuid-tree.o props.o hash.o free-space-tree.o
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c7721a6..66d4ced 100644
index 10e6b28..3beb0d0 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -761,6 +761,7 @@ static struct {
@@ -34,7 +114,7 @@ index c7721a6..66d4ced 100644
&btrfs_lzo_compress,
+ &btrfs_zstd_compress,
};
void __init btrfs_init_compress(void)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 39ec43a..d99fc21 100644
@@ -50,20 +130,20 @@ index 39ec43a..d99fc21 100644
+ BTRFS_COMPRESS_TYPES = 3,
+ BTRFS_COMPRESS_LAST = 4,
};
struct btrfs_compress_op {
@@ -92,5 +93,6 @@ struct btrfs_compress_op {
extern const struct btrfs_compress_op btrfs_zlib_compress;
extern const struct btrfs_compress_op btrfs_lzo_compress;
+extern const struct btrfs_compress_op btrfs_zstd_compress;
#endif
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 29b7fc2..878b23b9 100644
index 4f8f75d..61dd3dd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -270,6 +270,7 @@ struct btrfs_super_block {
@@ -271,6 +271,7 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \
BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
@@ -72,24 +152,24 @@ index 29b7fc2..878b23b9 100644
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08b74da..0c43e4e 100644
index 5f678dc..49c0e91 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2853,6 +2853,8 @@ int open_ctree(struct super_block *sb,
@@ -2831,6 +2831,8 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+ else if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
+ else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
+ features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
btrfs_info(fs_info, "has skinny extents");
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dabfc7a..d8ea727 100644
index e176375..f732cfd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -327,8 +327,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
comp = "lzo";
- else
@@ -101,13 +181,13 @@ index dabfc7a..d8ea727 100644
comp, strlen(comp), 0);
if (ret)
@@ -1463,6 +1465,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (range->compress_type == BTRFS_COMPRESS_LZO) {
btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (range->compress_type == BTRFS_COMPRESS_ZSTD) {
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
}
ret = defrag_count;
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index d6cb155..162105f 100644
@@ -119,7 +199,7 @@ index d6cb155..162105f 100644
return 0;
+ else if (!strncmp("zstd", value, len))
+ return 0;
return -EINVAL;
}
@@ -405,6 +407,8 @@ static int prop_compression_apply(struct inode *inode,
@@ -130,7 +210,7 @@ index d6cb155..162105f 100644
+ type = BTRFS_COMPRESS_ZSTD;
else
return -EINVAL;
@@ -422,6 +426,8 @@ static const char *prop_compression_extract(struct inode *inode)
return "zlib";
case BTRFS_COMPRESS_LZO:
@@ -138,10 +218,10 @@ index d6cb155..162105f 100644
+ case BTRFS_COMPRESS_ZSTD:
+ return "zstd";
}
return NULL;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index da687dc..b064456 100644
index 4f1cdd5..4f792d5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -513,6 +513,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
@@ -159,7 +239,7 @@ index da687dc..b064456 100644
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
@@ -1230,8 +1238,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
@@ -1240,8 +1248,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
if (btrfs_test_opt(info, COMPRESS)) {
if (info->compress_type == BTRFS_COMPRESS_ZLIB)
compress_type = "zlib";
@@ -193,7 +273,7 @@ index 1f157fb..b0dec90 100644
BTRFS_FEAT_ATTR_PTR(raid56),
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
new file mode 100644
index 0000000..45ea326
index 0000000..838741b
--- /dev/null
+++ b/fs/btrfs/zstd.c
@@ -0,0 +1,433 @@
@@ -231,7 +311,7 @@ index 0000000..45ea326
+
+static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
+{
+ ZSTD_parameters params = ZSTD_getParams(3, src_len, 0);
+ ZSTD_parameters params = ZSTD_getParams(1, src_len, 0);
+
+ if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
+ params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
@@ -631,7 +711,7 @@ index 0000000..45ea326
+ .decompress = zstd_decompress,
+};
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index db4c253..f26c34f 100644
index a456e53..992c150 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -255,13 +255,7 @@ struct btrfs_ioctl_fs_info_args {
@@ -646,6 +726,8 @@ index db4c253..f26c34f 100644
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD (1ULL << 4)
/*
* older kernels tried to do bigger metadata blocks, but the
--
2.9.3
contrib/linux-kernel/squashfs.diff → contrib/linux-kernel/0004-squashfs-Add-zstd-support.patch
+64 -6
View File
@@ -1,11 +1,67 @@
From 5ff6a64abaea7b7f11d37cb0fdf08642316a3a90 Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Mon, 12 Jun 2017 12:18:23 -0700
Subject: [PATCH 4/4] squashfs: Add zstd support
Add zstd compression and decompression support to SquashFS. zstd is a
great fit for SquashFS because it can compress at ratios approaching xz,
while decompressing twice as fast as zlib. For SquashFS in particular,
it can decompress as fast as lzo and lz4. It also has the flexibility
to turn down the compression ratio for faster compression times.
The compression benchmark is run on the file tree from the SquashFS archive
found in ubuntu-16.10-desktop-amd64.iso [1]. It uses `mksquashfs` with the
default block size (128 KB) and and various compression algorithms/levels.
xz and zstd are also benchmarked with 256 KB blocks. The decompression
benchmark times how long it takes to `tar` the file tree into `/dev/null`.
See the benchmark file in the upstream zstd source repository located under
`contrib/linux-kernel/squashfs-benchmark.sh` [2] for details.
I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of RAM, and a SSD.
| Method | Ratio | Compression MB/s | Decompression MB/s |
|----------------|-------|------------------|--------------------|
| gzip | 2.92 | 15 | 128 |
| lzo | 2.64 | 9.5 | 217 |
| lz4 | 2.12 | 94 | 218 |
| xz | 3.43 | 5.5 | 35 |
| xz 256 KB | 3.53 | 5.4 | 40 |
| zstd 1 | 2.71 | 96 | 210 |
| zstd 5 | 2.93 | 69 | 198 |
| zstd 10 | 3.01 | 41 | 225 |
| zstd 15 | 3.13 | 11.4 | 224 |
| zstd 16 256 KB | 3.24 | 8.1 | 210 |
This patch was written by Sean Purcell <me@seanp.xyz>, but I will be
taking over the submission process.
[1] http://releases.ubuntu.com/16.10/
[2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/squashfs-benchmark.sh
zstd source repository: https://github.com/facebook/zstd
Cc: Sean Purcell <me@seanp.xyz>
Signed-off-by: Nick Terrell <terrelln@fb.com>
---
fs/squashfs/Kconfig | 14 +++++
fs/squashfs/Makefile | 1 +
fs/squashfs/decompressor.c | 7 +++
fs/squashfs/decompressor.h | 4 ++
fs/squashfs/squashfs_fs.h | 1 +
fs/squashfs/zstd_wrapper.c | 150 +++++++++++++++++++++++++++++++++++++++++++++
6 files changed, 177 insertions(+)
create mode 100644 fs/squashfs/zstd_wrapper.c
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index ffb093e..1adb334 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -165,6 +165,20 @@ config SQUASHFS_XZ
If unsure, say N.
+config SQUASHFS_ZSTD
+ bool "Include support for ZSTD compressed file systems"
+ depends on SQUASHFS
@@ -39,7 +95,7 @@ index d2bc136..8366398 100644
@@ -65,6 +65,12 @@ static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
};
#endif
+#ifndef CONFIG_SQUASHFS_ZSTD
+static const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+ NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0
@@ -56,7 +112,7 @@ index d2bc136..8366398 100644
+ &squashfs_zstd_comp_ops,
&squashfs_unknown_comp_ops
};
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index a25713c..0f5a8e4 100644
--- a/fs/squashfs/decompressor.h
@@ -64,7 +120,7 @@ index a25713c..0f5a8e4 100644
@@ -58,4 +58,8 @@ extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
extern const struct squashfs_decompressor squashfs_zlib_comp_ops;
#endif
+#ifdef CONFIG_SQUASHFS_ZSTD
+extern const struct squashfs_decompressor squashfs_zstd_comp_ops;
+#endif
@@ -79,7 +135,7 @@ index 506f4ba..24d12fd 100644
#define XZ_COMPRESSION 4
#define LZ4_COMPRESSION 5
+#define ZSTD_COMPRESSION 6
struct squashfs_super_block {
__le32 s_magic;
diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
@@ -238,3 +294,5 @@ index 0000000..8cb7c76
+ .name = "zstd",
+ .supported = 1
+};
--
2.9.3
contrib/linux-kernel/btrfs-extract-benchmark.sh
Executable
+99
View File
@@ -0,0 +1,99 @@
# !/bin/sh
set -e
# Benchmarks run on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
# The VM is running on a Macbook Pro with a 3.1 GHz Intel Core i7 processor and
# 16 GB of RAM and an SSD.
# silesia is a directory that can be downloaded from
# http://mattmahoney.net/dc/silesia.html
# ls -l silesia/
# total 203M
# -rwxr-xr-x 1 terrelln 9.8M Apr 12 2002 dickens
# -rwxr-xr-x 1 terrelln 49M May 31 2002 mozilla
# -rwxr-xr-x 1 terrelln 9.6M Mar 20 2003 mr
# -rwxr-xr-x 1 terrelln 32M Apr 2 2002 nci
# -rwxr-xr-x 1 terrelln 5.9M Jul 4 2002 ooffice
# -rwxr-xr-x 1 terrelln 9.7M Apr 11 2002 osdb
# -rwxr-xr-x 1 terrelln 6.4M Apr 2 2002 reymont
# -rwxr-xr-x 1 terrelln 21M Mar 25 2002 samba
# -rwxr-xr-x 1 terrelln 7.0M Mar 24 2002 sao
# -rwxr-xr-x 1 terrelln 40M Mar 25 2002 webster
# -rwxr-xr-x 1 terrelln 8.1M Apr 4 2002 x-ray
# -rwxr-xr-x 1 terrelln 5.1M Nov 30 2000 xml
# $HOME is on a ext4 filesystem
BENCHMARK_FILE="linux-4.11.6.tar"
BENCHMARK_DIR="$HOME/$BENCHMARK_FILE"
# Normalize the environment
sudo umount /mnt/btrfs 2> /dev/null > /dev/null || true
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
sudo rm -rf /mnt/btrfs/*
sync
sudo umount /mnt/btrfs
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
# Run the benchmark
echo "Copy"
time sh -c "sudo cp -r $BENCHMARK_DIR /mnt/btrfs/$BENCHMARK_FILE && sync"
echo "Approximate tarred compression ratio"
printf "%d / %d\n" \
$(df /mnt/btrfs --output=used -B 1 | tail -n 1) \
$(sudo du /mnt/btrfs -b -d 0 | tr '\t' '\n' | head -n 1);
# Unmount and remount to avoid any caching
sudo umount /mnt/btrfs
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
echo "Extract"
time sh -c "sudo tar -C /mnt/btrfs -xf /mnt/btrfs/$BENCHMARK_FILE && sync"
# Remove the tarball, leaving only the extracted data
sudo rm /mnt/btrfs/$BENCHMARK_FILE
# Unmount and remount to avoid any caching
sudo umount /mnt/btrfs
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
echo "Approximate extracted compression ratio"
printf "%d / %d\n" \
$(df /mnt/btrfs --output=used -B 1 | tail -n 1) \
$(sudo du /mnt/btrfs -b -d 0 | tr '\t' '\n' | head -n 1);
echo "Read"
time sudo tar -c /mnt/btrfs 2> /dev/null | wc -c > /dev/null
sudo rm -rf /mnt/btrfs/*
sudo umount /mnt/btrfs
# Run for each of -o compress-force={none, lzo, zlib, zstd} 5 times and take the
# min time and ratio.
# none
# copy: 0.981 s
# extract: 5.501 s
# read: 8.807 s
# tarball ratio: 0.97
# extracted ratio: 0.78
# lzo
# copy: 1.631 s
# extract: 8.458 s
# read: 8.585 s
# tarball ratio: 2.06
# extracted ratio: 1.38
# zlib
# copy: 7.750 s
# extract: 21.544 s
# read: 11.744 s
# tarball ratio : 3.40
# extracted ratio: 1.86
# zstd 1
# copy: 2.579 s
# extract: 11.479 s
# read: 9.389 s
# tarball ratio : 3.57
# extracted ratio: 1.85
contrib/linux-kernel/fs/btrfs/zstd.c
+1 -1
View File
@@ -32,7 +32,7 @@
static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
{
ZSTD_parameters params = ZSTD_getParams(3, src_len, 0);
ZSTD_parameters params = ZSTD_getParams(1, src_len, 0);
if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
contrib/pzstd/Pzstd.cpp
+4 -1
View File
@@ -585,7 +585,10 @@ std::uint64_t writeFile(
std::uint64_t bytesWritten = 0;
std::shared_ptr<BufferWorkQueue> out;
// Grab the output queue for each decompression job (in order).
while (outs.pop(out) && !errorHolder.hasError()) {
while (outs.pop(out)) {
if (errorHolder.hasError()) {
continue;
}
if (!decompress) {
// If we are compressing and want to write skippable frames we can't
// start writing before compression is done because we need to know the
doc/zstd_manual.html
+336 -70
View File
@@ -13,7 +13,7 @@
<li><a href="#Chapter3">Simple API</a></li>
<li><a href="#Chapter4">Explicit memory management</a></li>
<li><a href="#Chapter5">Simple dictionary API</a></li>
<li><a href="#Chapter6">Fast dictionary API</a></li>
<li><a href="#Chapter6">Bulk processing dictionary API</a></li>
<li><a href="#Chapter7">Streaming</a></li>
<li><a href="#Chapter8">Streaming compression - HowTo</a></li>
<li><a href="#Chapter9">Streaming decompression - HowTo</a></li>
@@ -31,26 +31,27 @@
</ol>
<hr>
<a name="Chapter1"></a><h2>Introduction</h2><pre>
zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios
at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and
decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22.
zstd, short for Zstandard, is a fast lossless compression algorithm,
targeting real-time compression scenarios at zlib-level and better compression ratios.
The zstd compression library provides in-memory compression and decompression functions.
The library supports compression levels from 1 up to ZSTD_maxCLevel() which is currently 22.
Levels >= 20, labeled `--ultra`, should be used with caution, as they require more memory.
Compression can be done in:
- a single step (described as Simple API)
- a single step, reusing a context (described as Explicit memory management)
- unbounded multiple steps (described as Streaming compression)
The compression ratio achievable on small data can be highly improved using compression with a dictionary in:
The compression ratio achievable on small data can be highly improved using a dictionary in:
- a single step (described as Simple dictionary API)
- a single step, reusing a dictionary (described as Fast dictionary API)
Advanced experimental functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h.
These APIs shall never be used with a dynamic library.
Advanced experimental APIs shall never be used with a dynamic library.
They are not "stable", their definition may change in the future. Only static linking is allowed.
<BR></pre>
<a name="Chapter2"></a><h2>Version</h2><pre></pre>
<pre><b>unsigned ZSTD_versionNumber(void); </b>/**< library version number; to be used when checking dll version */<b>
<pre><b>unsigned ZSTD_versionNumber(void); </b>/**< useful to check dll version */<b>
</b></pre><BR>
<a name="Chapter3"></a><h2>Simple API</h2><pre></pre>
@@ -66,28 +67,24 @@
<pre><b>size_t ZSTD_decompress( void* dst, size_t dstCapacity,
const void* src, size_t compressedSize);
</b><p> `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
`dstCapacity` is an upper bound of originalSize.
`dstCapacity` is an upper bound of originalSize to regenerate.
If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
@return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
or an errorCode if it fails (which can be tested using ZSTD_isError()).
</p></pre><BR>
<pre><b>unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
</b><p> NOTE: This function is planned to be obsolete, in favour of ZSTD_getFrameContentSize.
ZSTD_getFrameContentSize functions the same way, returning the decompressed size of a single
frame, but distinguishes empty frames from frames with an unknown size, or errors.
Additionally, ZSTD_findDecompressedSize can be used instead. It can handle multiple
concatenated frames in one buffer, and so is more general.
As a result however, it requires more computation and entire frames to be passed to it,
as opposed to ZSTD_getFrameContentSize which requires only a single frame's header.
</b><p> NOTE: This function is planned to be obsolete, in favor of ZSTD_getFrameContentSize().
ZSTD_getFrameContentSize() works the same way,
returning the decompressed size of a single frame,
but distinguishes empty frames from frames with an unknown size, or errors.
'src' is the start of a zstd compressed frame.
@return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise.
note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
note 1 : decompressed size is an optional field, it may not be present, typically in streaming mode.
When `return==0`, data to decompress could be any size.
In which case, it's necessary to use streaming mode to decompress data.
Optionally, application can still use ZSTD_decompress() while relying on implied limits.
Optionally, application can use ZSTD_decompress() while relying on implied limits.
(For example, data may be necessarily cut into blocks <= 16 KB).
note 2 : decompressed size is always present when compression is done with ZSTD_compress()
note 3 : decompressed size can be very large (64-bits value),
@@ -96,7 +93,7 @@
note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
Always ensure result fits within application's authorized limits.
Each application can set its own limits.
note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameParams() to know more.
note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameHeader() to know more.
</p></pre><BR>
<h3>Helper functions</h3><pre></pre><b><pre>int ZSTD_maxCLevel(void); </b>/*!< maximum compression level available */<b>
@@ -114,20 +111,26 @@ const char* ZSTD_getErrorName(size_t code); </b>/*!< provides readable strin
ZSTD_CCtx* ZSTD_createCCtx(void);
size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx);
</pre></b><BR>
<pre><b>size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
<pre><b>size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel);
</b><p> Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()).
</p></pre><BR>
<h3>Decompression context</h3><pre> When decompressing many times,
it is recommended to allocate a context just once, and re-use it for each successive compression operation.
it is recommended to allocate a context only once,
and re-use it for each successive compression operation.
This will make workload friendlier for system's memory.
Use one context per thread for parallel execution in multi-threaded environments.
Use one context per thread for parallel execution.
</pre><b><pre>typedef struct ZSTD_DCtx_s ZSTD_DCtx;
ZSTD_DCtx* ZSTD_createDCtx(void);
size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
</pre></b><BR>
<pre><b>size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
</b><p> Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()).
<pre><b>size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize);
</b><p> Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx())
</p></pre><BR>
<a name="Chapter5"></a><h2>Simple dictionary API</h2><pre></pre>
@@ -137,32 +140,33 @@ size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
const void* src, size_t srcSize,
const void* dict,size_t dictSize,
int compressionLevel);
</b><p> Compression using a predefined Dictionary (see dictBuilder/zdict.h).
Note : This function loads the dictionary, resulting in significant startup delay.
Note : When `dict == NULL || dictSize < 8` no dictionary is used.
</b><p> Compression using a predefined Dictionary (see dictBuilder/zdict.h).
Note : This function loads the dictionary, resulting in significant startup delay.
Note : When `dict == NULL || dictSize < 8` no dictionary is used.
</p></pre><BR>
<pre><b>size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const void* dict,size_t dictSize);
</b><p> Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
Dictionary must be identical to the one used during compression.
Note : This function loads the dictionary, resulting in significant startup delay.
Note : When `dict == NULL || dictSize < 8` no dictionary is used.
</b><p> Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
Dictionary must be identical to the one used during compression.
Note : This function loads the dictionary, resulting in significant startup delay.
Note : When `dict == NULL || dictSize < 8` no dictionary is used.
</p></pre><BR>
<a name="Chapter6"></a><h2>Fast dictionary API</h2><pre></pre>
<a name="Chapter6"></a><h2>Bulk processing dictionary API</h2><pre></pre>
<pre><b>ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, int compressionLevel);
</b><p> When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
ZSTD_CDict can be created once and used by multiple threads concurrently, as its usage is read-only.
`dictBuffer` can be released after ZSTD_CDict creation, as its content is copied within CDict
<pre><b>ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
int compressionLevel);
</b><p> When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
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, since its content is copied within CDict
</p></pre><BR>
<pre><b>size_t ZSTD_freeCDict(ZSTD_CDict* CDict);
</b><p> Function frees memory allocated by ZSTD_createCDict().
</b><p> Function frees memory allocated by ZSTD_createCDict().
</p></pre><BR>
<pre><b>size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
@@ -176,20 +180,20 @@ size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
</p></pre><BR>
<pre><b>ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
</b><p> Create a digested dictionary, ready to start decompression operation without startup delay.
dictBuffer can be released after DDict creation, as its content is copied inside DDict
</b><p> Create a digested dictionary, ready to start decompression operation without startup delay.
dictBuffer can be released after DDict creation, as its content is copied inside DDict
</p></pre><BR>
<pre><b>size_t ZSTD_freeDDict(ZSTD_DDict* ddict);
</b><p> Function frees memory allocated with ZSTD_createDDict()
</b><p> Function frees memory allocated with ZSTD_createDDict()
</p></pre><BR>
<pre><b>size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_DDict* ddict);
</b><p> Decompression using a digested Dictionary.
Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times.
</b><p> Decompression using a digested Dictionary.
Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times.
</p></pre><BR>
<a name="Chapter7"></a><h2>Streaming</h2><pre></pre>
@@ -236,15 +240,17 @@ size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
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.
Similar to ZSTD_flushStream(), it may not be able to flush the full content if `output->size` is too small.
ZSTD_endStream() may not be able to flush full data if `output->size` is too small.
In which case, call again ZSTD_endStream() to complete the flush.
@return : nb of bytes still present within internal buffer (0 if it's empty, hence compression completed)
@return : 0 if frame fully completed and fully flushed,
or >0 if some data is still present within internal buffer
(value is minimum size estimation for remaining data to flush, but it could be more)
or an error code, which can be tested using ZSTD_isError().
<BR></pre>
<pre><b>typedef ZSTD_CCtx ZSTD_CStream; </b>/**< CCtx and CStream are effectively same object */<b>
<pre><b>typedef ZSTD_CCtx ZSTD_CStream; </b>/**< CCtx and CStream are now effectively same object (>= v1.3.0) */<b>
</b></pre><BR>
<h3>ZSTD_CStream management functions</h3><pre></pre><b><pre>ZSTD_CStream* ZSTD_createCStream(void);
size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
@@ -279,6 +285,8 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
<BR></pre>
<pre><b>typedef ZSTD_DCtx ZSTD_DStream; </b>/**< DCtx and DStream are now effectively same object (>= v1.3.0) */<b>
</b></pre><BR>
<h3>ZSTD_DStream management functions</h3><pre></pre><b><pre>ZSTD_DStream* ZSTD_createDStream(void);
size_t ZSTD_freeDStream(ZSTD_DStream* zds);
</pre></b><BR>
@@ -298,7 +306,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
<a name="Chapter11"></a><h2>Advanced types</h2><pre></pre>
<pre><b>typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; </b>/* from faster to stronger */<b>
<pre><b>typedef enum { ZSTD_fast=1, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2,
ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; </b>/* from faster to stronger */<b>
</b></pre><BR>
<pre><b>typedef struct {
unsigned windowLog; </b>/**< largest match distance : larger == more compression, more memory needed during decompression */<b>
@@ -331,6 +340,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
<h3>Custom memory allocation functions</h3><pre></pre><b><pre>typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
typedef void (*ZSTD_freeFunction) (void* opaque, void* address);
typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
</b>/* use this constant to defer to stdlib's functions */<b>
static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
</pre></b><BR>
<a name="Chapter12"></a><h2>Frame size functions</h2><pre></pre>
@@ -395,19 +406,20 @@ size_t ZSTD_estimateDCtxSize(void);
</b><p> These functions make it possible to estimate memory usage
of a future target object, before its allocation,
given a set of parameters, which vary depending on target object.
The objective is to guide decision before allocation.
The objective is to guide decision before allocation.
Note : CCtx estimation is only correct for single-threaded compression
</p></pre><BR>
<pre><b>size_t ZSTD_estimateCStreamSize(ZSTD_compressionParameters cParams);
size_t ZSTD_estimateDStreamSize(ZSTD_frameHeader fHeader);
</b><p> Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
an internal ?Dict will be created, which size is not estimated.
In this case, get additional size by using ZSTD_estimate?DictSize
an internal ?Dict will be created, which size is not estimated here.
In this case, get total size by adding ZSTD_estimate?DictSize
</p></pre><BR>
<pre><b>size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize);
size_t ZSTD_estimateDDictSize(size_t dictSize);
</b><p> Note : if dictionary is created "byReference", reduce estimation by dictSize
<pre><b>size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize, unsigned byReference);
size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference);
</b><p> Note : dictionary created "byReference" are smaller
</p></pre><BR>
<a name="Chapter14"></a><h2>Advanced compression functions</h2><pre></pre>
@@ -416,6 +428,23 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
</b><p> Create a ZSTD compression context using external alloc and free functions
</p></pre><BR>
<pre><b>ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize);
</b><p> workspace: The memory area to emplace the context into.
Provided pointer must 8-bytes aligned.
It must outlive context usage.
workspaceSize: Use ZSTD_estimateCCtxSize() or ZSTD_estimateCStreamSize()
to determine how large workspace must be to support scenario.
@return : pointer to ZSTD_CCtx*, or NULL if error (size too small)
Note : zstd will never resize nor malloc() when using a static cctx.
If it needs more memory than available, it will simply error out.
Note 2 : there is no corresponding "free" function.
Since workspace was allocated externally, it must be freed externally too.
Limitation 1 : currently not compatible with internal CDict creation, such as
ZSTD_CCtx_loadDictionary() or ZSTD_initCStream_usingDict().
Limitation 2 : currently not compatible with multi-threading
</p></pre><BR>
<pre><b>typedef enum {
ZSTD_p_forceWindow, </b>/* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0) */<b>
ZSTD_p_forceRawDict </b>/* Force loading dictionary in "content-only" mode (no header analysis) */<b>
@@ -432,11 +461,33 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict
</p></pre><BR>
<pre><b>ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference,
<pre><b>typedef enum { ZSTD_dm_auto=0, ZSTD_dm_rawContent, ZSTD_dm_fullDict } ZSTD_dictMode_e;
</b></pre><BR>
<pre><b>ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams, ZSTD_customMem customMem);
</b><p> Create a ZSTD_CDict using external alloc and free, and customized compression parameters
</p></pre><BR>
<pre><b>ZSTD_CDict* ZSTD_initStaticCDict(
void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams);
</b><p> Generate a digested dictionary in provided memory area.
workspace: The memory area to emplace the dictionary into.
Provided pointer must 8-bytes aligned.
It must outlive dictionary usage.
workspaceSize: Use ZSTD_estimateCDictSize()
to determine how large workspace must be.
cParams : use ZSTD_getCParams() to transform a compression level
into its relevants cParams.
@return : pointer to ZSTD_CDict*, or NULL if error (size too small)
Note : there is no corresponding "free" function.
Since workspace was allocated externally, it must be freed externally.
</p></pre><BR>
<pre><b>ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
</b><p> @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
`estimatedSrcSize` value is optional, select 0 if not known
@@ -452,8 +503,8 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
</p></pre><BR>
<pre><b>ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
</b><p> optimize params for a given `srcSize` and `dictSize`.
both values are optional, select `0` if unknown.
</b><p> optimize params for a given `srcSize` and `dictSize`.
both values are optional, select `0` if unknown.
</p></pre><BR>
<pre><b>size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx,
@@ -484,10 +535,28 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
</b><p> Create a ZSTD decompression context using external alloc and free functions
</p></pre><BR>
<pre><b>ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize);
</b><p> workspace: The memory area to emplace the context into.
Provided pointer must 8-bytes aligned.
It must outlive context usage.
workspaceSize: Use ZSTD_estimateDCtxSize() or ZSTD_estimateDStreamSize()
to determine how large workspace must be to support scenario.
@return : pointer to ZSTD_DCtx*, or NULL if error (size too small)
Note : zstd will never resize nor malloc() when using a static dctx.
If it needs more memory than available, it will simply error out.
Note 2 : static dctx is incompatible with legacy support
Note 3 : there is no corresponding "free" function.
Since workspace was allocated externally, it must be freed externally.
Limitation : currently not compatible with internal DDict creation,
such as ZSTD_initDStream_usingDict().
</p></pre><BR>
<pre><b>ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
</b><p> Create a digested dictionary, ready to start decompression operation without startup delay.
Dictionary content is simply referenced, and therefore stays in dictBuffer.
It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict
Dictionary content is referenced, and therefore stays in dictBuffer.
It is important that dictBuffer outlives DDict,
it must remain read accessible throughout the lifetime of DDict
</p></pre><BR>
<pre><b>ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
@@ -495,6 +564,21 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
</b><p> Create a ZSTD_DDict using external alloc and free, optionally by reference
</p></pre><BR>
<pre><b>ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference);
</b><p> Generate a digested dictionary in provided memory area.
workspace: The memory area to emplace the dictionary into.
Provided pointer must 8-bytes aligned.
It must outlive dictionary usage.
workspaceSize: Use ZSTD_estimateDDictSize()
to determine how large workspace must be.
@return : pointer to ZSTD_DDict*, or NULL if error (size too small)
Note : there is no corresponding "free" function.
Since workspace was allocated externally, it must be freed externally.
</p></pre><BR>
<pre><b>unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
</b><p> Provides the dictID stored within dictionary.
if @return == 0, the dictionary is not conformant with Zstandard specification.
@@ -516,18 +600,18 @@ size_t ZSTD_estimateDDictSize(size_t dictSize);
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_getFrameParams(), which will provide a more precise error code.
When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code.
</p></pre><BR>
<a name="Chapter16"></a><h2>Advanced streaming functions</h2><pre></pre>
<h3>Advanced Streaming compression functions</h3><pre></pre><b><pre>ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); </b>/**< pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */<b>
size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); </b>/**< note: a dict will not be used if dict == NULL or dictSize < 8. This result in the creation of an internal CDict */<b>
size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); </b>/**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. */<b>
size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize); </b>/**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */<b>
size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); </b>/**< note : cdict will just be referenced, and must outlive compression session */<b>
size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams); </b>/**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */<b>
size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); </b>/**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */<b>
</pre></b><BR>
<pre><b>size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
</b><p> start a new compression job, using same parameters from previous job.
@@ -593,7 +677,7 @@ size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned lo
Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
A ZSTD_DCtx object can be re-used multiple times.
First typical operation is to retrieve frame parameters, using ZSTD_getFrameParams().
First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
It fills a ZSTD_frameParams structure which provide important information to correctly decode the frame,
such as the minimum rolling buffer size to allocate to decompress data (`windowSize`),
and the dictionary ID used.
@@ -607,7 +691,8 @@ size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned lo
>0 : `srcSize` is too small, please provide at least @result bytes on next attempt.
errorCode, which can be tested using ZSTD_isError().
Start decompression, with ZSTD_decompressBegin() or ZSTD_decompressBegin_usingDict().
Start decompression, with ZSTD_decompressBegin().
If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict().
Alternatively, you can copy a prepared context, using ZSTD_copyDCtx().
Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively.
@@ -639,7 +724,7 @@ size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned lo
b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
c) Frame Content - any content (User Data) of length equal to Frame Size
For skippable frames ZSTD_decompressContinue() always returns 0.
For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
For skippable frames ZSTD_getFrameHeader() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
Note : If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might actually be a Zstd encoded frame with no content.
For purposes of decompression, it is valid in both cases to skip the frame using
ZSTD_findFrameCompressedSize to find its size in bytes.
@@ -649,12 +734,193 @@ size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned lo
<h3>Buffer-less streaming decompression functions</h3><pre></pre><b><pre>size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); </b>/**< doesn't consume input, see details below */<b>
size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx);
size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx);
size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
</pre></b><BR>
<pre><b>typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
</b></pre><BR>
<h3>New advanced API (experimental, and compression only)</h3><pre></pre><b><pre></pre></b><BR>
<pre><b>typedef enum {
</b>/* compression parameters */<b>
ZSTD_p_compressionLevel=100, </b>/* Update all compression parameters according to pre-defined cLevel table<b>
* Default level is ZSTD_CLEVEL_DEFAULT==3.
* Special: value 0 means "do not change cLevel". */
ZSTD_p_windowLog, </b>/* Maximum allowed back-reference distance, expressed as power of 2.<b>
* Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX.
* Special: value 0 means "do not change windowLog". */
ZSTD_p_hashLog, </b>/* Size of the probe table, as a power of 2.<b>
* Resulting table size is (1 << (hashLog+2)).
* Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX.
* Larger tables improve compression ratio of strategies <= dFast,
* and improve speed of strategies > dFast.
* Special: value 0 means "do not change hashLog". */
ZSTD_p_chainLog, </b>/* Size of the full-search table, as a power of 2.<b>
* Resulting table size is (1 << (chainLog+2)).
* Larger tables result in better and slower compression.
* This parameter is useless when using "fast" strategy.
* Special: value 0 means "do not change chainLog". */
ZSTD_p_searchLog, </b>/* Number of search attempts, as a power of 2.<b>
* More attempts result in better and slower compression.
* This parameter is useless when using "fast" and "dFast" strategies.
* Special: value 0 means "do not change searchLog". */
ZSTD_p_minMatch, </b>/* Minimum size of searched matches (note : repCode matches can be smaller).<b>
* Larger values make faster compression and decompression, but decrease ratio.
* Must be clamped between ZSTD_SEARCHLENGTH_MIN and ZSTD_SEARCHLENGTH_MAX.
* Note that currently, for all strategies < btopt, effective minimum is 4.
* Note that currently, for all strategies > fast, effective maximum is 6.
* Special: value 0 means "do not change minMatchLength". */
ZSTD_p_targetLength, </b>/* Only useful for strategies >= btopt.<b>
* Length of Match considered "good enough" to stop search.
* Larger values make compression stronger and slower.
* Special: value 0 means "do not change targetLength". */
ZSTD_p_compressionStrategy, </b>/* See ZSTD_strategy enum definition.<b>
* Cast selected strategy as unsigned for ZSTD_CCtx_setParameter() compatibility.
* The higher the value of selected strategy, the more complex it is,
* resulting in stronger and slower compression.
* Special: value 0 means "do not change strategy". */
#if 0
ZSTD_p_windowSize, </b>/* Maximum allowed back-reference distance.<b>
* Can be set to a more precise value than windowLog.
* Will be transparently reduced to closest possible inferior value
* (see Zstandard compression format) */
</b>/* Not ready yet ! */<b>
#endif
</b>/* frame parameters */<b>
ZSTD_p_contentSizeFlag=200, </b>/* Content size is written into frame header _whenever known_ (default:1) */<b>
ZSTD_p_checksumFlag, </b>/* A 32-bits checksum of content is written at end of frame (default:0) */<b>
ZSTD_p_dictIDFlag, </b>/* When applicable, dictID of dictionary is provided in frame header (default:1) */<b>
</b>/* dictionary parameters */<b>
ZSTD_p_refDictContent=300, </b>/* Content of dictionary content will be referenced, instead of copied (default:0).<b>
* This avoids duplicating dictionary content.
* But it also requires that dictionary buffer outlives its users */
</b>/* Not ready yet ! <=================================== */<b>
ZSTD_p_dictMode, </b>/* Select how dictionary must be interpreted. Value must be from type ZSTD_dictMode_e.<b>
* default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
</b>/* multi-threading parameters */<b>
ZSTD_p_nbThreads=400, </b>/* Select how many threads a compression job can spawn (default:1)<b>
* More threads improve speed, but also increase memory usage.
* Can only receive a value > 1 if ZSTD_MULTITHREAD is enabled.
* Special: value 0 means "do not change nbThreads" */
ZSTD_p_jobSize, </b>/* Size of a compression job. Each compression job is completed in parallel.<b>
* 0 means default, which is dynamically determined based on compression parameters.
* Job size must be a minimum of overlapSize, or 1 KB, whichever is largest
* The minimum size is automatically and transparently enforced */
ZSTD_p_overlapSizeLog, </b>/* Size of previous input reloaded at the beginning of each job.<b>
* 0 => no overlap, 6(default) => use 1/8th of windowSize, >=9 => use full windowSize */
</b>/* advanced parameters - may not remain available after API update */<b>
ZSTD_p_forceMaxWindow=1100, </b>/* Force back-references to remain < windowSize,<b>
* even when referencing into Dictionary content.
* default : 0 when using a CDict, 1 when using a Prefix */
} ZSTD_cParameter;
</b></pre><BR>
<pre><b>size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value);
</b><p> Set one compression parameter, selected by enum ZSTD_cParameter.
Note : when `value` is an enum, cast it to unsigned for proper type checking.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
</b><p> Total input data size to be compressed as a single frame.
This value will be controlled at the end, and result in error if not respected.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
Note 1 : 0 means zero, empty.
In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
Note 2 : If all data is provided and consumed in a single round,
this value is overriden by srcSize instead.
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
</b><p> Create an internal CDict from dict buffer.
Decompression will have to use same buffer.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary,
meaning "return to no-dictionary mode".
Note 1 : Dictionary content will be copied internally,
except if ZSTD_p_refDictContent is set.
Note 2 : Loading a dictionary involves building tables, which are dependent on compression parameters.
For this reason, compression parameters cannot be changed anymore after loading a dictionary.
It's also a CPU-heavy operation, with non-negligible impact on latency.
Note 3 : Dictionary will be used for all future compression jobs.
To return to "no-dictionary" situation, load a NULL dictionary
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
</b><p> Ref a prepared dictionary, to be used for all next compression jobs.
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 compression jobs using same CCtx.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
Special : adding a NULL CDict means "return to no-dictionary mode".
Note 1 : Currently, only one dictionary can be managed.
Adding a new dictionary effectively "discards" any previous one.
Note 2 : CDict is just referenced, its lifetime must outlive CCtx.
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); </b>/* Not ready yet ! <===================================== */<b>
</b><p> Reference a prefix (content-only dictionary) to bootstrap next compression job.
Decompression will have to use same prefix.
Prefix is only used once. Tables are discarded at end of compression job.
If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
Special : Adding a NULL (or 0-size) dictionary invalidates any previous prefix, meaning "return to no-dictionary mode".
Note 1 : Prefix buffer is referenced. It must outlive compression job.
Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
It's a CPU-heavy operation, with non-negligible impact on latency.
</p></pre><BR>
<pre><b>typedef enum {
ZSTD_e_continue=0, </b>/* collect more data, encoder transparently decides when to output result, for optimal conditions */<b>
ZSTD_e_flush, </b>/* flush any data provided so far - frame will continue, future data can still reference previous data for better compression */<b>
ZSTD_e_end </b>/* flush any remaining data and ends current frame. Any future compression starts a new frame. */<b>
} ZSTD_EndDirective;
</b></pre><BR>
<pre><b>size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
ZSTD_outBuffer* output,
ZSTD_inBuffer* input,
ZSTD_EndDirective endOp);
</b><p> Behave about the same as ZSTD_compressStream. To note :
- Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_setParameter()
- Compression parameters cannot be changed once compression is started.
- *dstPos must be <= dstCapacity, *srcPos must be <= srcSize
- *dspPos and *srcPos will be updated. They are guaranteed to remain below their respective limit.
- @return provides the minimum amount of data still to flush from internal buffers
or an error code, which can be tested using ZSTD_isError().
if @return != 0, flush is not fully completed, there is some data left within internal buffers.
- after a ZSTD_e_end directive, if internal buffer is not fully flushed,
only ZSTD_e_end or ZSTD_e_flush operations are allowed.
It is necessary to fully flush internal buffers
before starting a new compression job, or changing compression parameters.
</p></pre><BR>
<pre><b>void ZSTD_CCtx_reset(ZSTD_CCtx* cctx); </b>/* Not ready yet ! */<b>
</b><p> Return a CCtx to clean state.
Useful after an error, or to interrupt an ongoing compression job and start a new one.
Any internal data not yet flushed is cancelled.
Dictionary (if any) is dropped.
It's possible to modify compression parameters after a reset.
</p></pre><BR>
<pre><b>size_t ZSTD_compress_generic_simpleArgs (
ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity, size_t* dstPos,
const void* src, size_t srcSize, size_t* srcPos,
ZSTD_EndDirective endOp);
</b><p> Same as ZSTD_compress_generic(),
but using only integral types as arguments.
Argument list is larger and less expressive than ZSTD_{in,out}Buffer,
but can be helpful for binders from dynamic languages
which have troubles handling structures containing memory pointers.
</p></pre><BR>
<a name="Chapter20"></a><h2>Block functions</h2><pre>
Block functions produce and decode raw zstd blocks, without frame metadata.
Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes).
@@ -667,7 +933,7 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+ compression : any ZSTD_compressBegin*() variant, including with dictionary
+ decompression : any ZSTD_decompressBegin*() variant, including with dictionary
+ copyCCtx() and copyDCtx() can be used too
- Block size is limited, it must be <= ZSTD_getBlockSizeMax() <= ZSTD_BLOCKSIZE_ABSOLUTEMAX
- Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX
+ If input is larger than a block size, it's necessary to split input data into multiple blocks
+ For inputs larger than a single block size, consider using the regular ZSTD_compress() instead.
Frame metadata is not that costly, and quickly becomes negligible as source size grows larger.
@@ -680,7 +946,7 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
Use ZSTD_insertBlock() for such a case.
<BR></pre>
<h3>Raw zstd block functions</h3><pre></pre><b><pre>size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx);
<h3>Raw zstd block functions</h3><pre></pre><b><pre>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 ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); </b>/**< insert block into `dctx` history. Useful for uncompressed blocks */<b>
lib/common/bitstream.h
+9 -6
View File
@@ -58,7 +58,9 @@ extern "C" {
#if defined(BIT_DEBUG) && (BIT_DEBUG>=1)
# include <assert.h>
#else
# define assert(condition) ((void)0)
# ifndef assert
# define assert(condition) ((void)0)
# endif
#endif
@@ -73,6 +75,7 @@ extern "C" {
#define STREAM_ACCUMULATOR_MIN_64 57
#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
/*-******************************************
* bitStream encoding API (write forward)
********************************************/
@@ -307,19 +310,19 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
/* fall-through */
case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
/* fall-through */
case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
/* fall-through */
case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
/* fall-through */
case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
/* fall-through */
default: break;
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
lib/common/error_private.c
+2 -1
View File
@@ -24,7 +24,8 @@ const char* ERR_getErrorString(ERR_enum code)
case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
case PREFIX(frameParameter_unsupportedBy32bits): return "Frame parameter unsupported in 32-bits mode";
case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
case PREFIX(compressionParameter_unsupported): return "Compression parameter is out of bound";
case PREFIX(compressionParameter_unsupported): return "Compression parameter is not supported";
case PREFIX(compressionParameter_outOfBound): return "Compression parameter is out of bound";
case PREFIX(init_missing): return "Context should be init first";
case PREFIX(memory_allocation): return "Allocation error : not enough memory";
case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
lib/common/mem.h
-14
View File
@@ -352,20 +352,6 @@ MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val)
}
/* function safe only for comparisons */
MEM_STATIC U32 MEM_readMINMATCH(const void* memPtr, U32 length)
{
switch (length)
{
default :
case 4 : return MEM_read32(memPtr);
case 3 : if (MEM_isLittleEndian())
return MEM_read32(memPtr)<<8;
else
return MEM_read32(memPtr)>>8;
}
}
#if defined (__cplusplus)
}
#endif
lib/common/pool.c
+12
View File
@@ -146,6 +146,13 @@ void POOL_free(POOL_ctx *ctx) {
free(ctx);
}
size_t POOL_sizeof(POOL_ctx *ctx) {
if (ctx==NULL) return 0; /* supports sizeof NULL */
return sizeof(*ctx)
+ ctx->queueSize * sizeof(POOL_job)
+ ctx->numThreads * sizeof(pthread_t);
}
void POOL_add(void *ctxVoid, POOL_function function, void *opaque) {
POOL_ctx *ctx = (POOL_ctx *)ctxVoid;
if (!ctx) { return; }
@@ -191,4 +198,9 @@ void POOL_add(void *ctx, POOL_function function, void *opaque) {
function(opaque);
}
size_t POOL_sizeof(POOL_ctx *ctx) {
if (ctx==NULL) return 0; /* supports sizeof NULL */
return sizeof(*ctx);
}
#endif /* ZSTD_MULTITHREAD */
lib/common/pool.h
+5
View File
@@ -32,6 +32,11 @@ POOL_ctx *POOL_create(size_t numThreads, size_t queueSize);
*/
void POOL_free(POOL_ctx *ctx);
/*! POOL_sizeof() :
return memory usage of pool returned by POOL_create().
*/
size_t POOL_sizeof(POOL_ctx *ctx);
/*! POOL_function :
The function type that can be added to a thread pool.
*/
lib/common/zstd_common.c
+24 -19
View File
@@ -12,7 +12,8 @@
/*-*************************************
* Dependencies
***************************************/
#include <stdlib.h> /* malloc */
#include <stdlib.h> /* malloc, calloc, free */
#include <string.h> /* memset */
#include "error_private.h"
#define ZSTD_STATIC_LINKING_ONLY
#include "zstd.h"
@@ -21,7 +22,7 @@
/*-****************************************
* Version
******************************************/
unsigned ZSTD_versionNumber (void) { return ZSTD_VERSION_NUMBER; }
unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; }
const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; }
@@ -49,27 +50,31 @@ const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString
/*=**************************************************************
* Custom allocator
****************************************************************/
/* default uses stdlib */
void* ZSTD_defaultAllocFunction(void* opaque, size_t size)
{
void* address = malloc(size);
(void)opaque;
return address;
}
void ZSTD_defaultFreeFunction(void* opaque, void* address)
{
(void)opaque;
free(address);
}
void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
{
return customMem.customAlloc(customMem.opaque, size);
if (customMem.customAlloc)
return customMem.customAlloc(customMem.opaque, size);
return malloc(size);
}
void* ZSTD_calloc(size_t size, ZSTD_customMem customMem)
{
if (customMem.customAlloc) {
/* calloc implemented as malloc+memset;
* not as efficient as calloc, but next best guess for custom malloc */
void* const ptr = customMem.customAlloc(customMem.opaque, size);
memset(ptr, 0, size);
return ptr;
}
return calloc(1, size);
}
void ZSTD_free(void* ptr, ZSTD_customMem customMem)
{
if (ptr!=NULL)
customMem.customFree(customMem.opaque, ptr);
if (ptr!=NULL) {
if (customMem.customFree)
customMem.customFree(customMem.opaque, ptr);
else
free(ptr);
}
}
lib/common/zstd_errors.h
+7 -3
View File
@@ -35,8 +35,11 @@ extern "C" {
#endif
/*-****************************************
* error codes list
******************************************/
* error codes list
* note : this API is still considered unstable
* it should not be used with a dynamic library
* only static linking is allowed
******************************************/
typedef enum {
ZSTD_error_no_error,
ZSTD_error_GENERIC,
@@ -47,6 +50,7 @@ typedef enum {
ZSTD_error_frameParameter_unsupportedBy32bits,
ZSTD_error_frameParameter_windowTooLarge,
ZSTD_error_compressionParameter_unsupported,
ZSTD_error_compressionParameter_outOfBound,
ZSTD_error_init_missing,
ZSTD_error_memory_allocation,
ZSTD_error_stage_wrong,
@@ -67,7 +71,7 @@ typedef enum {
/*! ZSTD_getErrorCode() :
convert a `size_t` function result into a `ZSTD_ErrorCode` enum type,
which can be used to compare directly with enum list published into "error_public.h" */
which can be used to compare with enum list published above */
ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult);
ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code);
lib/common/zstd_internal.h
+61 -8
View File
@@ -18,6 +18,7 @@
# include <intrin.h> /* For Visual 2005 */
# pragma warning(disable : 4100) /* disable: C4100: unreferenced formal parameter */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
# pragma warning(disable : 4324) /* disable: C4324: padded structure */
#else
# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
@@ -50,9 +51,36 @@
#define ZSTD_STATIC_LINKING_ONLY
#include "zstd.h"
#ifndef XXH_STATIC_LINKING_ONLY
# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */
# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */
#endif
#include "xxhash.h" /* XXH_reset, update, digest */
/*-*************************************
* Debug
***************************************/
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
# include <assert.h>
#else
# ifndef assert
# define assert(condition) ((void)0)
# endif
#endif
#define ZSTD_STATIC_ASSERT(c) { enum { ZSTD_static_assert = 1/(int)(!!(c)) }; }
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
# include <stdio.h>
static unsigned g_debugLevel = ZSTD_DEBUG;
# define DEBUGLOG(l, ...) { \
if (l<=g_debugLevel) { \
fprintf(stderr, __FILE__ ": "); \
fprintf(stderr, __VA_ARGS__); \
fprintf(stderr, " \n"); \
} }
#else
# define DEBUGLOG(l, ...) {} /* disabled */
#endif
#include "xxhash.h" /* XXH_reset, update, digest */
/*-*************************************
@@ -235,15 +263,10 @@ typedef struct {
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);
int ZSTD_isSkipFrame(ZSTD_DCtx* dctx);
/* custom memory allocation functions */
void* ZSTD_defaultAllocFunction(void* opaque, size_t size);
void ZSTD_defaultFreeFunction(void* opaque, void* address);
#ifndef ZSTD_DLL_IMPORT
static const ZSTD_customMem defaultCustomMem = { ZSTD_defaultAllocFunction, ZSTD_defaultFreeFunction, NULL };
#endif
void* ZSTD_malloc(size_t size, ZSTD_customMem customMem);
void* ZSTD_calloc(size_t size, ZSTD_customMem customMem);
void ZSTD_free(void* ptr, ZSTD_customMem customMem);
@@ -281,4 +304,34 @@ MEM_STATIC U32 ZSTD_highbit32(U32 val)
void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx);
typedef enum { ZSTDb_not_buffered, ZSTDb_buffered } ZSTD_buffered_policy_e;
#if 0
/*! ZSTD_compressBegin_internal() :
* innermost initialization function. Private use only.
* expects params to be valid.
* must receive dict, or cdict, or none, but not both.
* @return : 0, or an error code */
size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
const void* dict, size_t dictSize,
const ZSTD_CDict* cdict,
ZSTD_parameters params, U64 pledgedSrcSize,
ZSTD_buffered_policy_e zbuff);
#endif
/*! ZSTD_initCStream_internal() :
* Private use only. Init streaming operation.
* expects params to be valid.
* must receive dict, or cdict, or none, but not both.
* @return : 0, or an error code */
size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
const void* dict, size_t dictSize,
const ZSTD_CDict* cdict,
ZSTD_parameters params, unsigned long long pledgedSrcSize);
/*! ZSTD_getParamsFromCDict() :
* as the name implies */
ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict);
#endif /* ZSTD_CCOMMON_H_MODULE */
lib/compress/zstd_compress.c
+911 -427
View File
@@ -8,6 +8,14 @@
*/
/*-*************************************
* Tuning parameters
***************************************/
#ifndef ZSTD_CLEVEL_DEFAULT
# define ZSTD_CLEVEL_DEFAULT 3
#endif
/*-*************************************
* Dependencies
***************************************/
@@ -18,26 +26,7 @@
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "zstd_internal.h" /* includes zstd.h */
/*-*************************************
* Debug
***************************************/
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
# include <assert.h>
#else
# define assert(condition) ((void)0)
#endif
#define ZSTD_STATIC_ASSERT(c) { enum { ZSTD_static_assert = 1/(int)(!!(c)) }; }
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
# include <stdio.h>
static unsigned g_debugLevel = ZSTD_DEBUG;
# define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); }
#else
# define DEBUGLOG(l, ...) {} /* disabled */
#endif
#include "zstdmt_compress.h"
/*-*************************************
@@ -79,7 +68,14 @@ static void ZSTD_resetSeqStore(seqStore_t* ssPtr)
/*-*************************************
* Context memory management
***************************************/
typedef enum { zcss_init, zcss_load, zcss_flush, zcss_final } ZSTD_cStreamStage;
typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage;
struct ZSTD_CDict_s {
void* dictBuffer;
const void* dictContent;
size_t dictContentSize;
ZSTD_CCtx* refContext;
}; /* typedef'd to ZSTD_CDict within "zstd.h" */
struct ZSTD_CCtx_s {
const BYTE* nextSrc; /* next block here to continue on current prefix */
@@ -92,19 +88,22 @@ struct ZSTD_CCtx_s {
U32 hashLog3; /* dispatch table : larger == faster, more memory */
U32 loadedDictEnd; /* index of end of dictionary */
U32 forceWindow; /* force back-references to respect limit of 1<<wLog, even for dictionary */
U32 forceRawDict; /* Force loading dictionary in "content-only" mode (no header analysis) */
ZSTD_dictMode_e dictMode; /* select restricting dictionary to "rawContent" or "fullDict" only */
ZSTD_compressionStage_e stage;
U32 rep[ZSTD_REP_NUM];
U32 repToConfirm[ZSTD_REP_NUM];
U32 dictID;
ZSTD_parameters params;
int compressionLevel;
ZSTD_parameters requestedParams;
ZSTD_parameters appliedParams;
void* workSpace;
size_t workSpaceSize;
size_t blockSize;
U64 frameContentSize;
U64 pledgedSrcSizePlusOne; /* this way, 0 (default) == unknown */
U64 consumedSrcSize;
XXH64_state_t xxhState;
ZSTD_customMem customMem;
size_t staticSize;
seqStore_t seqStore; /* sequences storage ptrs */
U32* hashTable;
@@ -132,39 +131,71 @@ struct ZSTD_CCtx_s {
size_t outBuffFlushedSize;
ZSTD_cStreamStage streamStage;
U32 frameEnded;
U64 pledgedSrcSize;
/* Multi-threading */
U32 nbThreads;
ZSTDMT_CCtx* mtctx;
};
ZSTD_CCtx* ZSTD_createCCtx(void)
{
return ZSTD_createCCtx_advanced(defaultCustomMem);
return ZSTD_createCCtx_advanced(ZSTD_defaultCMem);
}
ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem)
{
ZSTD_CCtx* cctx;
if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
if (!customMem.customAlloc || !customMem.customFree) return NULL;
if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
cctx = (ZSTD_CCtx*) ZSTD_malloc(sizeof(ZSTD_CCtx), customMem);
cctx = (ZSTD_CCtx*) ZSTD_calloc(sizeof(ZSTD_CCtx), customMem);
if (!cctx) return NULL;
memset(cctx, 0, sizeof(ZSTD_CCtx));
cctx->customMem = customMem;
cctx->compressionLevel = ZSTD_CLEVEL_DEFAULT;
ZSTD_STATIC_ASSERT(zcss_init==0);
ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1));
return cctx;
}
ZSTD_CCtx* ZSTD_initStaticCCtx(void *workspace, size_t workspaceSize)
{
ZSTD_CCtx* cctx = (ZSTD_CCtx*) workspace;
if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */
if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */
memset(workspace, 0, workspaceSize); /* may be a bit generous, could memset be smaller ? */
cctx->staticSize = workspaceSize;
cctx->workSpace = (void*)(cctx+1);
cctx->workSpaceSize = workspaceSize - sizeof(ZSTD_CCtx);
/* entropy space (never moves) */
/* note : this code should be shared with resetCCtx, rather than copy/pasted */
{ void* ptr = cctx->workSpace;
cctx->hufCTable = (HUF_CElt*)ptr;
ptr = (char*)cctx->hufCTable + hufCTable_size;
cctx->offcodeCTable = (FSE_CTable*) ptr;
ptr = (char*)ptr + offcodeCTable_size;
cctx->matchlengthCTable = (FSE_CTable*) ptr;
ptr = (char*)ptr + matchlengthCTable_size;
cctx->litlengthCTable = (FSE_CTable*) ptr;
ptr = (char*)ptr + litlengthCTable_size;
assert(((size_t)ptr & 3) == 0); /* ensure correct alignment */
cctx->entropyScratchSpace = (unsigned*) ptr;
}
return 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 */
ZSTD_free(cctx->workSpace, cctx->customMem);
cctx->workSpace = NULL;
ZSTD_freeCDict(cctx->cdictLocal);
cctx->cdictLocal = NULL;
ZSTD_free(cctx->inBuff, cctx->customMem);
cctx->inBuff = NULL;
ZSTD_free(cctx->outBuff, cctx->customMem);
cctx->outBuff = NULL;
ZSTDMT_freeCCtx(cctx->mtctx);
cctx->mtctx = NULL;
ZSTD_free(cctx, cctx->customMem);
return 0; /* reserved as a potential error code in the future */
}
@@ -172,38 +203,263 @@ size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx)
{
if (cctx==NULL) return 0; /* support sizeof on NULL */
DEBUGLOG(5, "sizeof(*cctx) : %u", (U32)sizeof(*cctx));
DEBUGLOG(5, "workSpaceSize : %u", (U32)cctx->workSpaceSize);
DEBUGLOG(5, "streaming buffers : %u", (U32)(cctx->outBuffSize + cctx->inBuffSize));
DEBUGLOG(5, "inner MTCTX : %u", (U32)ZSTDMT_sizeof_CCtx(cctx->mtctx));
return sizeof(*cctx) + cctx->workSpaceSize
+ ZSTD_sizeof_CDict(cctx->cdictLocal)
+ cctx->outBuffSize + cctx->inBuffSize;
+ cctx->outBuffSize + cctx->inBuffSize
+ ZSTDMT_sizeof_CCtx(cctx->mtctx);
}
size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs)
{
return ZSTD_sizeof_CCtx(zcs); /* same object */
}
/* private API call, for dictBuilder only */
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); }
static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx* cctx) { return cctx->appliedParams; }
/* older variant; will be deprecated */
size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value)
{
switch(param)
{
case ZSTD_p_forceWindow : cctx->forceWindow = value>0; cctx->loadedDictEnd = 0; return 0;
case ZSTD_p_forceRawDict : cctx->forceRawDict = value>0; return 0;
ZSTD_STATIC_ASSERT(ZSTD_dm_auto==0);
ZSTD_STATIC_ASSERT(ZSTD_dm_rawContent==1);
case ZSTD_p_forceRawDict : cctx->dictMode = (ZSTD_dictMode_e)(value>0); return 0;
default: return ERROR(parameter_unknown);
}
}
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) /* hidden interface */
#define ZSTD_CLEVEL_CUSTOM 999
static void ZSTD_cLevelToCParams(ZSTD_CCtx* cctx)
{
return &(ctx->seqStore);
if (cctx->compressionLevel==ZSTD_CLEVEL_CUSTOM) return;
cctx->requestedParams.cParams = ZSTD_getCParams(cctx->compressionLevel,
cctx->pledgedSrcSizePlusOne-1, 0);
cctx->compressionLevel = ZSTD_CLEVEL_CUSTOM;
}
static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx* cctx)
#define CLAMPCHECK(val,min,max) { \
if (((val)<(min)) | ((val)>(max))) { \
return ERROR(compressionParameter_outOfBound); \
} }
size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value)
{
return cctx->params;
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
switch(param)
{
case ZSTD_p_compressionLevel :
if ((int)value > ZSTD_maxCLevel()) value = ZSTD_maxCLevel(); /* cap max compression level */
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
cctx->compressionLevel = value;
return 0;
case ZSTD_p_windowLog :
DEBUGLOG(5, "setting ZSTD_p_windowLog = %u (cdict:%u)",
value, (cctx->cdict!=NULL));
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.windowLog = value;
return 0;
case ZSTD_p_hashLog :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.hashLog = value;
return 0;
case ZSTD_p_chainLog :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.chainLog = value;
return 0;
case ZSTD_p_searchLog :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.searchLog = value;
return 0;
case ZSTD_p_minMatch :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.searchLength = value;
return 0;
case ZSTD_p_targetLength :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.targetLength = value;
return 0;
case ZSTD_p_compressionStrategy :
if (value == 0) return 0; /* special value : 0 means "don't change anything" */
if (cctx->cdict) return ERROR(stage_wrong);
CLAMPCHECK(value, (unsigned)ZSTD_fast, (unsigned)ZSTD_btultra);
ZSTD_cLevelToCParams(cctx);
cctx->requestedParams.cParams.strategy = (ZSTD_strategy)value;
return 0;
#if 0
case ZSTD_p_windowSize : /* to be done later */
return ERROR(compressionParameter_unsupported);
#endif
case ZSTD_p_contentSizeFlag :
DEBUGLOG(5, "set content size flag = %u", (value>0));
/* Content size written in frame header _when known_ (default:1) */
cctx->requestedParams.fParams.contentSizeFlag = value>0;
return 0;
case ZSTD_p_checksumFlag :
/* A 32-bits content checksum will be calculated and written at end of frame (default:0) */
cctx->requestedParams.fParams.checksumFlag = value>0;
return 0;
case ZSTD_p_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */
DEBUGLOG(5, "set dictIDFlag = %u", (value>0));
cctx->requestedParams.fParams.noDictIDFlag = (value==0);
return 0;
case ZSTD_p_refDictContent : /* to be done later */
return ERROR(compressionParameter_unsupported);
case ZSTD_p_dictMode :
/* restrict dictionary mode, to "rawContent" or "fullDict" only */
ZSTD_STATIC_ASSERT((U32)ZSTD_dm_fullDict > (U32)ZSTD_dm_rawContent);
if (value > (unsigned)ZSTD_dm_fullDict)
return ERROR(compressionParameter_outOfBound);
cctx->dictMode = (ZSTD_dictMode_e)value;
return 0;
case ZSTD_p_forceMaxWindow : /* Force back-references to remain < windowSize,
* even when referencing into Dictionary content
* default : 0 when using a CDict, 1 when using a Prefix */
cctx->forceWindow = value>0;
cctx->loadedDictEnd = 0;
return 0;
case ZSTD_p_nbThreads:
if (value==0) return 0;
DEBUGLOG(5, " setting nbThreads : %u", value);
#ifndef ZSTD_MULTITHREAD
if (value > 1) return ERROR(compressionParameter_unsupported);
#endif
if ((value>1) && (cctx->nbThreads != value)) {
if (cctx->staticSize) /* MT not compatible with static alloc */
return ERROR(compressionParameter_unsupported);
ZSTDMT_freeCCtx(cctx->mtctx);
cctx->nbThreads = 1;
cctx->mtctx = ZSTDMT_createCCtx(value);
if (cctx->mtctx == NULL) return ERROR(memory_allocation);
}
cctx->nbThreads = value;
return 0;
case ZSTD_p_jobSize:
if (cctx->nbThreads <= 1) return ERROR(compressionParameter_unsupported);
assert(cctx->mtctx != NULL);
return ZSTDMT_setMTCtxParameter(cctx->mtctx, ZSTDMT_p_sectionSize, value);
case ZSTD_p_overlapSizeLog:
DEBUGLOG(5, " setting overlap with nbThreads == %u", cctx->nbThreads);
if (cctx->nbThreads <= 1) return ERROR(compressionParameter_unsupported);
assert(cctx->mtctx != NULL);
return ZSTDMT_setMTCtxParameter(cctx->mtctx, ZSTDMT_p_overlapSectionLog, value);
default: return ERROR(parameter_unknown);
}
}
ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize)
{
DEBUGLOG(5, " setting pledgedSrcSize to %u", (U32)pledgedSrcSize);
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
return 0;
}
/** ZSTD_checkParams() :
ensure param values remain within authorized range.
ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
{
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
if (cctx->staticSize) return ERROR(memory_allocation); /* no malloc for static CCtx */
DEBUGLOG(5, "load dictionary of 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;
} else {
ZSTD_compressionParameters const cParams =
cctx->compressionLevel == ZSTD_CLEVEL_CUSTOM ?
cctx->requestedParams.cParams :
ZSTD_getCParams(cctx->compressionLevel, 0, dictSize);
cctx->cdictLocal = ZSTD_createCDict_advanced(
dict, dictSize,
0 /* byReference */, cctx->dictMode,
cParams, cctx->customMem);
cctx->cdict = cctx->cdictLocal;
if (cctx->cdictLocal == NULL)
return ERROR(memory_allocation);
}
return 0;
}
/* Not ready yet ! */
size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize)
{
(void)cctx; (void)prefix; (void)prefixSize; /* to be done later */
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
return ERROR(compressionParameter_unsupported);
}
size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
{
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
cctx->cdict = cdict;
return ERROR(compressionParameter_unsupported);
}
static void ZSTD_startNewCompression(ZSTD_CCtx* cctx)
{
cctx->streamStage = zcss_init;
cctx->pledgedSrcSizePlusOne = 0;
}
/*! ZSTD_CCtx_reset() :
* Also dumps dictionary */
void ZSTD_CCtx_reset(ZSTD_CCtx* cctx)
{
ZSTD_startNewCompression(cctx);
cctx->cdict = NULL;
}
/** ZSTD_checkCParams() :
control CParam values remain within authorized range.
@return : 0, or an error code if one value is beyond authorized range */
size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
{
# define CLAMPCHECK(val,min,max) { if ((val<min) | (val>max)) return ERROR(compressionParameter_unsupported); }
CLAMPCHECK(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
CLAMPCHECK(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
CLAMPCHECK(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
@@ -214,6 +470,24 @@ size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
return 0;
}
/** ZSTD_clampCParams() :
* make CParam values within valid range.
* @return : valid CParams */
static ZSTD_compressionParameters ZSTD_clampCParams(ZSTD_compressionParameters cParams)
{
# define CLAMP(val,min,max) { \
if (val<min) val=min; \
else if (val>max) val=max; \
}
CLAMP(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
CLAMP(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
CLAMP(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
CLAMP(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
CLAMP(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
CLAMP(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
if ((U32)(cParams.strategy) > (U32)ZSTD_btultra) cParams.strategy = ZSTD_btultra;
return cParams;
}
/** ZSTD_cycleLog() :
* condition for correct operation : hashLog > 1 */
@@ -223,14 +497,15 @@ static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
return hashLog - btScale;
}
/** ZSTD_adjustCParams() :
/** ZSTD_adjustCParams_internal() :
optimize `cPar` for a given input (`srcSize` and `dictSize`).
mostly downsizing to reduce memory consumption and initialization.
Both `srcSize` and `dictSize` are optional (use 0 if unknown),
but if both are 0, no optimization can be done.
Note : cPar is considered validated at this stage. Use ZSTD_checkParams() to ensure that. */
ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
ZSTD_compressionParameters ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
{
assert(ZSTD_checkCParams(cPar)==0);
if (srcSize+dictSize == 0) return cPar; /* no size information available : no adjustment */
/* resize params, to use less memory when necessary */
@@ -250,10 +525,16 @@ ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, u
return cPar;
}
ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
{
cPar = ZSTD_clampCParams(cPar);
return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize);
}
size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams)
{
size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << cParams.windowLog);
size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
U32 const divider = (cParams.searchLength==3) ? 3 : 4;
size_t const maxNbSeq = blockSize / divider;
size_t const tokenSpace = blockSize + 11*maxNbSeq;
@@ -272,26 +553,48 @@ size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams)
size_t const optSpace = ((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btultra)) ? optBudget : 0;
size_t const neededSpace = entropySpace + tableSpace + tokenSpace + optSpace;
DEBUGLOG(5, "sizeof(ZSTD_CCtx) : %u", (U32)sizeof(ZSTD_CCtx));
DEBUGLOG(5, "estimate workSpace : %u", (U32)neededSpace);
return sizeof(ZSTD_CCtx) + neededSpace;
}
static U32 ZSTD_equivalentParams(ZSTD_parameters param1, ZSTD_parameters param2)
size_t ZSTD_estimateCStreamSize(ZSTD_compressionParameters cParams)
{
return (param1.cParams.hashLog == param2.cParams.hashLog)
& (param1.cParams.chainLog == param2.cParams.chainLog)
& (param1.cParams.strategy == param2.cParams.strategy) /* opt parser space */
& ((param1.cParams.searchLength==3) == (param2.cParams.searchLength==3)); /* hashlog3 space */
size_t const CCtxSize = ZSTD_estimateCCtxSize(cParams);
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;
return CCtxSize + streamingSize;
}
static U32 ZSTD_equivalentParams(ZSTD_compressionParameters cParams1,
ZSTD_compressionParameters cParams2)
{
U32 bslog1 = MIN(cParams1.windowLog, ZSTD_BLOCKSIZELOG_MAX);
U32 bslog2 = MIN(cParams2.windowLog, ZSTD_BLOCKSIZELOG_MAX);
return (bslog1 == bslog2) /* same block size */
& (cParams1.hashLog == cParams2.hashLog)
& (cParams1.chainLog == cParams2.chainLog)
& (cParams1.strategy == cParams2.strategy) /* opt parser space */
& ((cParams1.searchLength==3) == (cParams2.searchLength==3)); /* hashlog3 space */
}
/*! ZSTD_continueCCtx() :
reuse CCtx without reset (note : requires no dictionary) */
static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 frameContentSize)
* reuse CCtx without reset (note : requires no dictionary) */
static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 pledgedSrcSize)
{
U32 const end = (U32)(cctx->nextSrc - cctx->base);
cctx->params = params;
cctx->frameContentSize = frameContentSize;
DEBUGLOG(5, "continue mode");
cctx->appliedParams = params;
cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
cctx->consumedSrcSize = 0;
if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)
cctx->appliedParams.fParams.contentSizeFlag = 0;
DEBUGLOG(5, "pledged content size : %u ; flag : %u",
(U32)pledgedSrcSize, cctx->appliedParams.fParams.contentSizeFlag);
cctx->lowLimit = end;
cctx->dictLimit = end;
cctx->nextToUpdate = end+1;
@@ -304,33 +607,38 @@ static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 fra
return 0;
}
typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset, ZSTDcrp_fullReset } ZSTD_compResetPolicy_e;
typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset } ZSTD_compResetPolicy_e;
/*! ZSTD_resetCCtx_internal() :
note : `params` must be validated */
static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
ZSTD_parameters params, U64 frameContentSize,
ZSTD_compResetPolicy_e const crp)
note : `params` are assumed fully validated at this stage */
static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
ZSTD_parameters params, U64 pledgedSrcSize,
ZSTD_compResetPolicy_e const crp,
ZSTD_buffered_policy_e const zbuff)
{
DEBUGLOG(5, "ZSTD_resetCCtx_internal \n");
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
if (crp == ZSTDcrp_continue)
if (ZSTD_equivalentParams(params, zc->params)) {
DEBUGLOG(5, "ZSTD_equivalentParams()==1 \n");
if (crp == ZSTDcrp_continue) {
if (ZSTD_equivalentParams(params.cParams, zc->appliedParams.cParams)) {
DEBUGLOG(5, "ZSTD_equivalentParams()==1");
zc->fseCTables_ready = 0;
zc->hufCTable_repeatMode = HUF_repeat_none;
return ZSTD_continueCCtx(zc, params, frameContentSize);
}
return ZSTD_continueCCtx(zc, params, pledgedSrcSize);
} }
{ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog);
{ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << params.cParams.windowLog);
U32 const divider = (params.cParams.searchLength==3) ? 3 : 4;
size_t const maxNbSeq = blockSize / divider;
size_t const tokenSpace = blockSize + 11*maxNbSeq;
size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ? 0 : (1 << params.cParams.chainLog);
size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ?
0 : (1 << params.cParams.chainLog);
size_t const hSize = ((size_t)1) << params.cParams.hashLog;
U32 const hashLog3 = (params.cParams.searchLength>3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
U32 const hashLog3 = (params.cParams.searchLength>3) ?
0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
size_t const h3Size = ((size_t)1) << hashLog3;
size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
size_t const buffOutSize = (zbuff==ZSTDb_buffered) ? ZSTD_compressBound(blockSize)+1 : 0;
size_t const buffInSize = (zbuff==ZSTDb_buffered) ? ((size_t)1 << params.cParams.windowLog) + blockSize : 0;
void* ptr;
/* Check if workSpace is large enough, alloc a new one if needed */
@@ -339,11 +647,20 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
+ entropyScratchSpace_size;
size_t const optPotentialSpace = ((MaxML+1) + (MaxLL+1) + (MaxOff+1) + (1<<Litbits)) * sizeof(U32)
+ (ZSTD_OPT_NUM+1) * (sizeof(ZSTD_match_t)+sizeof(ZSTD_optimal_t));
size_t const optSpace = ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btultra)) ? optPotentialSpace : 0;
size_t const neededSpace = entropySpace + optSpace + tableSpace + tokenSpace;
if (zc->workSpaceSize < neededSpace) {
size_t const optSpace = ( (params.cParams.strategy == ZSTD_btopt)
|| (params.cParams.strategy == ZSTD_btultra)) ?
optPotentialSpace : 0;
size_t const bufferSpace = buffInSize + buffOutSize;
size_t const neededSpace = entropySpace + optSpace + tableSpace
+ tokenSpace + bufferSpace;
if (zc->workSpaceSize < neededSpace) { /* too small : resize /*/
DEBUGLOG(5, "Need to update workSpaceSize from %uK to %uK \n",
(unsigned)zc->workSpaceSize>>10, (unsigned)neededSpace>>10);
(unsigned)zc->workSpaceSize>>10,
(unsigned)neededSpace>>10);
/* static cctx : no resize, error out */
if (zc->staticSize) return ERROR(memory_allocation);
zc->workSpaceSize = 0;
ZSTD_free(zc->workSpace, zc->customMem);
zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
@@ -365,11 +682,14 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
} }
/* init params */
zc->params = params;
zc->blockSize = blockSize;
DEBUGLOG(5, "blockSize = %uK \n", (U32)blockSize>>10);
zc->frameContentSize = frameContentSize;
zc->appliedParams = params;
zc->pledgedSrcSizePlusOne = pledgedSrcSize+1;
zc->consumedSrcSize = 0;
if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)
zc->appliedParams.fParams.contentSizeFlag = 0;
DEBUGLOG(5, "pledged content size : %u ; flag : %u",
(U32)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag);
zc->blockSize = blockSize;
XXH64_reset(&zc->xxhState, 0);
zc->stage = ZSTDcs_init;
@@ -397,7 +717,7 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
/* opt parser space */
if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btultra)) {
DEBUGLOG(5, "reserving optimal parser space ");
DEBUGLOG(5, "reserving optimal parser space");
assert(((size_t)ptr & 3) == 0); /* ensure ptr is properly aligned */
zc->seqStore.litFreq = (U32*)ptr;
zc->seqStore.litLengthFreq = zc->seqStore.litFreq + (1<<Litbits);
@@ -425,6 +745,13 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
zc->seqStore.mlCode = zc->seqStore.llCode + maxNbSeq;
zc->seqStore.ofCode = zc->seqStore.mlCode + maxNbSeq;
zc->seqStore.litStart = zc->seqStore.ofCode + maxNbSeq;
ptr = zc->seqStore.litStart + blockSize;
/* buffers */
zc->inBuffSize = buffInSize;
zc->inBuff = (char*)ptr;
zc->outBuffSize = buffOutSize;
zc->outBuff = zc->inBuff + buffInSize;
return 0;
}
@@ -445,22 +772,25 @@ void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) {
* Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
* pledgedSrcSize=0 means "empty" if fParams.contentSizeFlag=1
* @return : 0, or an error code */
size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx,
ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize)
static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
const ZSTD_CCtx* srcCCtx,
ZSTD_frameParameters fParams,
unsigned long long pledgedSrcSize,
ZSTD_buffered_policy_e zbuff)
{
DEBUGLOG(5, "ZSTD_copyCCtx_internal \n");
DEBUGLOG(5, "ZSTD_copyCCtx_internal");
if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong);
memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
{ ZSTD_parameters params = srcCCtx->params;
{ ZSTD_parameters params = srcCCtx->appliedParams;
params.fParams = fParams;
DEBUGLOG(5, "ZSTD_resetCCtx_internal : dictIDFlag : %u \n", !fParams.noDictIDFlag);
ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset);
ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize,
ZSTDcrp_noMemset, zbuff);
}
/* copy tables */
{ size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog);
size_t const hSize = (size_t)1 << srcCCtx->params.cParams.hashLog;
{ size_t const chainSize = (srcCCtx->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->appliedParams.cParams.chainLog);
size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog;
size_t const h3Size = (size_t)1 << srcCCtx->hashLog3;
size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
assert((U32*)dstCCtx->chainTable == (U32*)dstCCtx->hashTable + hSize); /* chainTable must follow hashTable */
@@ -502,9 +832,11 @@ size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx,
size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize)
{
ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
ZSTD_buffered_policy_e const zbuff = (ZSTD_buffered_policy_e)(srcCCtx->inBuffSize>0);
ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1);
fParams.contentSizeFlag = pledgedSrcSize>0;
return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, fParams, pledgedSrcSize);
return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, fParams, pledgedSrcSize, zbuff);
}
@@ -523,10 +855,10 @@ static void ZSTD_reduceTable (U32* const table, U32 const size, U32 const reduce
* rescale all indexes to avoid future overflow (indexes are U32) */
static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue)
{
{ U32 const hSize = 1 << zc->params.cParams.hashLog;
{ U32 const hSize = 1 << zc->appliedParams.cParams.hashLog;
ZSTD_reduceTable(zc->hashTable, hSize, reducerValue); }
{ U32 const chainSize = (zc->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->params.cParams.chainLog);
{ U32 const chainSize = (zc->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->appliedParams.cParams.chainLog);
ZSTD_reduceTable(zc->chainTable, chainSize, reducerValue); }
{ U32 const h3Size = (zc->hashLog3) ? 1 << zc->hashLog3 : 0;
@@ -564,10 +896,11 @@ static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
break;
default: /*note : should not be necessary : flSize is within {1,2,3} */
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
memcpy(ostart + flSize, src, srcSize);
@@ -589,10 +922,11 @@ static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, cons
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
break;
default: /*note : should not be necessary : flSize is necessarily within {1,2,3} */
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
break;
default: /* not necessary : flSize is {1,2,3} */
assert(0);
}
ostart[flSize] = *(const BYTE*)src;
@@ -622,7 +956,7 @@ static size_t ZSTD_compressLiterals (ZSTD_CCtx* zc,
if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall); /* not enough space for compression */
{ HUF_repeat repeat = zc->hufCTable_repeatMode;
int const preferRepeat = zc->params.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
int const preferRepeat = zc->appliedParams.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
zc->entropyScratchSpace, entropyScratchSpace_size, zc->hufCTable, &repeat, preferRepeat)
@@ -654,13 +988,14 @@ static size_t ZSTD_compressLiterals (ZSTD_CCtx* zc,
MEM_writeLE32(ostart, lhc);
break;
}
default: /* should not be necessary, lhSize is only {3,4,5} */
case 5: /* 2 - 2 - 18 - 18 */
{ U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
MEM_writeLE32(ostart, lhc);
ostart[4] = (BYTE)(cLitSize >> 10);
break;
}
default: /* not possible : lhSize is {3,4,5} */
assert(0);
}
return lhSize+cLitSize;
}
@@ -711,7 +1046,7 @@ MEM_STATIC size_t ZSTD_compressSequences (ZSTD_CCtx* zc,
void* dst, size_t dstCapacity,
size_t srcSize)
{
const int longOffsets = zc->params.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
const int longOffsets = zc->appliedParams.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
const seqStore_t* seqStorePtr = &(zc->seqStore);
U32 count[MaxSeq+1];
S16 norm[MaxSeq+1];
@@ -916,12 +1251,6 @@ _check_compressibility:
return op - ostart;
}
#if 0 /* for debug */
# define STORESEQ_DEBUG
#include <stdio.h> /* fprintf */
U32 g_startDebug = 0;
const BYTE* g_start = NULL;
#endif
/*! ZSTD_storeSeq() :
Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
@@ -930,16 +1259,16 @@ const BYTE* g_start = NULL;
*/
MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const void* literals, U32 offsetCode, size_t matchCode)
{
#ifdef STORESEQ_DEBUG
if (g_startDebug) {
const U32 pos = (U32)((const BYTE*)literals - g_start);
if (g_start==NULL) g_start = (const BYTE*)literals;
if ((pos > 1895000) && (pos < 1895300))
DEBUGLOG(5, "Cpos %6u :%5u literals & match %3u bytes at distance %6u \n",
pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode);
}
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG >= 6)
static const BYTE* g_start = NULL;
U32 const pos = (U32)((const BYTE*)literals - g_start);
if (g_start==NULL) g_start = (const BYTE*)literals;
if ((pos > 0) && (pos < 1000000000))
DEBUGLOG(6, "Cpos %6u :%5u literals & match %3u bytes at distance %6u",
pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode);
#endif
/* copy Literals */
assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + 128 KB);
ZSTD_wildcopy(seqStorePtr->lit, literals, litLength);
seqStorePtr->lit += litLength;
@@ -1113,7 +1442,7 @@ static size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls)
static void ZSTD_fillHashTable (ZSTD_CCtx* zc, const void* end, const U32 mls)
{
U32* const hashTable = zc->hashTable;
U32 const hBits = zc->params.cParams.hashLog;
U32 const hBits = zc->appliedParams.cParams.hashLog;
const BYTE* const base = zc->base;
const BYTE* ip = base + zc->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
@@ -1132,7 +1461,7 @@ void ZSTD_compressBlock_fast_generic(ZSTD_CCtx* cctx,
const U32 mls)
{
U32* const hashTable = cctx->hashTable;
U32 const hBits = cctx->params.cParams.hashLog;
U32 const hBits = cctx->appliedParams.cParams.hashLog;
seqStore_t* seqStorePtr = &(cctx->seqStore);
const BYTE* const base = cctx->base;
const BYTE* const istart = (const BYTE*)src;
@@ -1217,7 +1546,7 @@ void ZSTD_compressBlock_fast_generic(ZSTD_CCtx* cctx,
static void ZSTD_compressBlock_fast(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
const U32 mls = ctx->params.cParams.searchLength;
const U32 mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1238,7 +1567,7 @@ static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx* ctx,
const U32 mls)
{
U32* hashTable = ctx->hashTable;
const U32 hBits = ctx->params.cParams.hashLog;
const U32 hBits = ctx->appliedParams.cParams.hashLog;
seqStore_t* seqStorePtr = &(ctx->seqStore);
const BYTE* const base = ctx->base;
const BYTE* const dictBase = ctx->dictBase;
@@ -1331,7 +1660,7 @@ static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx* ctx,
static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
U32 const mls = ctx->params.cParams.searchLength;
U32 const mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1353,9 +1682,9 @@ static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx* ctx,
static void ZSTD_fillDoubleHashTable (ZSTD_CCtx* cctx, const void* end, const U32 mls)
{
U32* const hashLarge = cctx->hashTable;
U32 const hBitsL = cctx->params.cParams.hashLog;
U32 const hBitsL = cctx->appliedParams.cParams.hashLog;
U32* const hashSmall = cctx->chainTable;
U32 const hBitsS = cctx->params.cParams.chainLog;
U32 const hBitsS = cctx->appliedParams.cParams.chainLog;
const BYTE* const base = cctx->base;
const BYTE* ip = base + cctx->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
@@ -1375,9 +1704,9 @@ void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx* cctx,
const U32 mls)
{
U32* const hashLong = cctx->hashTable;
const U32 hBitsL = cctx->params.cParams.hashLog;
const U32 hBitsL = cctx->appliedParams.cParams.hashLog;
U32* const hashSmall = cctx->chainTable;
const U32 hBitsS = cctx->params.cParams.chainLog;
const U32 hBitsS = cctx->appliedParams.cParams.chainLog;
seqStore_t* seqStorePtr = &(cctx->seqStore);
const BYTE* const base = cctx->base;
const BYTE* const istart = (const BYTE*)src;
@@ -1487,7 +1816,7 @@ void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx* cctx,
static void ZSTD_compressBlock_doubleFast(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
{
const U32 mls = ctx->params.cParams.searchLength;
const U32 mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1508,9 +1837,9 @@ static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx* ctx,
const U32 mls)
{
U32* const hashLong = ctx->hashTable;
U32 const hBitsL = ctx->params.cParams.hashLog;
U32 const hBitsL = ctx->appliedParams.cParams.hashLog;
U32* const hashSmall = ctx->chainTable;
U32 const hBitsS = ctx->params.cParams.chainLog;
U32 const hBitsS = ctx->appliedParams.cParams.chainLog;
seqStore_t* seqStorePtr = &(ctx->seqStore);
const BYTE* const base = ctx->base;
const BYTE* const dictBase = ctx->dictBase;
@@ -1637,7 +1966,7 @@ static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx* ctx,
static void ZSTD_compressBlock_doubleFast_extDict(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
U32 const mls = ctx->params.cParams.searchLength;
U32 const mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1663,10 +1992,10 @@ static U32 ZSTD_insertBt1(ZSTD_CCtx* zc, const BYTE* const ip, const U32 mls, co
U32 extDict)
{
U32* const hashTable = zc->hashTable;
U32 const hashLog = zc->params.cParams.hashLog;
U32 const hashLog = zc->appliedParams.cParams.hashLog;
size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const bt = zc->chainTable;
U32 const btLog = zc->params.cParams.chainLog - 1;
U32 const btLog = zc->appliedParams.cParams.chainLog - 1;
U32 const btMask = (1 << btLog) - 1;
U32 matchIndex = hashTable[h];
size_t commonLengthSmaller=0, commonLengthLarger=0;
@@ -1768,10 +2097,10 @@ static size_t ZSTD_insertBtAndFindBestMatch (
U32 extDict)
{
U32* const hashTable = zc->hashTable;
U32 const hashLog = zc->params.cParams.hashLog;
U32 const hashLog = zc->appliedParams.cParams.hashLog;
size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const bt = zc->chainTable;
U32 const btLog = zc->params.cParams.chainLog - 1;
U32 const btLog = zc->appliedParams.cParams.chainLog - 1;
U32 const btMask = (1 << btLog) - 1;
U32 matchIndex = hashTable[h];
size_t commonLengthSmaller=0, commonLengthLarger=0;
@@ -1931,9 +2260,9 @@ FORCE_INLINE
U32 ZSTD_insertAndFindFirstIndex (ZSTD_CCtx* zc, const BYTE* ip, U32 mls)
{
U32* const hashTable = zc->hashTable;
const U32 hashLog = zc->params.cParams.hashLog;
const U32 hashLog = zc->appliedParams.cParams.hashLog;
U32* const chainTable = zc->chainTable;
const U32 chainMask = (1 << zc->params.cParams.chainLog) - 1;
const U32 chainMask = (1 << zc->appliedParams.cParams.chainLog) - 1;
const BYTE* const base = zc->base;
const U32 target = (U32)(ip - base);
U32 idx = zc->nextToUpdate;
@@ -1959,7 +2288,7 @@ size_t ZSTD_HcFindBestMatch_generic (
const U32 maxNbAttempts, const U32 mls, const U32 extDict)
{
U32* const chainTable = zc->chainTable;
const U32 chainSize = (1 << zc->params.cParams.chainLog);
const U32 chainSize = (1 << zc->appliedParams.cParams.chainLog);
const U32 chainMask = chainSize-1;
const BYTE* const base = zc->base;
const BYTE* const dictBase = zc->dictBase;
@@ -2053,8 +2382,8 @@ void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx* ctx,
const BYTE* const ilimit = iend - 8;
const BYTE* const base = ctx->base + ctx->dictLimit;
U32 const maxSearches = 1 << ctx->params.cParams.searchLog;
U32 const mls = ctx->params.cParams.searchLength;
U32 const maxSearches = 1 << ctx->appliedParams.cParams.searchLog;
U32 const mls = ctx->appliedParams.cParams.searchLength;
typedef size_t (*searchMax_f)(ZSTD_CCtx* zc, const BYTE* ip, const BYTE* iLimit,
size_t* offsetPtr,
@@ -2221,8 +2550,8 @@ void ZSTD_compressBlock_lazy_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const dictEnd = dictBase + dictLimit;
const BYTE* const dictStart = dictBase + ctx->lowLimit;
const U32 maxSearches = 1 << ctx->params.cParams.searchLog;
const U32 mls = ctx->params.cParams.searchLength;
const U32 maxSearches = 1 << ctx->appliedParams.cParams.searchLog;
const U32 mls = ctx->appliedParams.cParams.searchLength;
typedef size_t (*searchMax_f)(ZSTD_CCtx* zc, const BYTE* ip, const BYTE* iLimit,
size_t* offsetPtr,
@@ -2440,26 +2769,32 @@ static void ZSTD_compressBlock_btultra_extDict(ZSTD_CCtx* ctx, const void* src,
}
/* ZSTD_selectBlockCompressor() :
* assumption : strat is a valid strategy */
typedef void (*ZSTD_blockCompressor) (ZSTD_CCtx* ctx, const void* src, size_t srcSize);
static ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, int extDict)
{
static const ZSTD_blockCompressor blockCompressor[2][8] = {
{ ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy,
static const ZSTD_blockCompressor blockCompressor[2][(unsigned)ZSTD_btultra+1] = {
{ ZSTD_compressBlock_fast /* default for 0 */,
ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy,
ZSTD_compressBlock_lazy, ZSTD_compressBlock_lazy2, ZSTD_compressBlock_btlazy2,
ZSTD_compressBlock_btopt, ZSTD_compressBlock_btultra },
{ ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict,
{ ZSTD_compressBlock_fast_extDict /* default for 0 */,
ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict,
ZSTD_compressBlock_lazy_extDict,ZSTD_compressBlock_lazy2_extDict, ZSTD_compressBlock_btlazy2_extDict,
ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btultra_extDict }
};
ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1);
assert((U32)strat >= (U32)ZSTD_fast);
assert((U32)strat <= (U32)ZSTD_btultra);
return blockCompressor[extDict][(U32)strat];
return blockCompressor[extDict!=0][(U32)strat];
}
static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->params.cParams.strategy, zc->lowLimit < zc->dictLimit);
ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->appliedParams.cParams.strategy, zc->lowLimit < zc->dictLimit);
const BYTE* const base = zc->base;
const BYTE* const istart = (const BYTE*)src;
const U32 current = (U32)(istart-base);
@@ -2472,14 +2807,14 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, void* dst, size_t dstCa
}
/*! ZSTD_compress_generic() :
/*! ZSTD_compress_frameChunk() :
* Compress a chunk of data into one or multiple blocks.
* All blocks will be terminated, all input will be consumed.
* Function will issue an error if there is not enough `dstCapacity` to hold the compressed content.
* Frame is supposed already started (header already produced)
* @return : compressed size, or an error code
*/
static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
U32 lastFrameChunk)
@@ -2489,9 +2824,9 @@ static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
const BYTE* ip = (const BYTE*)src;
BYTE* const ostart = (BYTE*)dst;
BYTE* op = ostart;
U32 const maxDist = 1 << cctx->params.cParams.windowLog;
U32 const maxDist = 1 << cctx->appliedParams.cParams.windowLog;
if (cctx->params.fParams.checksumFlag && srcSize)
if (cctx->appliedParams.fParams.checksumFlag && srcSize)
XXH64_update(&cctx->xxhState, src, srcSize);
while (remaining) {
@@ -2504,9 +2839,9 @@ static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
/* preemptive overflow correction */
if (cctx->lowLimit > (3U<<29)) {
U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->params.cParams.hashLog, cctx->params.cParams.strategy)) - 1;
U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->appliedParams.cParams.hashLog, cctx->appliedParams.cParams.strategy)) - 1;
U32 const current = (U32)(ip - cctx->base);
U32 const newCurrent = (current & cycleMask) + (1 << cctx->params.cParams.windowLog);
U32 const newCurrent = (current & cycleMask) + (1 << cctx->appliedParams.cParams.windowLog);
U32 const correction = current - newCurrent;
ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_64 <= 30);
ZSTD_reduceIndex(cctx, correction);
@@ -2566,7 +2901,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
size_t pos;
if (dstCapacity < ZSTD_frameHeaderSize_max) return ERROR(dstSize_tooSmall);
DEBUGLOG(5, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u \n",
DEBUGLOG(5, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u",
!params.fParams.noDictIDFlag, dictID, dictIDSizeCode);
MEM_writeLE32(dst, ZSTD_MAGICNUMBER);
@@ -2574,7 +2909,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
if (!singleSegment) op[pos++] = windowLogByte;
switch(dictIDSizeCode)
{
default: /* impossible */
default: assert(0); /* impossible */
case 0 : break;
case 1 : op[pos] = (BYTE)(dictID); pos++; break;
case 2 : MEM_writeLE16(op+pos, (U16)dictID); pos+=2; break;
@@ -2582,7 +2917,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
}
switch(fcsCode)
{
default: /* impossible */
default: assert(0); /* impossible */
case 0 : if (singleSegment) op[pos++] = (BYTE)(pledgedSrcSize); break;
case 1 : MEM_writeLE16(op+pos, (U16)(pledgedSrcSize-256)); pos+=2; break;
case 2 : MEM_writeLE32(op+pos, (U32)(pledgedSrcSize)); pos+=4; break;
@@ -2603,7 +2938,8 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
if (cctx->stage==ZSTDcs_created) return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */
if (frame && (cctx->stage==ZSTDcs_init)) {
fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, cctx->frameContentSize, cctx->dictID);
fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams,
cctx->pledgedSrcSizePlusOne-1, cctx->dictID);
if (ZSTD_isError(fhSize)) return fhSize;
dstCapacity -= fhSize;
dst = (char*)dst + fhSize;
@@ -2633,7 +2969,7 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
if (srcSize) {
size_t const cSize = frame ?
ZSTD_compress_generic (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize);
if (ZSTD_isError(cSize)) return cSize;
cctx->consumedSrcSize += srcSize;
@@ -2651,14 +2987,18 @@ size_t ZSTD_compressContinue (ZSTD_CCtx* cctx,
}
size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx)
size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
{
return MIN (ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << cctx->params.cParams.windowLog);
U32 const cLevel = cctx->compressionLevel;
ZSTD_compressionParameters cParams = (cLevel == ZSTD_CLEVEL_CUSTOM) ?
cctx->appliedParams.cParams :
ZSTD_getCParams(cLevel, 0, 0);
return MIN (ZSTD_BLOCKSIZE_MAX, 1 << cParams.windowLog);
}
size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
size_t const blockSizeMax = ZSTD_getBlockSizeMax(cctx);
size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
if (srcSize > blockSizeMax) return ERROR(srcSize_wrong);
return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
}
@@ -2682,32 +3022,32 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_CCtx* zc, const void* src, size_t
zc->nextSrc = iend;
if (srcSize <= HASH_READ_SIZE) return 0;
switch(zc->params.cParams.strategy)
switch(zc->appliedParams.cParams.strategy)
{
case ZSTD_fast:
ZSTD_fillHashTable (zc, iend, zc->params.cParams.searchLength);
ZSTD_fillHashTable (zc, iend, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_dfast:
ZSTD_fillDoubleHashTable (zc, iend, zc->params.cParams.searchLength);
ZSTD_fillDoubleHashTable (zc, iend, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_greedy:
case ZSTD_lazy:
case ZSTD_lazy2:
if (srcSize >= HASH_READ_SIZE)
ZSTD_insertAndFindFirstIndex(zc, iend-HASH_READ_SIZE, zc->params.cParams.searchLength);
ZSTD_insertAndFindFirstIndex(zc, iend-HASH_READ_SIZE, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_btlazy2:
case ZSTD_btopt:
case ZSTD_btultra:
if (srcSize >= HASH_READ_SIZE)
ZSTD_updateTree(zc, iend-HASH_READ_SIZE, iend, 1 << zc->params.cParams.searchLog, zc->params.cParams.searchLength);
ZSTD_updateTree(zc, iend-HASH_READ_SIZE, iend, 1 << zc->appliedParams.cParams.searchLog, zc->appliedParams.cParams.searchLength);
break;
default:
return ERROR(GENERIC); /* strategy doesn't exist; impossible */
assert(0); /* not possible : not a valid strategy id */
}
zc->nextToUpdate = (U32)(iend - zc->base);
@@ -2747,7 +3087,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx* cctx, const void* dict, size_t
BYTE scratchBuffer[1<<MAX(MLFSELog,LLFSELog)];
dictPtr += 4; /* skip magic number */
cctx->dictID = cctx->params.fParams.noDictIDFlag ? 0 : MEM_readLE32(dictPtr);
cctx->dictID = cctx->appliedParams.fParams.noDictIDFlag ? 0 : MEM_readLE32(dictPtr);
dictPtr += 4;
{ size_t const hufHeaderSize = HUF_readCTable(cctx->hufCTable, 255, dictPtr, dictEnd-dictPtr);
@@ -2818,28 +3158,56 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx* cctx, const void* dict, size_t
/** ZSTD_compress_insertDictionary() :
* @return : 0, or an error code */
static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx* cctx,
const void* dict, size_t dictSize,
ZSTD_dictMode_e dictMode)
{
DEBUGLOG(5, "ZSTD_compress_insertDictionary");
if ((dict==NULL) || (dictSize<=8)) return 0;
/* dict as pure content */
if ((MEM_readLE32(dict) != ZSTD_DICT_MAGIC) || (cctx->forceRawDict))
/* dict restricted modes */
if (dictMode==ZSTD_dm_rawContent)
return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
/* dict as zstd dictionary */
if (MEM_readLE32(dict) != ZSTD_DICT_MAGIC) {
if (dictMode == ZSTD_dm_auto) {
DEBUGLOG(5, "raw content dictionary detected");
return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
}
if (dictMode == ZSTD_dm_fullDict)
return ERROR(dictionary_wrong);
assert(0); /* impossible */
}
/* dict as full zstd dictionary */
return ZSTD_loadZstdDictionary(cctx, dict, dictSize);
}
/*! ZSTD_compressBegin_internal() :
* @return : 0, or an error code */
* @return : 0, or an error code */
static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
const void* dict, size_t dictSize,
ZSTD_parameters params, U64 pledgedSrcSize)
ZSTD_dictMode_e dictMode,
const ZSTD_CDict* cdict,
ZSTD_parameters params, U64 pledgedSrcSize,
ZSTD_buffered_policy_e zbuff)
{
ZSTD_compResetPolicy_e const crp = dictSize ? ZSTDcrp_fullReset : ZSTDcrp_continue;
DEBUGLOG(5, "ZSTD_compressBegin_internal");
DEBUGLOG(5, "dict ? %s", dict ? "dict" : cdict ? "cdict" : "none");
DEBUGLOG(5, "dictMode : %u", (U32)dictMode);
/* params are supposed to be fully validated at this point */
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
CHECK_F(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, crp));
return ZSTD_compress_insertDictionary(cctx, dict, dictSize);
assert(!((dict) && (cdict))); /* either dict or cdict, not both */
if (cdict && cdict->dictContentSize>0) {
return ZSTD_copyCCtx_internal(cctx, cdict->refContext,
params.fParams, pledgedSrcSize,
zbuff);
}
CHECK_F( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
ZSTDcrp_continue, zbuff) );
return ZSTD_compress_insertDictionary(cctx, dict, dictSize, dictMode);
}
@@ -2851,14 +3219,16 @@ size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx,
{
/* compression parameters verification and optimization */
CHECK_F(ZSTD_checkCParams(params.cParams));
return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, pledgedSrcSize);
return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
params, pledgedSrcSize, ZSTDb_not_buffered);
}
size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, 0);
return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
params, 0, ZSTDb_not_buffered);
}
@@ -2877,12 +3247,12 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
BYTE* op = ostart;
size_t fhSize = 0;
DEBUGLOG(5, "ZSTD_writeEpilogue \n");
DEBUGLOG(5, "ZSTD_writeEpilogue");
if (cctx->stage == ZSTDcs_created) return ERROR(stage_wrong); /* init missing */
/* special case : empty frame */
if (cctx->stage == ZSTDcs_init) {
fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, 0, 0);
fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, 0, 0);
if (ZSTD_isError(fhSize)) return fhSize;
dstCapacity -= fhSize;
op += fhSize;
@@ -2898,7 +3268,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
dstCapacity -= ZSTD_blockHeaderSize;
}
if (cctx->params.fParams.checksumFlag) {
if (cctx->appliedParams.fParams.checksumFlag) {
U32 const checksum = (U32) XXH64_digest(&cctx->xxhState);
if (dstCapacity<4) return ERROR(dstSize_tooSmall);
MEM_writeLE32(op, checksum);
@@ -2915,15 +3285,19 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx,
const void* src, size_t srcSize)
{
size_t endResult;
size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize,
1 /* frame mode */, 1 /* last chunk */);
size_t const cSize = ZSTD_compressContinue_internal(cctx,
dst, dstCapacity, src, srcSize,
1 /* frame mode */, 1 /* last chunk */);
if (ZSTD_isError(cSize)) return cSize;
endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize);
if (ZSTD_isError(endResult)) return endResult;
if (cctx->params.fParams.contentSizeFlag) { /* control src size */
if (cctx->frameContentSize != cctx->consumedSrcSize)
if (cctx->appliedParams.fParams.contentSizeFlag) { /* control src size */
DEBUGLOG(5, "end of frame : controlling src size");
if (cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1) {
DEBUGLOG(5, "error : pledgedSrcSize = %u, while realSrcSize = %u",
(U32)cctx->pledgedSrcSizePlusOne-1, (U32)cctx->consumedSrcSize);
return ERROR(srcSize_wrong);
}
} }
return cSize + endResult;
}
@@ -2934,7 +3308,8 @@ static size_t ZSTD_compress_internal (ZSTD_CCtx* cctx,
const void* dict,size_t dictSize,
ZSTD_parameters params)
{
CHECK_F(ZSTD_compressBegin_internal(cctx, dict, dictSize, params, srcSize));
CHECK_F( ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
params, srcSize, ZSTDb_not_buffered) );
return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
}
@@ -2966,33 +3341,30 @@ size_t ZSTD_compress(void* dst, size_t dstCapacity, const void* src, size_t srcS
size_t result;
ZSTD_CCtx ctxBody;
memset(&ctxBody, 0, sizeof(ctxBody));
memcpy(&ctxBody.customMem, &defaultCustomMem, sizeof(ZSTD_customMem));
ctxBody.customMem = ZSTD_defaultCMem;
result = ZSTD_compressCCtx(&ctxBody, dst, dstCapacity, src, srcSize, compressionLevel);
ZSTD_free(ctxBody.workSpace, defaultCustomMem); /* can't free ctxBody itself, as it's on stack; free only heap content */
ZSTD_free(ctxBody.workSpace, ZSTD_defaultCMem); /* can't free ctxBody itself, as it's on stack; free only heap content */
return result;
}
/* ===== Dictionary API ===== */
struct ZSTD_CDict_s {
void* dictBuffer;
const void* dictContent;
size_t dictContentSize;
ZSTD_CCtx* refContext;
}; /* typedef'd tp ZSTD_CDict within "zstd.h" */
/*! ZSTD_estimateCDictSize() :
* Estimate amount of memory that will be needed to create a dictionary with following arguments */
size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize)
size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize, unsigned byReference)
{
cParams = ZSTD_adjustCParams(cParams, 0, dictSize);
return sizeof(ZSTD_CDict) + dictSize + ZSTD_estimateCCtxSize(cParams);
DEBUGLOG(5, "sizeof(ZSTD_CDict) : %u", (U32)sizeof(ZSTD_CDict));
DEBUGLOG(5, "CCtx estimate : %u", (U32)ZSTD_estimateCCtxSize(cParams));
return sizeof(ZSTD_CDict) + ZSTD_estimateCCtxSize(cParams)
+ (byReference ? 0 : dictSize);
}
size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict)
{
if (cdict==NULL) return 0; /* support sizeof on NULL */
DEBUGLOG(5, "sizeof(*cdict) : %u", (U32)sizeof(*cdict));
DEBUGLOG(5, "ZSTD_sizeof_CCtx : %u", (U32)ZSTD_sizeof_CCtx(cdict->refContext));
return ZSTD_sizeof_CCtx(cdict->refContext) + (cdict->dictBuffer ? cdict->dictContentSize : 0) + sizeof(*cdict);
}
@@ -3004,13 +3376,46 @@ static ZSTD_parameters ZSTD_makeParams(ZSTD_compressionParameters cParams, ZSTD_
return params;
}
ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, unsigned byReference,
static size_t ZSTD_initCDict_internal(
ZSTD_CDict* cdict,
const void* dictBuffer, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams)
{
DEBUGLOG(5, "ZSTD_initCDict_internal, mode %u", (U32)dictMode);
if ((byReference) || (!dictBuffer) || (!dictSize)) {
cdict->dictBuffer = NULL;
cdict->dictContent = dictBuffer;
} else {
void* const internalBuffer = ZSTD_malloc(dictSize, cdict->refContext->customMem);
cdict->dictBuffer = internalBuffer;
cdict->dictContent = internalBuffer;
if (!internalBuffer) return ERROR(memory_allocation);
memcpy(internalBuffer, dictBuffer, dictSize);
}
cdict->dictContentSize = dictSize;
{ ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */,
0 /* checksumFlag */, 0 /* noDictIDFlag */ }; /* dummy */
ZSTD_parameters const params = ZSTD_makeParams(cParams, fParams);
CHECK_F( ZSTD_compressBegin_internal(cdict->refContext,
cdict->dictContent, dictSize, dictMode,
NULL,
params, ZSTD_CONTENTSIZE_UNKNOWN,
ZSTDb_not_buffered) );
}
return 0;
}
ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams, ZSTD_customMem customMem)
{
if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
if (!customMem.customAlloc || !customMem.customFree) return NULL;
DEBUGLOG(5, "ZSTD_createCDict_advanced, mode %u", (U32)dictMode);
if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
{ ZSTD_CDict* const cdict = (ZSTD_CDict*) ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
{ ZSTD_CDict* const cdict = (ZSTD_CDict*)ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
ZSTD_CCtx* const cctx = ZSTD_createCCtx_advanced(customMem);
if (!cdict || !cctx) {
@@ -3018,46 +3423,34 @@ ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, u
ZSTD_freeCCtx(cctx);
return NULL;
}
cdict->refContext = cctx;
if ((byReference) || (!dictBuffer) || (!dictSize)) {
cdict->dictBuffer = NULL;
cdict->dictContent = dictBuffer;
} else {
void* const internalBuffer = ZSTD_malloc(dictSize, customMem);
if (!internalBuffer) { ZSTD_free(cctx, customMem); ZSTD_free(cdict, customMem); return NULL; }
memcpy(internalBuffer, dictBuffer, dictSize);
cdict->dictBuffer = internalBuffer;
cdict->dictContent = internalBuffer;
if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
dictBuffer, dictSize,
byReference, dictMode,
cParams) )) {
ZSTD_freeCDict(cdict);
return NULL;
}
{ ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */, 0 /* checksumFlag */, 0 /* noDictIDFlag */ }; /* dummy */
ZSTD_parameters const params = ZSTD_makeParams(cParams, fParams);
size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0);
if (ZSTD_isError(errorCode)) {
ZSTD_free(cdict->dictBuffer, customMem);
ZSTD_free(cdict, customMem);
ZSTD_freeCCtx(cctx);
return NULL;
} }
cdict->refContext = cctx;
cdict->dictContentSize = dictSize;
return cdict;
}
}
ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_customMem const allocator = { NULL, NULL, NULL };
ZSTD_compressionParameters cParams = ZSTD_getCParams(compressionLevel, 0, dictSize);
return ZSTD_createCDict_advanced(dict, dictSize, 0, cParams, allocator);
return ZSTD_createCDict_advanced(dict, dictSize,
0 /* byReference */, ZSTD_dm_auto,
cParams, ZSTD_defaultCMem);
}
ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_customMem const allocator = { NULL, NULL, NULL };
ZSTD_compressionParameters cParams = ZSTD_getCParams(compressionLevel, 0, dictSize);
return ZSTD_createCDict_advanced(dict, dictSize, 1, cParams, allocator);
return ZSTD_createCDict_advanced(dict, dictSize,
1 /* byReference */, ZSTD_dm_auto,
cParams, ZSTD_defaultCMem);
}
size_t ZSTD_freeCDict(ZSTD_CDict* cdict)
@@ -3071,7 +3464,54 @@ size_t ZSTD_freeCDict(ZSTD_CDict* cdict)
}
}
static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict) {
/*! ZSTD_initStaticCDict_advanced() :
* Generate a digested dictionary in provided memory area.
* workspace: The memory area to emplace the dictionary into.
* Provided pointer must 8-bytes aligned.
* It must outlive dictionary usage.
* workspaceSize: Use ZSTD_estimateCDictSize()
* to determine how large workspace must be.
* cParams : use ZSTD_getCParams() to transform a compression level
* into its relevants cParams.
* @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
* Note : there is no corresponding "free" function.
* Since workspace was allocated externally, it must be freed externally.
*/
ZSTD_CDict* ZSTD_initStaticCDict(void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams)
{
size_t const cctxSize = ZSTD_estimateCCtxSize(cParams);
size_t const neededSize = sizeof(ZSTD_CDict) + (byReference ? 0 : dictSize)
+ cctxSize;
ZSTD_CDict* const cdict = (ZSTD_CDict*) workspace;
void* ptr;
DEBUGLOG(5, "(size_t)workspace & 7 : %u", (U32)(size_t)workspace & 7);
if ((size_t)workspace & 7) return NULL; /* 8-aligned */
DEBUGLOG(5, "(workspaceSize < neededSize) : (%u < %u) => %u",
(U32)workspaceSize, (U32)neededSize, (U32)(workspaceSize < neededSize));
if (workspaceSize < neededSize) return NULL;
if (!byReference) {
memcpy(cdict+1, dict, dictSize);
dict = cdict+1;
ptr = (char*)workspace + sizeof(ZSTD_CDict) + dictSize;
} else {
ptr = cdict+1;
}
cdict->refContext = ZSTD_initStaticCCtx(ptr, cctxSize);
if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
dict, dictSize,
1 /* byReference */, dictMode,
cParams) ))
return NULL;
return cdict;
}
ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict) {
return ZSTD_getParamsFromCCtx(cdict->refContext);
}
@@ -3081,16 +3521,16 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict,
ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
{
if (cdict==NULL) return ERROR(GENERIC); /* does not support NULL cdict */
DEBUGLOG(5, "ZSTD_compressBegin_usingCDict_advanced : dictIDFlag == %u \n", !fParams.noDictIDFlag);
if (cdict->dictContentSize)
CHECK_F( ZSTD_copyCCtx_internal(cctx, cdict->refContext, fParams, pledgedSrcSize) )
else {
ZSTD_parameters params = cdict->refContext->params;
if (cdict==NULL) return ERROR(dictionary_wrong);
{ ZSTD_parameters params = cdict->refContext->appliedParams;
params.fParams = fParams;
CHECK_F(ZSTD_compressBegin_internal(cctx, NULL, 0, params, pledgedSrcSize));
DEBUGLOG(5, "ZSTD_compressBegin_usingCDict_advanced");
return ZSTD_compressBegin_internal(cctx,
NULL, 0, ZSTD_dm_auto,
cdict,
params, pledgedSrcSize,
ZSTDb_not_buffered);
}
return 0;
}
/* ZSTD_compressBegin_usingCDict() :
@@ -3099,7 +3539,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
{
ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
DEBUGLOG(5, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u \n", !fParams.noDictIDFlag);
DEBUGLOG(5, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u", !fParams.noDictIDFlag);
return ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, 0);
}
@@ -3134,12 +3574,11 @@ size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
ZSTD_CStream* ZSTD_createCStream(void)
{
return ZSTD_createCStream_advanced(defaultCustomMem);
return ZSTD_createCStream_advanced(ZSTD_defaultCMem);
}
ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem)
{
/* CStream and CCtx are now same object */
{ /* CStream and CCtx are now same object */
return ZSTD_createCCtx_advanced(customMem);
}
@@ -3148,35 +3587,28 @@ size_t ZSTD_freeCStream(ZSTD_CStream* zcs)
return ZSTD_freeCCtx(zcs); /* same object */
}
size_t ZSTD_estimateCStreamSize(ZSTD_compressionParameters cParams)
{
size_t const CCtxSize = ZSTD_estimateCCtxSize(cParams);
size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (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;
return CCtxSize + streamingSize;
}
/*====== Initialization ======*/
size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX; }
size_t ZSTD_CStreamOutSize(void)
{
return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ;
return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ;
}
static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs, ZSTD_parameters params, unsigned long long pledgedSrcSize)
static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs,
ZSTD_parameters params,
unsigned long long pledgedSrcSize)
{
if (zcs->inBuffSize==0) return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */
DEBUGLOG(5, "ZSTD_resetCStream_internal");
DEBUGLOG(5, "ZSTD_resetCStream_internal : dictIDFlag == %u \n", !zcs->params.fParams.noDictIDFlag);
if (zcs->cdict) CHECK_F(ZSTD_compressBegin_usingCDict_advanced(zcs, zcs->cdict, params.fParams, pledgedSrcSize))
else CHECK_F(ZSTD_compressBegin_internal(zcs, NULL, 0, params, pledgedSrcSize));
CHECK_F( ZSTD_compressBegin_internal(zcs,
NULL, 0, ZSTD_dm_auto,
zcs->cdict,
params, pledgedSrcSize,
ZSTDb_buffered) );
zcs->inToCompress = 0;
zcs->inBuffPos = 0;
@@ -3184,87 +3616,79 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs, ZSTD_parameters para
zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
zcs->streamStage = zcss_load;
zcs->frameEnded = 0;
zcs->pledgedSrcSize = pledgedSrcSize;
return 0; /* ready to go */
}
size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
{
ZSTD_parameters params = zcs->params;
ZSTD_parameters params = zcs->requestedParams;
params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
DEBUGLOG(5, "ZSTD_resetCStream : dictIDFlag == %u \n", !zcs->params.fParams.noDictIDFlag);
DEBUGLOG(5, "ZSTD_resetCStream");
if (zcs->compressionLevel != ZSTD_CLEVEL_CUSTOM) {
params.cParams = ZSTD_getCParams(zcs->compressionLevel, pledgedSrcSize, 0 /* dictSize */);
}
return ZSTD_resetCStream_internal(zcs, params, pledgedSrcSize);
}
/* ZSTD_initCStream_internal() :
* params are supposed validated at this stage
* and zcs->cdict is supposed to be correct */
static size_t ZSTD_initCStream_stage2(ZSTD_CStream* zcs,
const ZSTD_parameters params,
unsigned long long pledgedSrcSize)
/*! ZSTD_initCStream_internal() :
* Assumption 1 : params are valid
* Assumption 2 : either dict, or cdict, is defined, not both */
size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
DEBUGLOG(5, "ZSTD_initCStream_internal");
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
zcs->blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog);
assert(!((dict) && (cdict))); /* either dict or cdict, not both */
/* allocate buffers */
{ size_t const neededInBuffSize = ((size_t)1 << params.cParams.windowLog) + zcs->blockSize;
if (zcs->inBuffSize < neededInBuffSize) {
zcs->inBuffSize = 0;
ZSTD_free(zcs->inBuff, zcs->customMem);
zcs->inBuff = (char*)ZSTD_malloc(neededInBuffSize, zcs->customMem);
if (zcs->inBuff == NULL) return ERROR(memory_allocation);
zcs->inBuffSize = neededInBuffSize;
if (dict && dictSize >= 8) {
DEBUGLOG(5, "loading dictionary of size %u", (U32)dictSize);
if (zcs->staticSize) { /* static CCtx : never uses malloc */
/* incompatible with internal cdict creation */
return ERROR(memory_allocation);
}
}
if (zcs->outBuffSize < ZSTD_compressBound(zcs->blockSize)+1) {
size_t const outBuffSize = ZSTD_compressBound(zcs->blockSize)+1;
zcs->outBuffSize = 0;
ZSTD_free(zcs->outBuff, zcs->customMem);
zcs->outBuff = (char*)ZSTD_malloc(outBuffSize, zcs->customMem);
if (zcs->outBuff == NULL) return ERROR(memory_allocation);
zcs->outBuffSize = outBuffSize;
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
0 /* byReference */, ZSTD_dm_auto,
params.cParams, zcs->customMem);
zcs->cdict = zcs->cdictLocal;
if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
} else {
if (cdict) {
ZSTD_parameters const cdictParams = ZSTD_getParamsFromCDict(cdict);
params.cParams = cdictParams.cParams; /* cParams are enforced from cdict */
}
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = NULL;
zcs->cdict = cdict;
}
DEBUGLOG(5, "ZSTD_initCStream_stage2 : dictIDFlag == %u \n", !params.fParams.noDictIDFlag);
zcs->requestedParams = params;
zcs->compressionLevel = ZSTD_CLEVEL_CUSTOM;
return ZSTD_resetCStream_internal(zcs, params, pledgedSrcSize);
}
/* ZSTD_initCStream_usingCDict_advanced() :
* same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams)
{
if (!cdict) return ERROR(GENERIC); /* cannot handle NULL cdict (does not know what to do) */
size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
const ZSTD_CDict* cdict,
ZSTD_frameParameters fParams,
unsigned long long pledgedSrcSize)
{ /* cannot handle NULL cdict (does not know what to do) */
if (!cdict) return ERROR(dictionary_wrong);
{ ZSTD_parameters params = ZSTD_getParamsFromCDict(cdict);
params.fParams = fParams;
zcs->cdict = cdict;
return ZSTD_initCStream_stage2(zcs, params, pledgedSrcSize);
return ZSTD_initCStream_internal(zcs,
NULL, 0, cdict,
params, pledgedSrcSize);
}
}
/* note : cdict must outlive compression session */
size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
{
ZSTD_frameParameters const fParams = { 0 /* content */, 0 /* checksum */, 0 /* noDictID */ };
return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, 0, fParams);
}
static size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
zcs->cdict = NULL;
if (dict && dictSize >= 8) {
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0 /* copy */, params.cParams, zcs->customMem);
if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
zcs->cdict = zcs->cdictLocal;
}
DEBUGLOG(5, "ZSTD_initCStream_internal : dictIDFlag == %u \n", !params.fParams.noDictIDFlag);
return ZSTD_initCStream_stage2(zcs, params, pledgedSrcSize);
ZSTD_frameParameters const fParams = { 0 /* contentSize */, 0 /* checksum */, 0 /* hideDictID */ };
return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, fParams, 0); /* note : will check that cdict != NULL */
}
size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
@@ -3272,127 +3696,161 @@ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
CHECK_F( ZSTD_checkCParams(params.cParams) );
DEBUGLOG(5, "ZSTD_initCStream_advanced : pledgedSrcSize == %u \n", (U32)pledgedSrcSize);
DEBUGLOG(5, "wlog %u \n", params.cParams.windowLog);
return ZSTD_initCStream_internal(zcs, dict, dictSize, params, pledgedSrcSize);
zcs->requestedParams = params;
zcs->compressionLevel = ZSTD_CLEVEL_CUSTOM;
return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, params, pledgedSrcSize);
}
size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
return ZSTD_initCStream_internal(zcs, dict, dictSize, params, 0);
zcs->compressionLevel = compressionLevel;
return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, params, 0);
}
size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize)
{
ZSTD_parameters params = ZSTD_getParams(compressionLevel, pledgedSrcSize, 0);
params.fParams.contentSizeFlag = (pledgedSrcSize>0);
return ZSTD_initCStream_internal(zcs, NULL, 0, params, pledgedSrcSize);
return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, params, pledgedSrcSize);
}
size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0);
return ZSTD_initCStream_internal(zcs, NULL, 0, params, 0);
}
size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs)
{
return ZSTD_sizeof_CCtx(zcs); /* same object */
return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, params, 0);
}
/*====== Compression ======*/
typedef enum { zsf_gather, zsf_flush, zsf_end } ZSTD_flush_e;
MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity,
const void* src, size_t srcSize)
{
size_t const length = MIN(dstCapacity, srcSize);
memcpy(dst, src, length);
if (length) memcpy(dst, src, length);
return length;
}
static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
void* dst, size_t* dstCapacityPtr,
const void* src, size_t* srcSizePtr,
ZSTD_flush_e const flush)
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;
const char* ip = istart + input->pos;
char* const ostart = (char*)output->dst;
char* const oend = ostart + output->size;
char* op = ostart + output->pos;
U32 someMoreWork = 1;
const char* const istart = (const char*)src;
const char* const iend = istart + *srcSizePtr;
const char* ip = istart;
char* const ostart = (char*)dst;
char* const oend = ostart + *dstCapacityPtr;
char* op = ostart;
DEBUGLOG(5, "ZSTD_compressStream_generic \n");
/* check expectations */
DEBUGLOG(5, "ZSTD_compressStream_generic");
assert(zcs->inBuff != NULL);
assert(zcs->inBuffSize>0);
assert(zcs->outBuff!= NULL);
assert(zcs->outBuffSize>0);
assert(output->pos <= output->size);
assert(input->pos <= input->size);
while (someMoreWork) {
switch(zcs->streamStage)
{
case zcss_init: return ERROR(init_missing); /* call ZBUFF_compressInit() first ! */
case zcss_init:
/* call ZSTD_initCStream() first ! */
return ERROR(init_missing);
case zcss_load:
/* complete inBuffer */
{ size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos;
size_t const loaded = ZSTD_limitCopy(zcs->inBuff + zcs->inBuffPos, toLoad, ip, iend-ip);
DEBUGLOG(5, "loading %u/%u \n", (U32)loaded, (U32)toLoad);
size_t const loaded = ZSTD_limitCopy(
zcs->inBuff + zcs->inBuffPos, toLoad,
ip, iend-ip);
zcs->inBuffPos += loaded;
ip += loaded;
if ( (zcs->inBuffPos==zcs->inToCompress) || (!flush && (toLoad != loaded)) ) {
someMoreWork = 0; break; /* not enough input to get a full block : stop there, wait for more */
} }
if ( (flushMode == ZSTD_e_continue)
&& (zcs->inBuffPos < zcs->inBuffTarget) ) {
/* not enough input to fill full block : stop here */
someMoreWork = 0; break;
}
if ( (flushMode == ZSTD_e_flush)
&& (zcs->inBuffPos == zcs->inToCompress) ) {
/* empty */
someMoreWork = 0; break;
}
}
/* compress current block (note : this stage cannot be stopped in the middle) */
DEBUGLOG(5, "stream compression stage (flush==%u)\n", flush);
DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode);
{ void* cDst;
size_t cSize;
size_t const iSize = zcs->inBuffPos - zcs->inToCompress;
size_t oSize = oend-op;
unsigned const lastBlock = (flushMode == ZSTD_e_end) && (ip==iend);
if (oSize >= ZSTD_compressBound(iSize))
cDst = op; /* compress directly into output buffer (avoid flush stage) */
cDst = op; /* compress into output buffer, to skip flush stage */
else
cDst = zcs->outBuff, oSize = zcs->outBuffSize;
cSize = (flush == zsf_end) ?
ZSTD_compressEnd(zcs, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize) :
ZSTD_compressContinue(zcs, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize);
cSize = lastBlock ?
ZSTD_compressEnd(zcs, cDst, oSize,
zcs->inBuff + zcs->inToCompress, iSize) :
ZSTD_compressContinue(zcs, cDst, oSize,
zcs->inBuff + zcs->inToCompress, iSize);
if (ZSTD_isError(cSize)) return cSize;
DEBUGLOG(5, "cSize = %u \n", (U32)cSize);
if (flush == zsf_end) zcs->frameEnded = 1;
zcs->frameEnded = lastBlock;
/* prepare next block */
zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
if (zcs->inBuffTarget > zcs->inBuffSize)
zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; /* note : inBuffTarget == blockSize <= inBuffSize */
assert(zcs->inBuffTarget <= zcs->inBuffSize);
zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize;
DEBUGLOG(5, "inBuffTarget:%u / inBuffSize:%u",
(U32)zcs->inBuffTarget, (U32)zcs->inBuffSize);
if (!lastBlock)
assert(zcs->inBuffTarget <= zcs->inBuffSize);
zcs->inToCompress = zcs->inBuffPos;
if (cDst == op) { op += cSize; break; } /* no need to flush */
if (cDst == op) { /* no need to flush */
op += cSize;
if (zcs->frameEnded) {
DEBUGLOG(5, "Frame completed directly in outBuffer");
someMoreWork = 0;
ZSTD_startNewCompression(zcs);
}
break;
}
zcs->outBuffContentSize = cSize;
zcs->outBuffFlushedSize = 0;
zcs->streamStage = zcss_flush; /* pass-through to flush stage */
zcs->streamStage = zcss_flush; /* pass-through to flush stage */
}
/* fall-through */
case zcss_flush:
DEBUGLOG(5, "flush stage \n");
DEBUGLOG(5, "flush stage");
{ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
size_t const flushed = ZSTD_limitCopy(op, oend-op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
DEBUGLOG(5, "toFlush: %u ; flushed: %u \n", (U32)toFlush, (U32)flushed);
size_t const flushed = ZSTD_limitCopy(op, oend-op,
zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
DEBUGLOG(5, "toFlush: %u ; flushed: %u", (U32)toFlush, (U32)flushed);
op += flushed;
zcs->outBuffFlushedSize += flushed;
if (toFlush!=flushed) { someMoreWork = 0; break; } /* dst too small to store flushed data : stop there */
if (toFlush!=flushed) {
/* dst too small to store flushed data : stop there */
someMoreWork = 0;
break;
}
zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
if (zcs->frameEnded) {
DEBUGLOG(5, "Frame completed on flush");
someMoreWork = 0;
ZSTD_startNewCompression(zcs);
break;
}
zcs->streamStage = zcss_load;
break;
}
case zcss_final:
someMoreWork = 0; /* do nothing */
break;
default:
return ERROR(GENERIC); /* impossible */
default: /* impossible */
assert(0);
}
}
*srcSizePtr = ip - istart;
*dstCapacityPtr = op - ostart;
input->pos = ip - istart;
output->pos = op - ostart;
if (zcs->frameEnded) return 0;
{ size_t hintInSize = zcs->inBuffTarget - zcs->inBuffPos;
if (hintInSize==0) hintInSize = zcs->blockSize;
@@ -3402,14 +3860,82 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
{
size_t sizeRead = input->size - input->pos;
size_t sizeWritten = output->size - output->pos;
size_t const result = ZSTD_compressStream_generic(zcs,
(char*)(output->dst) + output->pos, &sizeWritten,
(const char*)(input->src) + input->pos, &sizeRead, zsf_gather);
input->pos += sizeRead;
output->pos += sizeWritten;
return result;
/* check conditions */
if (output->pos > output->size) return ERROR(GENERIC);
if (input->pos > input->size) return ERROR(GENERIC);
return ZSTD_compressStream_generic(zcs, output, input, ZSTD_e_continue);
}
/*! ZSTDMT_initCStream_internal() :
* Private use only. Init streaming operation.
* expects params to be valid.
* must receive dict, or cdict, or none, but not both.
* @return : 0, or an error code */
size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
ZSTD_parameters params, unsigned long long pledgedSrcSize);
size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
ZSTD_outBuffer* output,
ZSTD_inBuffer* input,
ZSTD_EndDirective endOp)
{
/* check conditions */
if (output->pos > output->size) return ERROR(GENERIC);
if (input->pos > input->size) return ERROR(GENERIC);
assert(cctx!=NULL);
if (cctx->streamStage == zcss_init) {
/* transparent reset */
ZSTD_parameters params = cctx->requestedParams;
if (cctx->compressionLevel != ZSTD_CLEVEL_CUSTOM)
params.cParams = ZSTD_getCParams(cctx->compressionLevel,
cctx->pledgedSrcSizePlusOne-1, 0 /* dictSize */);
#ifdef ZSTD_MULTITHREAD
if (cctx->nbThreads > 1) {
DEBUGLOG(4, "call ZSTDMT_initCStream_internal");
CHECK_F( ZSTDMT_initCStream_internal(cctx->mtctx, NULL, 0, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
cctx->streamStage = zcss_load;
} else
#endif
{
CHECK_F( ZSTD_resetCStream_internal(cctx, params, cctx->pledgedSrcSizePlusOne-1) );
} }
#ifdef ZSTD_MULTITHREAD
if (cctx->nbThreads > 1) {
size_t const flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
DEBUGLOG(4, "ZSTDMT_compressStream_generic : %u", (U32)flushMin);
if ( ZSTD_isError(flushMin)
|| (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */
ZSTD_startNewCompression(cctx);
}
return flushMin;
}
#endif
DEBUGLOG(5, "calling ZSTD_compressStream_generic(%i,...)", endOp);
CHECK_F( ZSTD_compressStream_generic(cctx, output, input, endOp) );
DEBUGLOG(5, "completed ZSTD_compress_generic");
return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */
}
size_t ZSTD_compress_generic_simpleArgs (
ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity, size_t* dstPos,
const void* src, size_t srcSize, size_t* srcPos,
ZSTD_EndDirective endOp)
{
ZSTD_outBuffer output = { dst, dstCapacity, *dstPos };
ZSTD_inBuffer input = { src, srcSize, *srcPos };
/* ZSTD_compress_generic() will check validity of dstPos and srcPos */
size_t const cErr = ZSTD_compress_generic(cctx, &output, &input, endOp);
*dstPos = output.pos;
*srcPos = input.pos;
return cErr;
}
@@ -3419,62 +3945,27 @@ size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuf
* @return : amount of data remaining to flush */
size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
{
size_t srcSize = 0;
size_t sizeWritten = output->size - output->pos;
size_t const result = ZSTD_compressStream_generic(zcs,
(char*)(output->dst) + output->pos, &sizeWritten,
&srcSize, &srcSize, /* use a valid src address instead of NULL */
zsf_flush);
output->pos += sizeWritten;
if (ZSTD_isError(result)) return result;
return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
ZSTD_inBuffer input = { NULL, 0, 0 };
if (output->pos > output->size) return ERROR(GENERIC);
CHECK_F( ZSTD_compressStream_generic(zcs, output, &input, ZSTD_e_flush) );
return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
}
size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
{
BYTE* const ostart = (BYTE*)(output->dst) + output->pos;
BYTE* const oend = (BYTE*)(output->dst) + output->size;
BYTE* op = ostart;
ZSTD_inBuffer input = { NULL, 0, 0 };
if (output->pos > output->size) return ERROR(GENERIC);
CHECK_F( ZSTD_compressStream_generic(zcs, output, &input, ZSTD_e_end) );
DEBUGLOG(5, "ZSTD_endStream (dstCapacity : %u) \n", (U32)(oend-op));
if (zcs->streamStage != zcss_final) {
/* flush whatever remains */
size_t srcSize = 0;
size_t sizeWritten = output->size - output->pos;
size_t const notEnded = ZSTD_compressStream_generic(zcs, ostart, &sizeWritten,
&srcSize /* use a valid src address instead of NULL */, &srcSize, zsf_end);
size_t const remainingToFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
op += sizeWritten;
if (remainingToFlush) {
output->pos += sizeWritten;
return remainingToFlush + ZSTD_BLOCKHEADERSIZE /* final empty block */
+ ((zcs->params.fParams.checksumFlag > 0) * 4) /* optional 32-bits checksum */;
}
/* create epilogue */
zcs->streamStage = zcss_final;
zcs->outBuffContentSize = !notEnded ? 0 :
/* write epilogue, including final empty block, into outBuff */
ZSTD_compressEnd(zcs, zcs->outBuff, zcs->outBuffSize, NULL, 0);
if (ZSTD_isError(zcs->outBuffContentSize)) return zcs->outBuffContentSize;
}
/* flush epilogue */
{ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
size_t const flushed = ZSTD_limitCopy(op, oend-op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
op += flushed;
zcs->outBuffFlushedSize += flushed;
output->pos += op-ostart;
if (toFlush==flushed) zcs->streamStage = zcss_init; /* end reached */
return toFlush - flushed;
}
DEBUGLOG(5, "ZSTD_endStream : remaining to flush : %u",
(unsigned)(zcs->outBuffContentSize - zcs->outBuffFlushedSize));
return zcs->outBuffContentSize - zcs->outBuffFlushedSize;
}
/*-===== Pre-defined compression levels =====-*/
#define ZSTD_DEFAULT_CLEVEL 1
#define ZSTD_MAX_CLEVEL 22
int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
@@ -3588,30 +4079,23 @@ 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 */
ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize)
{
ZSTD_compressionParameters cp;
size_t const addedSize = srcSize ? 0 : 500;
U64 const rSize = srcSize+dictSize ? srcSize+dictSize+addedSize : (U64)-1;
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 */
if (compressionLevel <= 0) compressionLevel = ZSTD_DEFAULT_CLEVEL; /* 0 == default; no negative compressionLevel yet */
if (compressionLevel <= 0) compressionLevel = ZSTD_CLEVEL_DEFAULT; /* 0 == default; no negative compressionLevel yet */
if (compressionLevel > ZSTD_MAX_CLEVEL) compressionLevel = ZSTD_MAX_CLEVEL;
cp = ZSTD_defaultCParameters[tableID][compressionLevel];
if (MEM_32bits()) { /* auto-correction, for 32-bits mode */
if (cp.windowLog > ZSTD_WINDOWLOG_MAX) cp.windowLog = ZSTD_WINDOWLOG_MAX;
if (cp.chainLog > ZSTD_CHAINLOG_MAX) cp.chainLog = ZSTD_CHAINLOG_MAX;
if (cp.hashLog > ZSTD_HASHLOG_MAX) cp.hashLog = ZSTD_HASHLOG_MAX;
}
cp = ZSTD_adjustCParams(cp, srcSize, dictSize);
return cp;
{ ZSTD_compressionParameters const cp = ZSTD_defaultCParameters[tableID][compressionLevel];
return ZSTD_adjustCParams_internal(cp, srcSizeHint, 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) */
ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize) {
ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) {
ZSTD_parameters params;
ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSize, dictSize);
ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSizeHint, dictSize);
memset(&params, 0, sizeof(params));
params.cParams = cParams;
return params;
lib/compress/zstd_opt.h
+30 -15
View File
@@ -43,6 +43,7 @@ MEM_STATIC void ZSTD_rescaleFreqs(seqStore_t* ssPtr, const BYTE* src, size_t src
if (ssPtr->litLengthSum == 0) {
if (srcSize <= 1024) ssPtr->staticPrices = 1;
assert(ssPtr->litFreq!=NULL);
for (u=0; u<=MaxLit; u++)
ssPtr->litFreq[u] = 0;
for (u=0; u<srcSize; u++)
@@ -201,6 +202,20 @@ MEM_STATIC void ZSTD_updatePrice(seqStore_t* seqStorePtr, U32 litLength, const B
}
/* function safe only for comparisons */
MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
{
switch (length)
{
default :
case 4 : return MEM_read32(memPtr);
case 3 : if (MEM_isLittleEndian())
return MEM_read32(memPtr)<<8;
else
return MEM_read32(memPtr)>>8;
}
}
/* Update hashTable3 up to ip (excluded)
Assumption : always within prefix (i.e. not within extDict) */
@@ -234,12 +249,12 @@ static U32 ZSTD_insertBtAndGetAllMatches (
{
const BYTE* const base = zc->base;
const U32 current = (U32)(ip-base);
const U32 hashLog = zc->params.cParams.hashLog;
const U32 hashLog = zc->appliedParams.cParams.hashLog;
const size_t h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const hashTable = zc->hashTable;
U32 matchIndex = hashTable[h];
U32* const bt = zc->chainTable;
const U32 btLog = zc->params.cParams.chainLog - 1;
const U32 btLog = zc->appliedParams.cParams.chainLog - 1;
const U32 btMask= (1U << btLog) - 1;
size_t commonLengthSmaller=0, commonLengthLarger=0;
const BYTE* const dictBase = zc->dictBase;
@@ -267,7 +282,7 @@ static U32 ZSTD_insertBtAndGetAllMatches (
if (match[bestLength] == ip[bestLength]) currentMl = ZSTD_count(ip, match, iLimit);
} else {
match = dictBase + matchIndex3;
if (MEM_readMINMATCH(match, MINMATCH) == MEM_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
if (ZSTD_readMINMATCH(match, MINMATCH) == ZSTD_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
currentMl = ZSTD_count_2segments(ip+MINMATCH, match+MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH;
}
@@ -410,10 +425,10 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
const BYTE* const base = ctx->base;
const BYTE* const prefixStart = base + ctx->dictLimit;
const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
const U32 sufficient_len = ctx->params.cParams.targetLength;
const U32 mls = ctx->params.cParams.searchLength;
const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
const U32 mls = ctx->appliedParams.cParams.searchLength;
const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
ZSTD_optimal_t* opt = seqStorePtr->priceTable;
ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -439,7 +454,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
for (i=(ip == anchor); i<last_i; i++) {
const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
if ( (repCur > 0) && (repCur < (S32)(ip-prefixStart))
&& (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(ip - repCur, minMatch))) {
&& (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) {
mlen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repCur, iend) + minMatch;
if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
best_mlen = mlen; best_off = i; cur = 0; last_pos = 1;
@@ -524,7 +539,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
for (i=(opt[cur].mlen != 1); i<last_i; i++) { /* check rep */
const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
if ( (repCur > 0) && (repCur < (S32)(inr-prefixStart))
&& (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(inr - repCur, minMatch))) {
&& (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) {
mlen = (U32)ZSTD_count(inr+minMatch, inr+minMatch - repCur, iend) + minMatch;
if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
@@ -663,10 +678,10 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const dictBase = ctx->dictBase;
const BYTE* const dictEnd = dictBase + dictLimit;
const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
const U32 sufficient_len = ctx->params.cParams.targetLength;
const U32 mls = ctx->params.cParams.searchLength;
const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
const U32 mls = ctx->appliedParams.cParams.searchLength;
const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
ZSTD_optimal_t* opt = seqStorePtr->priceTable;
ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -698,7 +713,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const repMatch = repBase + repIndex;
if ( (repCur > 0 && repCur <= (S32)current)
&& (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex)) /* intentional overflow */
&& (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
&& (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
/* repcode detected we should take it */
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
mlen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;
@@ -794,7 +809,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const repMatch = repBase + repIndex;
if ( (repCur > 0 && repCur <= (S32)(current+cur))
&& (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex)) /* intentional overflow */
&& (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
&& (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
/* repcode detected */
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
mlen = (U32)ZSTD_count_2segments(inr+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;
lib/compress/zstdmt_compress.c
+270 -129
View File
@@ -14,34 +14,31 @@
/* ====== Compiler specifics ====== */
#if defined(_MSC_VER)
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
#endif
/* ====== Dependencies ====== */
#include <stdlib.h> /* malloc */
#include <string.h> /* memcpy */
#include "pool.h" /* threadpool */
#include "threading.h" /* mutex */
#include "zstd_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
#include <string.h> /* memcpy, memset */
#include "pool.h" /* threadpool */
#include "threading.h" /* mutex */
#include "zstd_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
#include "zstdmt_compress.h"
/* ====== Debug ====== */
#if 0
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
# include <stdio.h>
# include <unistd.h>
# include <sys/times.h>
static unsigned g_debugLevel = 5;
# define DEBUGLOGRAW(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __VA_ARGS__); }
# define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); }
# define DEBUGLOGRAW(l, ...) if (l<=ZSTD_DEBUG) { fprintf(stderr, __VA_ARGS__); }
# define DEBUG_PRINTHEX(l,p,n) { \
unsigned debug_u; \
for (debug_u=0; debug_u<(n); debug_u++) \
# define DEBUG_PRINTHEX(l,p,n) { \
unsigned debug_u; \
for (debug_u=0; debug_u<(n); debug_u++) \
DEBUGLOGRAW(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \
DEBUGLOGRAW(l, " \n"); \
DEBUGLOGRAW(l, " \n"); \
}
static unsigned long long GetCurrentClockTimeMicroseconds(void)
@@ -54,21 +51,21 @@ static unsigned long long GetCurrentClockTimeMicroseconds(void)
}
#define MUTEX_WAIT_TIME_DLEVEL 5
#define PTHREAD_MUTEX_LOCK(mutex) \
if (g_debugLevel>=MUTEX_WAIT_TIME_DLEVEL) { \
unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
pthread_mutex_lock(mutex); \
{ unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
unsigned long long const elapsedTime = (afterTime-beforeTime); \
if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \
DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
elapsedTime, #mutex); \
} } \
} else pthread_mutex_lock(mutex);
#define PTHREAD_MUTEX_LOCK(mutex) { \
if (ZSTD_DEBUG>=MUTEX_WAIT_TIME_DLEVEL) { \
unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
pthread_mutex_lock(mutex); \
{ unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
unsigned long long const elapsedTime = (afterTime-beforeTime); \
if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \
DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
elapsedTime, #mutex); \
} } \
} else pthread_mutex_lock(mutex); \
}
#else
# define DEBUGLOG(l, ...) {} /* disabled */
# define PTHREAD_MUTEX_LOCK(m) pthread_mutex_lock(m)
# define DEBUG_PRINTHEX(l,p,n) {}
@@ -87,16 +84,19 @@ static const buffer_t g_nullBuffer = { NULL, 0 };
typedef struct ZSTDMT_bufferPool_s {
unsigned totalBuffers;
unsigned nbBuffers;
ZSTD_customMem cMem;
buffer_t bTable[1]; /* variable size */
} ZSTDMT_bufferPool;
static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads)
static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads, ZSTD_customMem cMem)
{
unsigned const maxNbBuffers = 2*nbThreads + 2;
ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)calloc(1, sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t));
ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)ZSTD_calloc(
sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t), cMem);
if (bufPool==NULL) return NULL;
bufPool->totalBuffers = maxNbBuffers;
bufPool->nbBuffers = 0;
bufPool->cMem = cMem;
return bufPool;
}
@@ -105,8 +105,21 @@ static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool)
unsigned u;
if (!bufPool) return; /* compatibility with free on NULL */
for (u=0; u<bufPool->totalBuffers; u++)
free(bufPool->bTable[u].start);
free(bufPool);
ZSTD_free(bufPool->bTable[u].start, bufPool->cMem);
ZSTD_free(bufPool, bufPool->cMem);
}
/* only works at initialization, not during compression */
static size_t ZSTDMT_sizeof_bufferPool(ZSTDMT_bufferPool* bufPool)
{
size_t const poolSize = sizeof(*bufPool)
+ (bufPool->totalBuffers - 1) * sizeof(buffer_t);
unsigned u;
size_t totalBufferSize = 0;
for (u=0; u<bufPool->totalBuffers; u++)
totalBufferSize += bufPool->bTable[u].size;
return poolSize + totalBufferSize;
}
/* assumption : invocation from main thread only ! */
@@ -115,13 +128,15 @@ static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* pool, size_t bSize)
if (pool->nbBuffers) { /* try to use an existing buffer */
buffer_t const buf = pool->bTable[--(pool->nbBuffers)];
size_t const availBufferSize = buf.size;
if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize)) /* large enough, but not too much */
if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize))
/* large enough, but not too much */
return buf;
free(buf.start); /* size conditions not respected : scratch this buffer and create a new one */
/* size conditions not respected : scratch this buffer, create new one */
ZSTD_free(buf.start, pool->cMem);
}
/* create new buffer */
{ buffer_t buffer;
void* const start = malloc(bSize);
void* const start = ZSTD_malloc(bSize, pool->cMem);
if (start==NULL) bSize = 0;
buffer.start = start; /* note : start can be NULL if malloc fails ! */
buffer.size = bSize;
@@ -138,7 +153,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
return;
}
/* Reached bufferPool capacity (should not happen) */
free(buf.start);
ZSTD_free(buf.start, pool->cMem);
}
@@ -147,6 +162,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
typedef struct {
unsigned totalCCtx;
unsigned availCCtx;
ZSTD_customMem cMem;
ZSTD_CCtx* cctx[1]; /* variable size */
} ZSTDMT_CCtxPool;
@@ -158,23 +174,40 @@ static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool)
unsigned u;
for (u=0; u<pool->totalCCtx; u++)
ZSTD_freeCCtx(pool->cctx[u]); /* note : compatible with free on NULL */
free(pool);
ZSTD_free(pool, pool->cMem);
}
/* ZSTDMT_createCCtxPool() :
* implies nbThreads >= 1 , checked by caller ZSTDMT_createCCtx() */
static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads)
static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads,
ZSTD_customMem cMem)
{
ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) calloc(1, sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*));
ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) ZSTD_calloc(
sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*), cMem);
if (!cctxPool) return NULL;
cctxPool->cMem = cMem;
cctxPool->totalCCtx = nbThreads;
cctxPool->availCCtx = 1; /* at least one cctx for single-thread mode */
cctxPool->cctx[0] = ZSTD_createCCtx();
cctxPool->cctx[0] = ZSTD_createCCtx_advanced(cMem);
if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; }
DEBUGLOG(1, "cctxPool created, with %u threads", nbThreads);
DEBUGLOG(4, "cctxPool created, with %u threads", nbThreads);
return cctxPool;
}
/* only works during initialization phase, not during compression */
static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool)
{
unsigned const nbThreads = cctxPool->totalCCtx;
size_t const poolSize = sizeof(*cctxPool)
+ (nbThreads-1)*sizeof(ZSTD_CCtx*);
unsigned u;
size_t totalCCtxSize = 0;
for (u=0; u<nbThreads; u++)
totalCCtxSize += ZSTD_sizeof_CCtx(cctxPool->cctx[u]);
return poolSize + totalCCtxSize;
}
static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* pool)
{
if (pool->availCCtx) {
@@ -218,7 +251,7 @@ typedef struct {
pthread_mutex_t* jobCompleted_mutex;
pthread_cond_t* jobCompleted_cond;
ZSTD_parameters params;
ZSTD_CDict* cdict;
const ZSTD_CDict* cdict;
unsigned long long fullFrameSize;
} ZSTDMT_jobDescription;
@@ -228,11 +261,11 @@ void ZSTDMT_compressChunk(void* jobDescription)
ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription;
const void* const src = (const char*)job->srcStart + job->dictSize;
buffer_t const dstBuff = job->dstBuff;
DEBUGLOG(3, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
DEBUGLOG(4, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
job->firstChunk, job->lastChunk, (U32)job->dictSize, (U32)job->srcSize);
if (job->cdict) { /* should only happen for first segment */
size_t const initError = ZSTD_compressBegin_usingCDict_advanced(job->cctx, job->cdict, job->params.fParams, job->fullFrameSize);
if (job->cdict) DEBUGLOG(3, "using CDict ");
DEBUGLOG(5, "using CDict");
if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; }
} else { /* srcStart points at reloaded section */
if (!job->firstChunk) job->params.fParams.contentSizeFlag = 0; /* ensure no srcSize control */
@@ -247,12 +280,12 @@ void ZSTDMT_compressChunk(void* jobDescription)
ZSTD_invalidateRepCodes(job->cctx);
}
DEBUGLOG(4, "Compressing : ");
DEBUGLOG(5, "Compressing : ");
DEBUG_PRINTHEX(4, job->srcStart, 12);
job->cSize = (job->lastChunk) ?
ZSTD_compressEnd (job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize) :
ZSTD_compressContinue(job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize);
DEBUGLOG(3, "compressed %u bytes into %u bytes (first:%u) (last:%u)",
DEBUGLOG(4, "compressed %u bytes into %u bytes (first:%u) (last:%u)",
(unsigned)job->srcSize, (unsigned)job->cSize, job->firstChunk, job->lastChunk);
DEBUGLOG(5, "dstBuff.size : %u ; => %s", (U32)dstBuff.size, ZSTD_getErrorName(job->cSize));
@@ -271,6 +304,7 @@ _endJob:
struct ZSTDMT_CCtx_s {
POOL_ctx* factory;
ZSTDMT_jobDescription* jobs;
ZSTDMT_bufferPool* buffPool;
ZSTDMT_CCtxPool* cctxPool;
pthread_mutex_t jobCompleted_mutex;
@@ -292,43 +326,51 @@ struct ZSTDMT_CCtx_s {
unsigned overlapRLog;
unsigned long long frameContentSize;
size_t sectionSize;
ZSTD_CDict* cdict;
ZSTD_CStream* cstream;
ZSTDMT_jobDescription jobs[1]; /* variable size (must lies at the end) */
ZSTD_customMem cMem;
ZSTD_CDict* cdictLocal;
const ZSTD_CDict* cdict;
};
ZSTDMT_CCtx *ZSTDMT_createCCtx(unsigned nbThreads)
ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads, ZSTD_customMem cMem)
{
ZSTDMT_CCtx* cctx;
ZSTDMT_CCtx* mtctx;
U32 const minNbJobs = nbThreads + 2;
U32 const nbJobsLog2 = ZSTD_highbit32(minNbJobs) + 1;
U32 const nbJobs = 1 << nbJobsLog2;
DEBUGLOG(5, "nbThreads : %u ; minNbJobs : %u ; nbJobsLog2 : %u ; nbJobs : %u \n",
nbThreads, minNbJobs, nbJobsLog2, nbJobs);
DEBUGLOG(5, "nbThreads: %u ; minNbJobs: %u ; nbJobsLog2: %u ; nbJobs: %u",
nbThreads, minNbJobs, nbJobsLog2, nbJobs);
if ((nbThreads < 1) | (nbThreads > ZSTDMT_NBTHREADS_MAX)) return NULL;
cctx = (ZSTDMT_CCtx*) calloc(1, sizeof(ZSTDMT_CCtx) + nbJobs*sizeof(ZSTDMT_jobDescription));
if (!cctx) return NULL;
cctx->nbThreads = nbThreads;
cctx->jobIDMask = nbJobs - 1;
cctx->allJobsCompleted = 1;
cctx->sectionSize = 0;
cctx->overlapRLog = 3;
cctx->factory = POOL_create(nbThreads, 1);
cctx->buffPool = ZSTDMT_createBufferPool(nbThreads);
cctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads);
if (!cctx->factory | !cctx->buffPool | !cctx->cctxPool) { /* one object was not created */
ZSTDMT_freeCCtx(cctx);
if ((cMem.customAlloc!=NULL) ^ (cMem.customFree!=NULL))
/* invalid custom allocator */
return NULL;
mtctx = (ZSTDMT_CCtx*) ZSTD_calloc(sizeof(ZSTDMT_CCtx), cMem);
if (!mtctx) return NULL;
mtctx->cMem = cMem;
mtctx->nbThreads = nbThreads;
mtctx->jobIDMask = nbJobs - 1;
mtctx->allJobsCompleted = 1;
mtctx->sectionSize = 0;
mtctx->overlapRLog = 3;
mtctx->factory = POOL_create(nbThreads, 1);
mtctx->jobs = (ZSTDMT_jobDescription*)ZSTD_calloc(
nbJobs * sizeof(*mtctx->jobs), cMem);
mtctx->buffPool = ZSTDMT_createBufferPool(nbThreads, cMem);
mtctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads, cMem);
if (!mtctx->factory | !mtctx->jobs | !mtctx->buffPool | !mtctx->cctxPool) {
ZSTDMT_freeCCtx(mtctx);
return NULL;
}
if (nbThreads==1) {
cctx->cstream = ZSTD_createCStream();
if (!cctx->cstream) {
ZSTDMT_freeCCtx(cctx); return NULL;
} }
pthread_mutex_init(&cctx->jobCompleted_mutex, NULL); /* Todo : check init function return */
pthread_cond_init(&cctx->jobCompleted_cond, NULL);
DEBUGLOG(4, "mt_cctx created, for %u threads \n", nbThreads);
return cctx;
pthread_mutex_init(&mtctx->jobCompleted_mutex, NULL); /* Todo : check init function return */
pthread_cond_init(&mtctx->jobCompleted_cond, NULL);
DEBUGLOG(4, "mt_cctx created, for %u threads", nbThreads);
return mtctx;
}
ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads)
{
return ZSTDMT_createCCtx_advanced(nbThreads, ZSTD_defaultCMem);
}
/* ZSTDMT_releaseAllJobResources() :
@@ -356,15 +398,26 @@ size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx)
POOL_free(mtctx->factory);
if (!mtctx->allJobsCompleted) ZSTDMT_releaseAllJobResources(mtctx); /* stop workers first */
ZSTDMT_freeBufferPool(mtctx->buffPool); /* release job resources into pools first */
ZSTD_free(mtctx->jobs, mtctx->cMem);
ZSTDMT_freeCCtxPool(mtctx->cctxPool);
ZSTD_freeCDict(mtctx->cdict);
ZSTD_freeCStream(mtctx->cstream);
ZSTD_freeCDict(mtctx->cdictLocal);
pthread_mutex_destroy(&mtctx->jobCompleted_mutex);
pthread_cond_destroy(&mtctx->jobCompleted_cond);
free(mtctx);
ZSTD_free(mtctx, mtctx->cMem);
return 0;
}
size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx)
{
if (mtctx == NULL) return 0; /* supports sizeof NULL */
return sizeof(*mtctx)
+ POOL_sizeof(mtctx->factory)
+ ZSTDMT_sizeof_bufferPool(mtctx->buffPool)
+ (mtctx->jobIDMask+1) * sizeof(ZSTDMT_jobDescription)
+ ZSTDMT_sizeof_CCtxPool(mtctx->cctxPool)
+ ZSTD_sizeof_CDict(mtctx->cdictLocal);
}
size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value)
{
switch(parameter)
@@ -373,7 +426,7 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter,
mtctx->sectionSize = value;
return 0;
case ZSTDMT_p_overlapSectionLog :
DEBUGLOG(4, "ZSTDMT_p_overlapSectionLog : %u", value);
DEBUGLOG(5, "ZSTDMT_p_overlapSectionLog : %u", value);
mtctx->overlapRLog = (value >= 9) ? 0 : 9 - value;
return 0;
default :
@@ -404,8 +457,8 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
unsigned const compressWithinDst = (dstCapacity >= ZSTD_compressBound(srcSize)) ? nbChunks : (unsigned)(dstCapacity / ZSTD_compressBound(avgChunkSize)); /* presumes avgChunkSize >= 256 KB, which should be the case */
size_t frameStartPos = 0, dstBufferPos = 0;
DEBUGLOG(3, "windowLog : %2u => chunkTargetSize : %u bytes ", params.cParams.windowLog, (U32)chunkTargetSize);
DEBUGLOG(2, "nbChunks : %2u (chunkSize : %u bytes) ", nbChunks, (U32)avgChunkSize);
DEBUGLOG(4, "windowLog : %2u => chunkTargetSize : %u bytes ", params.cParams.windowLog, (U32)chunkTargetSize);
DEBUGLOG(4, "nbChunks : %2u (chunkSize : %u bytes) ", nbChunks, (U32)avgChunkSize);
params.fParams.contentSizeFlag = 1;
if (nbChunks==1) { /* fallback to single-thread mode */
@@ -442,8 +495,8 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
mtctx->jobs[u].jobCompleted_mutex = &mtctx->jobCompleted_mutex;
mtctx->jobs[u].jobCompleted_cond = &mtctx->jobCompleted_cond;
DEBUGLOG(3, "posting job %u (%u bytes)", u, (U32)chunkSize);
DEBUG_PRINTHEX(3, mtctx->jobs[u].srcStart, 12);
DEBUGLOG(4, "posting job %u (%u bytes)", u, (U32)chunkSize);
DEBUG_PRINTHEX(5, mtctx->jobs[u].srcStart, 12);
POOL_add(mtctx->factory, ZSTDMT_compressChunk, &mtctx->jobs[u]);
frameStartPos += chunkSize;
@@ -455,14 +508,14 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
{ unsigned chunkID;
size_t error = 0, dstPos = 0;
for (chunkID=0; chunkID<nbChunks; chunkID++) {
DEBUGLOG(3, "waiting for chunk %u ", chunkID);
DEBUGLOG(5, "waiting for chunk %u ", chunkID);
PTHREAD_MUTEX_LOCK(&mtctx->jobCompleted_mutex);
while (mtctx->jobs[chunkID].jobCompleted==0) {
DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", chunkID);
DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", chunkID);
pthread_cond_wait(&mtctx->jobCompleted_cond, &mtctx->jobCompleted_mutex);
}
pthread_mutex_unlock(&mtctx->jobCompleted_mutex);
DEBUGLOG(3, "ready to write chunk %u ", chunkID);
DEBUGLOG(5, "ready to write chunk %u ", chunkID);
ZSTDMT_releaseCCtx(mtctx->cctxPool, mtctx->jobs[chunkID].cctx);
mtctx->jobs[chunkID].cctx = NULL;
@@ -480,7 +533,7 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
dstPos += cSize ;
}
}
if (!error) DEBUGLOG(3, "compressed size : %u ", (U32)dstPos);
if (!error) DEBUGLOG(4, "compressed size : %u ", (U32)dstPos);
return error ? error : dstPos;
}
@@ -491,12 +544,13 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
/* ======= Streaming API ======= */
/* ====================================== */
static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs)
{
while (zcs->doneJobID < zcs->nextJobID) {
unsigned const jobID = zcs->doneJobID & zcs->jobIDMask;
PTHREAD_MUTEX_LOCK(&zcs->jobCompleted_mutex);
while (zcs->jobs[jobID].jobCompleted==0) {
DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID); /* we want to block when waiting for data to flush */
DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID); /* we want to block when waiting for data to flush */
pthread_cond_wait(&zcs->jobCompleted_cond, &zcs->jobCompleted_mutex);
}
pthread_mutex_unlock(&zcs->jobCompleted_mutex);
@@ -505,33 +559,50 @@ static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
}
static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
const void* dict, size_t dictSize, unsigned updateDict,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
ZSTD_customMem const cmem = { NULL, NULL, NULL };
DEBUGLOG(3, "Started new compression, with windowLog : %u", params.cParams.windowLog);
if (zcs->nbThreads==1) return ZSTD_initCStream_advanced(zcs->cstream, dict, dictSize, params, pledgedSrcSize);
if (zcs->allJobsCompleted == 0) { /* previous job not correctly finished */
DEBUGLOG(5, "ZSTDMT_initCStream_internal");
/* params are supposed to be fully validated at this point */
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
assert(!((dict) && (cdict))); /* either dict or cdict, not both */
if (zcs->nbThreads==1) {
DEBUGLOG(5, "single thread mode");
return ZSTD_initCStream_internal(zcs->cctxPool->cctx[0],
dict, dictSize, cdict,
params, pledgedSrcSize);
}
if (zcs->allJobsCompleted == 0) { /* previous compression not correctly finished */
ZSTDMT_waitForAllJobsCompleted(zcs);
ZSTDMT_releaseAllJobResources(zcs);
zcs->allJobsCompleted = 1;
}
zcs->params = params;
if (updateDict) {
ZSTD_freeCDict(zcs->cdict); zcs->cdict = NULL;
if (dict && dictSize) {
zcs->cdict = ZSTD_createCDict_advanced(dict, dictSize, 0, params.cParams, cmem);
if (zcs->cdict == NULL) return ERROR(memory_allocation);
} }
zcs->frameContentSize = pledgedSrcSize;
if (dict) {
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
0 /* byRef */, ZSTD_dm_auto,
params.cParams, zcs->cMem);
zcs->cdict = zcs->cdictLocal;
if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
} else {
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = NULL;
zcs->cdict = cdict;
}
zcs->targetDictSize = (zcs->overlapRLog>=9) ? 0 : (size_t)1 << (zcs->params.cParams.windowLog - zcs->overlapRLog);
DEBUGLOG(4, "overlapRLog : %u ", zcs->overlapRLog);
DEBUGLOG(3, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
DEBUGLOG(5, "overlapRLog : %u ", zcs->overlapRLog);
DEBUGLOG(5, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
zcs->targetSectionSize = zcs->sectionSize ? zcs->sectionSize : (size_t)1 << (zcs->params.cParams.windowLog + 2);
zcs->targetSectionSize = MAX(ZSTDMT_SECTION_SIZE_MIN, zcs->targetSectionSize);
zcs->targetSectionSize = MAX(zcs->targetDictSize, zcs->targetSectionSize);
DEBUGLOG(3, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
DEBUGLOG(5, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
zcs->marginSize = zcs->targetSectionSize >> 2;
zcs->inBuffSize = zcs->targetDictSize + zcs->targetSectionSize + zcs->marginSize;
zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
@@ -546,24 +617,39 @@ static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
return 0;
}
size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* zcs,
size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
return ZSTDMT_initCStream_internal(zcs, dict, dictSize, 1, params, pledgedSrcSize);
DEBUGLOG(5, "ZSTDMT_initCStream_advanced");
return ZSTDMT_initCStream_internal(mtctx, dict, dictSize, NULL, params, pledgedSrcSize);
}
size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
const ZSTD_CDict* cdict,
ZSTD_frameParameters fParams,
unsigned long long pledgedSrcSize)
{
ZSTD_parameters params = ZSTD_getParamsFromCDict(cdict);
if (cdict==NULL) return ERROR(dictionary_wrong); /* method incompatible with NULL cdict */
params.fParams = fParams;
return ZSTDMT_initCStream_internal(mtctx, NULL, 0 /*dictSize*/, cdict,
params, pledgedSrcSize);
}
/* ZSTDMT_resetCStream() :
* pledgedSrcSize is optional and can be zero == unknown */
size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* zcs, unsigned long long pledgedSrcSize)
{
if (zcs->nbThreads==1) return ZSTD_resetCStream(zcs->cstream, pledgedSrcSize);
if (zcs->nbThreads==1)
return ZSTD_resetCStream(zcs->cctxPool->cctx[0], pledgedSrcSize);
return ZSTDMT_initCStream_internal(zcs, NULL, 0, 0, zcs->params, pledgedSrcSize);
}
size_t ZSTDMT_initCStream(ZSTDMT_CCtx* zcs, int compressionLevel) {
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0);
return ZSTDMT_initCStream_internal(zcs, NULL, 0, 1, params, 0);
return ZSTDMT_initCStream_internal(zcs, NULL, 0, NULL, params, 0);
}
@@ -582,13 +668,16 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
return ERROR(memory_allocation);
}
DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ", zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ",
zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
zcs->jobs[jobID].src = zcs->inBuff.buffer;
zcs->jobs[jobID].srcStart = zcs->inBuff.buffer.start;
zcs->jobs[jobID].srcSize = srcSize;
zcs->jobs[jobID].dictSize = zcs->dictSize; /* note : zcs->inBuff.filled is presumed >= srcSize + dictSize */
zcs->jobs[jobID].dictSize = zcs->dictSize;
assert(zcs->inBuff.filled >= srcSize + zcs->dictSize);
zcs->jobs[jobID].params = zcs->params;
if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0; /* do not calculate checksum within sections, just keep it in header for first section */
/* do not calculate checksum within sections, but write it in header for first section */
if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0;
zcs->jobs[jobID].cdict = zcs->nextJobID==0 ? zcs->cdict : NULL;
zcs->jobs[jobID].fullFrameSize = zcs->frameContentSize;
zcs->jobs[jobID].dstBuff = dstBuffer;
@@ -603,6 +692,7 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
/* get a new buffer for next input */
if (!endFrame) {
size_t const newDictSize = MIN(srcSize + zcs->dictSize, zcs->targetDictSize);
DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
if (zcs->inBuff.buffer.start == NULL) { /* not enough memory to allocate next input buffer */
zcs->jobs[jobID].jobCompleted = 1;
@@ -611,22 +701,33 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
ZSTDMT_releaseAllJobResources(zcs);
return ERROR(memory_allocation);
}
DEBUGLOG(5, "inBuff filled to %u", (U32)zcs->inBuff.filled);
DEBUGLOG(5, "inBuff currently filled to %u", (U32)zcs->inBuff.filled);
zcs->inBuff.filled -= srcSize + zcs->dictSize - newDictSize;
DEBUGLOG(5, "new job : filled to %u, with %u dict and %u src", (U32)zcs->inBuff.filled, (U32)newDictSize, (U32)(zcs->inBuff.filled - newDictSize));
memmove(zcs->inBuff.buffer.start, (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize, zcs->inBuff.filled);
DEBUGLOG(5, "new job : inBuff filled to %u, with %u dict and %u src",
(U32)zcs->inBuff.filled, (U32)newDictSize,
(U32)(zcs->inBuff.filled - newDictSize));
memmove(zcs->inBuff.buffer.start,
(const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize,
zcs->inBuff.filled);
DEBUGLOG(5, "new inBuff pre-filled");
zcs->dictSize = newDictSize;
} else {
} else { /* if (endFrame==1) */
DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
zcs->inBuff.buffer = g_nullBuffer;
zcs->inBuff.filled = 0;
zcs->dictSize = 0;
zcs->frameEnded = 1;
if (zcs->nextJobID == 0)
zcs->params.fParams.checksumFlag = 0; /* single chunk : checksum is calculated directly within worker thread */
/* single chunk exception : checksum is calculated directly within worker thread */
zcs->params.fParams.checksumFlag = 0;
}
DEBUGLOG(3, "posting job %u : %u bytes (end:%u) (note : doneJob = %u=>%u)", zcs->nextJobID, (U32)zcs->jobs[jobID].srcSize, zcs->jobs[jobID].lastChunk, zcs->doneJobID, zcs->doneJobID & zcs->jobIDMask);
DEBUGLOG(4, "posting job %u : %u bytes (end:%u) (note : doneJob = %u=>%u)",
zcs->nextJobID,
(U32)zcs->jobs[jobID].srcSize,
zcs->jobs[jobID].lastChunk,
zcs->doneJobID,
zcs->doneJobID & zcs->jobIDMask);
POOL_add(zcs->factory, ZSTDMT_compressChunk, &zcs->jobs[jobID]); /* this call is blocking when thread worker pool is exhausted */
zcs->nextJobID++;
return 0;
@@ -664,7 +765,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
XXH64_update(&zcs->xxhState, (const char*)job.srcStart + job.dictSize, job.srcSize);
if (zcs->frameEnded && (zcs->doneJobID+1 == zcs->nextJobID)) { /* write checksum at end of last section */
U32 const checksum = (U32)XXH64_digest(&zcs->xxhState);
DEBUGLOG(4, "writing checksum : %08X \n", checksum);
DEBUGLOG(5, "writing checksum : %08X \n", checksum);
MEM_writeLE32((char*)job.dstBuff.start + job.cSize, checksum);
job.cSize += 4;
zcs->jobs[wJobID].cSize += 4;
@@ -675,7 +776,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
zcs->jobs[wJobID].jobScanned = 1;
}
{ size_t const toWrite = MIN(job.cSize - job.dstFlushed, output->size - output->pos);
DEBUGLOG(4, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
DEBUGLOG(5, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
memcpy((char*)output->dst + output->pos, (const char*)job.dstBuff.start + job.dstFlushed, toWrite);
output->pos += toWrite;
job.dstFlushed += toWrite;
@@ -699,23 +800,29 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
{
size_t const newJobThreshold = zcs->dictSize + zcs->targetSectionSize + zcs->marginSize;
if (zcs->frameEnded) return ERROR(stage_wrong); /* current frame being ended. Only flush is allowed. Restart with init */
if (zcs->nbThreads==1) return ZSTD_compressStream(zcs->cstream, output, input);
if (zcs->frameEnded) {
/* current frame being ended. Only flush is allowed. Or start new job with init */
DEBUGLOG(5, "ZSTDMT_compressStream: zcs::frameEnded==1");
return ERROR(stage_wrong);
}
if (zcs->nbThreads==1) {
return ZSTD_compressStream(zcs->cctxPool->cctx[0], output, input);
}
/* fill input buffer */
{ size_t const toLoad = MIN(input->size - input->pos, zcs->inBuffSize - zcs->inBuff.filled);
memcpy((char*)zcs->inBuff.buffer.start + zcs->inBuff.filled, input->src, toLoad);
memcpy((char*)zcs->inBuff.buffer.start + zcs->inBuff.filled, (const char*)input->src + input->pos, toLoad);
input->pos += toLoad;
zcs->inBuff.filled += toLoad;
}
if ( (zcs->inBuff.filled >= newJobThreshold) /* filled enough : let's compress */
&& (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) { /* avoid overwriting job round buffer */
CHECK_F( ZSTDMT_createCompressionJob(zcs, zcs->targetSectionSize, 0) );
CHECK_F( ZSTDMT_createCompressionJob(zcs, zcs->targetSectionSize, 0 /* endFrame */) );
}
/* check for data to flush */
CHECK_F( ZSTDMT_flushNextJob(zcs, output, (zcs->inBuff.filled == zcs->inBuffSize)) ); /* block if it wasn't possible to create new job due to saturation */
CHECK_F( ZSTDMT_flushNextJob(zcs, output, (zcs->inBuff.filled == zcs->inBuffSize) /* blockToFlush */) ); /* block if it wasn't possible to create new job due to saturation */
/* recommended next input size : fill current input buffer */
return zcs->inBuffSize - zcs->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */
@@ -726,26 +833,60 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* outp
{
size_t const srcSize = zcs->inBuff.filled - zcs->dictSize;
if (srcSize) DEBUGLOG(4, "flushing : %u bytes left to compress", (U32)srcSize);
if (srcSize)
DEBUGLOG(5, "ZSTDMT_flushStream_internal : %u bytes left to compress",
(U32)srcSize);
if ( ((srcSize > 0) || (endFrame && !zcs->frameEnded))
&& (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) {
DEBUGLOG(5, "create new job with %u bytes to compress", (U32)srcSize);
DEBUGLOG(5, "end order : %u", endFrame);
CHECK_F( ZSTDMT_createCompressionJob(zcs, srcSize, endFrame) );
DEBUGLOG(5, "resulting zcs->frameEnded : %u", zcs->frameEnded);
}
/* check if there is any data available to flush */
DEBUGLOG(5, "zcs->doneJobID : %u ; zcs->nextJobID : %u ", zcs->doneJobID, zcs->nextJobID);
return ZSTDMT_flushNextJob(zcs, output, 1);
DEBUGLOG(5, "zcs->doneJobID : %u ; zcs->nextJobID : %u",
zcs->doneJobID, zcs->nextJobID);
return ZSTDMT_flushNextJob(zcs, output, 1 /*blockToFlush */);
}
size_t ZSTDMT_flushStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
{
if (zcs->nbThreads==1) return ZSTD_flushStream(zcs->cstream, output);
return ZSTDMT_flushStream_internal(zcs, output, 0);
DEBUGLOG(5, "ZSTDMT_flushStream");
if (zcs->nbThreads==1)
return ZSTD_flushStream(zcs->cctxPool->cctx[0], output);
return ZSTDMT_flushStream_internal(zcs, output, 0 /* endFrame */);
}
size_t ZSTDMT_endStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
{
if (zcs->nbThreads==1) return ZSTD_endStream(zcs->cstream, output);
return ZSTDMT_flushStream_internal(zcs, output, 1);
DEBUGLOG(5, "ZSTDMT_endStream");
if (zcs->nbThreads==1)
return ZSTD_endStream(zcs->cctxPool->cctx[0], output);
return ZSTDMT_flushStream_internal(zcs, output, 1 /* endFrame */);
}
size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
ZSTD_outBuffer* output,
ZSTD_inBuffer* input,
ZSTD_EndDirective endOp)
{
DEBUGLOG(5, "in: pos:%u / size:%u ; endOp=%u",
(U32)input->pos, (U32)input->size, (U32)endOp);
if (input->pos < input->size) /* exclude final flushes */
CHECK_F(ZSTDMT_compressStream(mtctx, output, input));
if (input->pos < input->size) endOp = ZSTD_e_continue;
switch(endOp)
{
case ZSTD_e_flush:
return ZSTDMT_flushStream(mtctx, output);
case ZSTD_e_end:
DEBUGLOG(5, "endOp:%u; calling ZSTDMT_endStream", (U32)endOp);
return ZSTDMT_endStream(mtctx, output);
case ZSTD_e_continue:
return 1;
default:
return ERROR(GENERIC); /* invalid endDirective */
}
}
lib/compress/zstdmt_compress.h
+41 -13
View File
@@ -15,25 +15,33 @@
#endif
/* Note : All prototypes defined in this file shall be considered experimental.
* There is no guarantee of API continuity (yet) on any of these prototypes */
/* Note : All prototypes defined in this file are labelled experimental.
* No guarantee of API continuity is provided on any of them.
* In fact, the expectation is that these prototypes will be replaced
* by ZSTD_compress_generic() API in the near future */
/* === Dependencies === */
#include <stddef.h> /* size_t */
#include <stddef.h> /* size_t */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters */
#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
/* === Simple one-pass functions === */
/* === Memory management === */
typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads);
ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* cctx);
ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads,
ZSTD_customMem cMem);
ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel);
ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
/* === Simple buffer-to-butter one-pass function === */
ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel);
/* === Streaming functions === */
@@ -53,8 +61,15 @@ ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);
# define ZSTDMT_SECTION_SIZE_MIN (1U << 20) /* 1 MB - Minimum size of each compression job */
#endif
ZSTDLIB_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_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,
const ZSTD_CDict* cdict,
ZSTD_frameParameters fparams,
unsigned long long pledgedSrcSize); /* note : zero means empty */
/* ZSDTMT_parameter :
* List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
@@ -71,6 +86,19 @@ typedef enum {
ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value);
/*! ZSTDMT_compressStream_generic() :
* Combines ZSTDMT_compressStream() with ZSTDMT_flushStream() or ZSTDMT_endStream()
* depending on flush directive.
* @return : minimum amount of data still to be flushed
* 0 if fully flushed
* or an error code */
ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
ZSTD_outBuffer* output,
ZSTD_inBuffer* input,
ZSTD_EndDirective endOp);
#if defined (__cplusplus)
}
#endif
lib/decompress/zstd_decompress.c
+294 -235
View File
@@ -53,8 +53,7 @@
# include "zstd_legacy.h"
#endif
#if defined(_MSC_VER)
#if defined(_MSC_VER) && !defined(_M_IA64) /* _mm_prefetch() is not defined for ia64 */
# include <mmintrin.h> /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
# define ZSTD_PREFETCH(ptr) _mm_prefetch((const char*)ptr, _MM_HINT_T0)
#elif defined(__GNUC__)
@@ -63,8 +62,9 @@
# define ZSTD_PREFETCH(ptr) /* disabled */
#endif
/*-*************************************
* Macros
* Errors
***************************************/
#define ZSTD_isError ERR_isError /* for inlining */
#define FSE_isError ERR_isError
@@ -85,6 +85,9 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
ZSTDds_decompressLastBlock, ZSTDds_checkChecksum,
ZSTDds_decodeSkippableHeader, ZSTDds_skipFrame } ZSTD_dStage;
typedef enum { zdss_init=0, zdss_loadHeader,
zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
typedef struct {
FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)];
FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
@@ -117,11 +120,39 @@ struct ZSTD_DCtx_s
ZSTD_customMem customMem;
size_t litSize;
size_t rleSize;
BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH];
size_t staticSize;
/* streaming */
ZSTD_DDict* ddictLocal;
const ZSTD_DDict* ddict;
ZSTD_dStreamStage streamStage;
char* inBuff;
size_t inBuffSize;
size_t inPos;
size_t maxWindowSize;
char* outBuff;
size_t outBuffSize;
size_t outStart;
size_t outEnd;
size_t blockSize;
size_t lhSize;
void* legacyContext;
U32 previousLegacyVersion;
U32 legacyVersion;
U32 hostageByte;
/* workspace */
BYTE litBuffer[ZSTD_BLOCKSIZE_MAX + WILDCOPY_OVERLENGTH];
BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
}; /* typedef'd to ZSTD_DCtx within "zstd.h" */
size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) { return (dctx==NULL) ? 0 : sizeof(ZSTD_DCtx); }
size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx)
{
if (dctx==NULL) return 0; /* support sizeof NULL */
return sizeof(*dctx)
+ ZSTD_sizeof_DDict(dctx->ddictLocal)
+ dctx->inBuffSize + dctx->outBuffSize;
}
size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); }
@@ -145,36 +176,73 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
return 0;
}
static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
{
ZSTD_decompressBegin(dctx); /* cannot fail */
dctx->staticSize = 0;
dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
dctx->ddict = NULL;
dctx->ddictLocal = NULL;
dctx->inBuff = NULL;
dctx->inBuffSize = 0;
dctx->outBuffSize= 0;
dctx->streamStage = zdss_init;
}
ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
{
ZSTD_DCtx* dctx;
if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
if (!customMem.customAlloc || !customMem.customFree) return NULL;
{ ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(*dctx), customMem);
if (!dctx) return NULL;
dctx->customMem = customMem;
dctx->legacyContext = NULL;
ZSTD_initDCtx_internal(dctx);
return dctx;
}
}
dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem);
if (!dctx) return NULL;
memcpy(&dctx->customMem, &customMem, sizeof(customMem));
ZSTD_decompressBegin(dctx);
ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize)
{
ZSTD_DCtx* dctx = (ZSTD_DCtx*) workspace;
if ((size_t)workspace & 7) return NULL; /* 8-aligned */
if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL; /* minimum size */
ZSTD_initDCtx_internal(dctx);
dctx->staticSize = workspaceSize;
dctx->inBuff = (char*)(dctx+1);
return dctx;
}
ZSTD_DCtx* ZSTD_createDCtx(void)
{
return ZSTD_createDCtx_advanced(defaultCustomMem);
return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
}
size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
{
if (dctx==NULL) return 0; /* support free on NULL */
ZSTD_free(dctx, dctx->customMem);
return 0; /* reserved as a potential error code in the future */
if (dctx->staticSize) return ERROR(memory_allocation); /* not compatible with static DCtx */
{ ZSTD_customMem const cMem = dctx->customMem;
ZSTD_freeDDict(dctx->ddictLocal);
dctx->ddictLocal = NULL;
ZSTD_free(dctx->inBuff, cMem);
dctx->inBuff = NULL;
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
if (dctx->legacyContext)
ZSTD_freeLegacyStreamContext(dctx->legacyContext, dctx->previousLegacyVersion);
#endif
ZSTD_free(dctx, cMem);
return 0;
}
}
/* no longer useful */
void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx)
{
size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX+WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max;
memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize); /* no need to copy workspace */
size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx);
memcpy(dstDCtx, srcDCtx, toCopy); /* no need to copy workspace */
}
@@ -230,7 +298,8 @@ size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t src
if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) {
if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
/* skippable frame */
if (srcSize < ZSTD_skippableHeaderSize) return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */
if (srcSize < ZSTD_skippableHeaderSize)
return ZSTD_skippableHeaderSize; /* magic number + frame length */
memset(zfhPtr, 0, sizeof(*zfhPtr));
zfhPtr->frameContentSize = MEM_readLE32((const char *)src + 4);
zfhPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
@@ -253,11 +322,13 @@ size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t src
U32 windowSize = 0;
U32 dictID = 0;
U64 frameContentSize = 0;
if ((fhdByte & 0x08) != 0) return ERROR(frameParameter_unsupported); /* reserved bits, which must be zero */
if ((fhdByte & 0x08) != 0)
return ERROR(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); /* avoids issue with 1 << windowLog */
if (windowLog > ZSTD_WINDOWLOG_MAX)
return ERROR(frameParameter_windowTooLarge);
windowSize = (1U << windowLog);
windowSize += (windowSize >> 3) * (wlByte&7);
}
@@ -321,51 +392,48 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
* @return : decompressed size of the frames contained */
unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)
{
{
unsigned long long totalDstSize = 0;
while (srcSize >= ZSTD_frameHeaderSize_prefix) {
const U32 magicNumber = MEM_readLE32(src);
unsigned long long totalDstSize = 0;
if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
size_t skippableSize;
if (srcSize < ZSTD_skippableHeaderSize)
return ERROR(srcSize_wrong);
skippableSize = MEM_readLE32((const BYTE *)src + 4) +
ZSTD_skippableHeaderSize;
if (srcSize < skippableSize) {
return ZSTD_CONTENTSIZE_ERROR;
}
while (srcSize >= ZSTD_frameHeaderSize_prefix) {
const U32 magicNumber = MEM_readLE32(src);
src = (const BYTE *)src + skippableSize;
srcSize -= skippableSize;
continue;
if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
size_t skippableSize;
if (srcSize < ZSTD_skippableHeaderSize)
return ERROR(srcSize_wrong);
skippableSize = MEM_readLE32((const BYTE *)src + 4) +
ZSTD_skippableHeaderSize;
if (srcSize < skippableSize) {
return ZSTD_CONTENTSIZE_ERROR;
}
{
unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
/* check for overflow */
if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
totalDstSize += ret;
}
{
size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
if (ZSTD_isError(frameSrcSize)) {
return ZSTD_CONTENTSIZE_ERROR;
}
src = (const BYTE *)src + frameSrcSize;
srcSize -= frameSrcSize;
}
src = (const BYTE *)src + skippableSize;
srcSize -= skippableSize;
continue;
}
if (srcSize) {
return ZSTD_CONTENTSIZE_ERROR;
}
{ unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
return totalDstSize;
/* check for overflow */
if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
totalDstSize += ret;
}
{ size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
if (ZSTD_isError(frameSrcSize)) {
return ZSTD_CONTENTSIZE_ERROR;
}
src = (const BYTE *)src + frameSrcSize;
srcSize -= frameSrcSize;
}
}
if (srcSize) {
return ZSTD_CONTENTSIZE_ERROR;
}
return totalDstSize;
}
/** ZSTD_getDecompressedSize() :
@@ -483,7 +551,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
litCSize = (lhc >> 22) + (istart[4] << 10);
break;
}
if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
if (HUF_isError((litEncType==set_repeat) ?
@@ -555,7 +623,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
if (srcSize<4) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
break;
}
if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
dctx->litPtr = dctx->litBuffer;
dctx->litSize = litSize;
@@ -1288,7 +1356,7 @@ static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
{ /* blockType == blockCompressed */
const BYTE* ip = (const BYTE*)src;
if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(srcSize_wrong);
if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
/* Decode literals section */
{ size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
@@ -1503,6 +1571,8 @@ 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 incompatible with static dctx */
if (dctx->staticSize) return ERROR(memory_allocation);
decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
@@ -1578,7 +1648,7 @@ size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const
size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE==1)
#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
size_t regenSize;
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
if (dctx==NULL) return ERROR(memory_allocation);
@@ -1619,21 +1689,22 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
}
}
int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; } /* for zbuff */
static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; }
/** ZSTD_decompressContinue() :
* @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
* or an error code, which can be tested using ZSTD_isError() */
* srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress())
* @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
* or an error code, which can be tested using ZSTD_isError() */
size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
/* Sanity check */
if (srcSize != dctx->expected) return ERROR(srcSize_wrong);
if (srcSize != dctx->expected) return ERROR(srcSize_wrong); /* unauthorized */
if (dstCapacity) ZSTD_checkContinuity(dctx, dst);
switch (dctx->stage)
{
case ZSTDds_getFrameHeaderSize :
if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong); /* impossible */
if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong); /* unauthorized */
if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix; /* magic number + skippable frame length */
@@ -1678,7 +1749,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
dctx->stage = ZSTDds_getFrameHeaderSize;
}
} else {
dctx->expected = 3; /* go directly to next header */
dctx->expected = ZSTD_blockHeaderSize; /* jump to next header */
dctx->stage = ZSTDds_decodeBlockHeader;
}
return 0;
@@ -1904,33 +1975,39 @@ static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
}
static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, const void* dict, size_t dictSize, unsigned byReference)
{
if ((byReference) || (!dict) || (!dictSize)) {
ddict->dictBuffer = NULL;
ddict->dictContent = dict;
} else {
void* const internalBuffer = ZSTD_malloc(dictSize, ddict->cMem);
ddict->dictBuffer = internalBuffer;
ddict->dictContent = internalBuffer;
if (!internalBuffer) return ERROR(memory_allocation);
memcpy(internalBuffer, dict, dictSize);
}
ddict->dictSize = dictSize;
ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
/* parse dictionary content */
CHECK_F( ZSTD_loadEntropy_inDDict(ddict) );
return 0;
}
ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem)
{
if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
if (!customMem.customAlloc || !customMem.customFree) return NULL;
if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
{ ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
if (!ddict) return NULL;
ddict->cMem = customMem;
if ((byReference) || (!dict) || (!dictSize)) {
ddict->dictBuffer = NULL;
ddict->dictContent = dict;
} else {
void* const internalBuffer = ZSTD_malloc(dictSize, customMem);
if (!internalBuffer) { ZSTD_freeDDict(ddict); return NULL; }
memcpy(internalBuffer, dict, dictSize);
ddict->dictBuffer = internalBuffer;
ddict->dictContent = internalBuffer;
if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, byReference) )) {
ZSTD_freeDDict(ddict);
return NULL;
}
ddict->dictSize = dictSize;
ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
/* parse dictionary content */
{ size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict);
if (ZSTD_isError(errorCode)) {
ZSTD_freeDDict(ddict);
return NULL;
} }
return ddict;
}
@@ -1946,7 +2023,6 @@ ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
return ZSTD_createDDict_advanced(dict, dictSize, 0, allocator);
}
/*! ZSTD_createDDict_byReference() :
* Create a digested dictionary, to start decompression without startup delay.
* Dictionary content is simply referenced, it will be accessed during decompression.
@@ -1958,6 +2034,24 @@ ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize
}
ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference)
{
size_t const neededSpace = sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
ZSTD_DDict* const ddict = (ZSTD_DDict*)workspace;
if ((size_t)workspace & 7) return NULL; /* 8-aligned */
if (workspaceSize < neededSpace) return NULL;
if (!byReference) {
memcpy(ddict+1, dict, dictSize); /* local copy */
dict = ddict+1;
}
if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, 1 /* byRef */) ))
return NULL;
return ddict;
}
size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
{
if (ddict==NULL) return 0; /* support free on NULL */
@@ -1970,10 +2064,10 @@ size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
/*! ZSTD_estimateDDictSize() :
* Estimate amount of memory that will be needed to create a dictionary for decompression.
* Note : if dictionary is created "byReference", reduce this amount by dictSize */
size_t ZSTD_estimateDDictSize(size_t dictSize)
* Note : dictionary created "byReference" are smaller */
size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference)
{
return dictSize + sizeof(ZSTD_DDict);
return sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
}
size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
@@ -2044,88 +2138,30 @@ size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
* Streaming decompression
*====================================*/
typedef enum { zdss_init, zdss_loadHeader,
zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
/* *** Resource management *** */
struct ZSTD_DStream_s {
ZSTD_DCtx* dctx;
ZSTD_DDict* ddictLocal;
const ZSTD_DDict* ddict;
ZSTD_frameHeader fParams;
ZSTD_dStreamStage stage;
char* inBuff;
size_t inBuffSize;
size_t inPos;
size_t maxWindowSize;
char* outBuff;
size_t outBuffSize;
size_t outStart;
size_t outEnd;
size_t blockSize;
BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; /* tmp buffer to store frame header */
size_t lhSize;
ZSTD_customMem customMem;
void* legacyContext;
U32 previousLegacyVersion;
U32 legacyVersion;
U32 hostageByte;
}; /* typedef'd to ZSTD_DStream within "zstd.h" */
ZSTD_DStream* ZSTD_createDStream(void)
{
return ZSTD_createDStream_advanced(defaultCustomMem);
return ZSTD_createDStream_advanced(ZSTD_defaultCMem);
}
ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
{
ZSTD_DStream* zds;
if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
if (!customMem.customAlloc || !customMem.customFree) return NULL;
zds = (ZSTD_DStream*) ZSTD_malloc(sizeof(ZSTD_DStream), customMem);
if (zds==NULL) return NULL;
memset(zds, 0, sizeof(ZSTD_DStream));
memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem));
zds->dctx = ZSTD_createDCtx_advanced(customMem);
if (zds->dctx == NULL) { ZSTD_freeDStream(zds); return NULL; }
zds->stage = zdss_init;
zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
return zds;
return ZSTD_createDCtx_advanced(customMem);
}
size_t ZSTD_freeDStream(ZSTD_DStream* zds)
{
if (zds==NULL) return 0; /* support free on null */
{ ZSTD_customMem const cMem = zds->customMem;
ZSTD_freeDCtx(zds->dctx);
zds->dctx = NULL;
ZSTD_freeDDict(zds->ddictLocal);
zds->ddictLocal = NULL;
ZSTD_free(zds->inBuff, cMem);
zds->inBuff = NULL;
ZSTD_free(zds->outBuff, cMem);
zds->outBuff = NULL;
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
if (zds->legacyContext)
ZSTD_freeLegacyStreamContext(zds->legacyContext, zds->previousLegacyVersion);
#endif
ZSTD_free(zds, cMem);
return 0;
}
return ZSTD_freeDCtx(zds);
}
/* *** Initialization *** */
size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; }
size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; }
size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; }
size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
{
zds->stage = zdss_loadHeader;
zds->streamStage = zdss_loadHeader;
zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
ZSTD_freeDDict(zds->ddictLocal);
if (dict && dictSize >= 8) {
@@ -2154,7 +2190,7 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict)
size_t ZSTD_resetDStream(ZSTD_DStream* zds)
{
zds->stage = zdss_loadHeader;
zds->streamStage = zdss_loadHeader;
zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
zds->legacyVersion = 0;
zds->hostageByte = 0;
@@ -2175,17 +2211,13 @@ size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds,
size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds)
{
if (zds==NULL) return 0; /* support sizeof NULL */
return sizeof(*zds)
+ ZSTD_sizeof_DCtx(zds->dctx)
+ ZSTD_sizeof_DDict(zds->ddictLocal)
+ zds->inBuffSize + zds->outBuffSize;
return ZSTD_sizeof_DCtx(zds);
}
size_t ZSTD_estimateDStreamSize(ZSTD_frameHeader fHeader)
{
size_t const windowSize = fHeader.windowSize;
size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
size_t const inBuffSize = blockSize; /* no block can be larger */
size_t const outBuffSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
return sizeof(ZSTD_DStream) + ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize;
@@ -2212,13 +2244,18 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
char* op = ostart;
U32 someMoreWork = 1;
DEBUGLOG(5, "ZSTD_decompressStream");
DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
if (zds->legacyVersion)
if (zds->legacyVersion) {
/* legacy support is incompatible with static dctx */
if (zds->staticSize) return ERROR(memory_allocation);
return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
}
#endif
while (someMoreWork) {
switch(zds->stage)
switch(zds->streamStage)
{
case zdss_init :
ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
@@ -2226,22 +2263,25 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
case zdss_loadHeader :
{ size_t const hSize = ZSTD_getFrameHeader(&zds->fParams, zds->headerBuffer, zds->lhSize);
if (ZSTD_isError(hSize))
if (ZSTD_isError(hSize)) {
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
{ U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
if (legacyVersion) {
const void* const dict = zds->ddict ? zds->ddict->dictContent : NULL;
size_t const dictSize = zds->ddict ? zds->ddict->dictSize : 0;
/* legacy support is incompatible with static dctx */
if (zds->staticSize) return ERROR(memory_allocation);
CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext, zds->previousLegacyVersion, legacyVersion,
dict, dictSize));
zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
} else {
return hSize; /* error */
} }
}
#else
return hSize;
#endif
}
if (hSize != 0) { /* need more input */
size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */
if (toLoad > (size_t)(iend-ip)) { /* not enough input to load full header */
@@ -2252,82 +2292,97 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
}
memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad;
break;
}
} }
/* check for single-pass mode opportunity */
if (zds->fParams.frameContentSize && zds->fParams.windowSize /* skippable frame if == 0 */
&& (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) {
size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
if (cSize <= (size_t)(iend-istart)) {
size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend-op, istart, cSize, zds->ddict);
if (ZSTD_isError(decompressedSize)) return decompressedSize;
ip = istart + cSize;
op += decompressedSize;
zds->dctx->expected = 0;
zds->stage = zdss_init;
someMoreWork = 0;
break;
} }
/* check for single-pass mode opportunity */
if (zds->fParams.frameContentSize && zds->fParams.windowSize /* skippable frame if == 0 */
&& (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) {
size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
if (cSize <= (size_t)(iend-istart)) {
size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
if (ZSTD_isError(decompressedSize)) return decompressedSize;
ip = istart + cSize;
op += decompressedSize;
zds->expected = 0;
zds->streamStage = zdss_init;
someMoreWork = 0;
break;
} }
/* Consume header */
CHECK_F(ZSTD_decompressBegin_usingDDict(zds->dctx, zds->ddict));
{ size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); /* == ZSTD_frameHeaderSize_prefix */
CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size));
{ size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);
CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer+h1Size, h2Size));
} }
/* Consume header (see ZSTDds_decodeFrameHeader) */
DEBUGLOG(5, "Consume header");
CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
if ((MEM_readLE32(zds->headerBuffer) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
zds->expected = MEM_readLE32(zds->headerBuffer + 4);
zds->stage = ZSTDds_skipFrame;
} else {
CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
zds->expected = ZSTD_blockHeaderSize;
zds->stage = ZSTDds_decodeBlockHeader;
}
/* Adapt buffer sizes to frame header instructions */
{ size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
size_t const neededOutSize = zds->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
zds->blockSize = blockSize;
if (zds->inBuffSize < blockSize) {
/* control buffer memory usage */
DEBUGLOG(5, "Control max buffer memory usage");
zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
/* Adapt buffer sizes to frame header instructions */
{ size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_MAX);
size_t const neededOutSize = zds->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
zds->blockSize = blockSize;
if ((zds->inBuffSize < blockSize) || (zds->outBuffSize < neededOutSize)) {
size_t const bufferSize = blockSize + neededOutSize;
DEBUGLOG(5, "inBuff : from %u to %u",
(U32)zds->inBuffSize, (U32)blockSize);
DEBUGLOG(5, "outBuff : from %u to %u",
(U32)zds->outBuffSize, (U32)neededOutSize);
if (zds->staticSize) { /* static DCtx */
DEBUGLOG(5, "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);
} else {
ZSTD_free(zds->inBuff, zds->customMem);
zds->inBuffSize = 0;
zds->inBuff = (char*)ZSTD_malloc(blockSize, zds->customMem);
if (zds->inBuff == NULL) return ERROR(memory_allocation);
zds->inBuffSize = blockSize;
}
if (zds->outBuffSize < neededOutSize) {
ZSTD_free(zds->outBuff, zds->customMem);
zds->outBuffSize = 0;
zds->outBuff = (char*)ZSTD_malloc(neededOutSize, zds->customMem);
if (zds->outBuff == NULL) return ERROR(memory_allocation);
zds->outBuffSize = neededOutSize;
} }
zds->stage = zdss_read;
}
zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem);
if (zds->inBuff == NULL) return ERROR(memory_allocation);
}
zds->inBuffSize = blockSize;
zds->outBuff = zds->inBuff + zds->inBuffSize;
zds->outBuffSize = neededOutSize;
} }
zds->streamStage = zdss_read;
/* pass-through */
case zdss_read:
{ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
DEBUGLOG(5, "stage zdss_read");
{ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize);
if (neededInSize==0) { /* end of frame */
zds->stage = zdss_init;
zds->streamStage = zdss_init;
someMoreWork = 0;
break;
}
if ((size_t)(iend-ip) >= neededInSize) { /* decode directly from src */
const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
int const isSkipFrame = ZSTD_isSkipFrame(zds);
size_t const decodedSize = ZSTD_decompressContinue(zds,
zds->outBuff + zds->outStart, (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart),
ip, neededInSize);
if (ZSTD_isError(decodedSize)) return decodedSize;
ip += neededInSize;
if (!decodedSize && !isSkipFrame) break; /* this was just a header */
zds->outEnd = zds->outStart + decodedSize;
zds->stage = zdss_flush;
zds->streamStage = zdss_flush;
break;
}
if (ip==iend) { someMoreWork = 0; break; } /* no more input */
zds->stage = zdss_load;
/* pass-through */
}
} }
if (ip==iend) { someMoreWork = 0; break; } /* no more input */
zds->streamStage = zdss_load;
/* pass-through */
case zdss_load:
{ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
{ size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
size_t const toLoad = neededInSize - zds->inPos; /* should always be <= remaining space within inBuff */
size_t loadedSize;
if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected); /* should never happen */
@@ -2337,17 +2392,17 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
if (loadedSize < toLoad) { someMoreWork = 0; break; } /* not enough input, wait for more */
/* decode loaded input */
{ const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
{ const int isSkipFrame = ZSTD_isSkipFrame(zds);
size_t const decodedSize = ZSTD_decompressContinue(zds,
zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart,
zds->inBuff, neededInSize);
if (ZSTD_isError(decodedSize)) return decodedSize;
zds->inPos = 0; /* input is consumed */
if (!decodedSize && !isSkipFrame) { zds->stage = zdss_read; break; } /* this was just a header */
if (!decodedSize && !isSkipFrame) { zds->streamStage = zdss_read; break; } /* this was just a header */
zds->outEnd = zds->outStart + decodedSize;
zds->stage = zdss_flush;
/* pass-through */
} }
zds->streamStage = zdss_flush;
/* pass-through */
case zdss_flush:
{ size_t const toFlushSize = zds->outEnd - zds->outStart;
@@ -2355,37 +2410,41 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
op += flushedSize;
zds->outStart += flushedSize;
if (flushedSize == toFlushSize) { /* flush completed */
zds->stage = zdss_read;
zds->streamStage = zdss_read;
if (zds->outStart + zds->blockSize > zds->outBuffSize)
zds->outStart = zds->outEnd = 0;
break;
}
/* cannot complete flush */
someMoreWork = 0;
break;
}
} }
/* cannot complete flush */
someMoreWork = 0;
break;
default: return ERROR(GENERIC); /* impossible */
} }
/* result */
input->pos += (size_t)(ip-istart);
output->pos += (size_t)(op-ostart);
{ size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx);
{ size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds);
if (!nextSrcSizeHint) { /* frame fully decoded */
if (zds->outEnd == zds->outStart) { /* output fully flushed */
if (zds->hostageByte) {
if (input->pos >= input->size) { zds->stage = zdss_read; return 1; } /* can't release hostage (not present) */
if (input->pos >= input->size) {
/* can't release hostage (not present) */
zds->streamStage = zdss_read;
return 1;
}
input->pos++; /* release hostage */
}
} /* zds->hostageByte */
return 0;
}
} /* zds->outEnd == zds->outStart */
if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */
zds->hostageByte=1;
}
return 1;
}
nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block); /* preload header of next block */
} /* nextSrcSizeHint==0 */
nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block); /* preload header of next block */
if (zds->inPos > nextSrcSizeHint) return ERROR(GENERIC); /* should never happen */
nextSrcSizeHint -= zds->inPos; /* already loaded*/
return nextSrcSizeHint;
lib/dictBuilder/zdict.c
+4 -4
View File
@@ -576,7 +576,7 @@ typedef struct
{
ZSTD_CCtx* ref;
ZSTD_CCtx* zc;
void* workPlace; /* must be ZSTD_BLOCKSIZE_ABSOLUTEMAX allocated */
void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */
} EStats_ress_t;
#define MAXREPOFFSET 1024
@@ -585,14 +585,14 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
U32* countLit, U32* offsetcodeCount, U32* matchlengthCount, U32* litlengthCount, U32* repOffsets,
const void* src, size_t srcSize, U32 notificationLevel)
{
size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << params.cParams.windowLog);
size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_MAX, 1 << params.cParams.windowLog);
size_t cSize;
if (srcSize > blockSizeMax) srcSize = blockSizeMax; /* protection vs large samples */
{ size_t const errorCode = ZSTD_copyCCtx(esr.zc, esr.ref, 0);
if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
}
cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize);
cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_MAX, src, srcSize);
if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
if (cSize) { /* if == 0; block is not compressible */
@@ -700,7 +700,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
/* init */
esr.ref = ZSTD_createCCtx();
esr.zc = ZSTD_createCCtx();
esr.workPlace = malloc(ZSTD_BLOCKSIZE_ABSOLUTEMAX);
esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
if (!esr.ref || !esr.zc || !esr.workPlace) {
eSize = ERROR(memory_allocation);
DISPLAYLEVEL(1, "Not enough memory \n");
lib/zstd.h
+376 -72
View File
@@ -38,20 +38,21 @@ extern "C" {
/*******************************************************************************************************
Introduction
zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios
at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and
decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22.
zstd, short for Zstandard, is a fast lossless compression algorithm,
targeting real-time compression scenarios at zlib-level and better compression ratios.
The zstd compression library provides in-memory compression and decompression functions.
The library supports compression levels from 1 up to ZSTD_maxCLevel() which is currently 22.
Levels >= 20, labeled `--ultra`, should be used with caution, as they require more memory.
Compression can be done in:
- a single step (described as Simple API)
- a single step, reusing a context (described as Explicit memory management)
- unbounded multiple steps (described as Streaming compression)
The compression ratio achievable on small data can be highly improved using compression with a dictionary in:
The compression ratio achievable on small data can be highly improved using a dictionary in:
- a single step (described as Simple dictionary API)
- a single step, reusing a dictionary (described as Fast dictionary API)
Advanced experimental functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h.
These APIs shall never be used with a dynamic library.
Advanced experimental APIs shall never be used with a dynamic library.
They are not "stable", their definition may change in the future. Only static linking is allowed.
*********************************************************************************************************/
@@ -61,13 +62,13 @@ extern "C" {
#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 be used when checking dll version */
ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< useful to check dll version */
#define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE
#define ZSTD_QUOTE(str) #str
#define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str)
#define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
ZSTDLIB_API const char* ZSTD_versionString(void);
ZSTDLIB_API const char* ZSTD_versionString(void); /* >= v1.3.0 */
/***************************************
@@ -84,7 +85,7 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity,
/*! ZSTD_decompress() :
* `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
* `dstCapacity` is an upper bound of originalSize.
* `dstCapacity` is an upper bound of originalSize to regenerate.
* If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
* @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
* or an errorCode if it fails (which can be tested using ZSTD_isError()). */
@@ -92,21 +93,17 @@ ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
const void* src, size_t compressedSize);
/*! ZSTD_getDecompressedSize() :
* NOTE: This function is planned to be obsolete, in favour of ZSTD_getFrameContentSize.
* ZSTD_getFrameContentSize functions the same way, returning the decompressed size of a single
* frame, but distinguishes empty frames from frames with an unknown size, or errors.
*
* Additionally, ZSTD_findDecompressedSize can be used instead. It can handle multiple
* concatenated frames in one buffer, and so is more general.
* As a result however, it requires more computation and entire frames to be passed to it,
* as opposed to ZSTD_getFrameContentSize which requires only a single frame's header.
* NOTE: This function is planned to be obsolete, in favor of ZSTD_getFrameContentSize().
* ZSTD_getFrameContentSize() works the same way,
* returning the decompressed size of a single frame,
* but distinguishes empty frames from frames with an unknown size, or errors.
*
* 'src' is the start of a zstd compressed frame.
* @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise.
* note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
* note 1 : decompressed size is an optional field, it may not be present, typically in streaming mode.
* When `return==0`, data to decompress could be any size.
* In which case, it's necessary to use streaming mode to decompress data.
* Optionally, application can still use ZSTD_decompress() while relying on implied limits.
* Optionally, application can use ZSTD_decompress() while relying on implied limits.
* (For example, data may be necessarily cut into blocks <= 16 KB).
* note 2 : decompressed size is always present when compression is done with ZSTD_compress()
* note 3 : decompressed size can be very large (64-bits value),
@@ -115,7 +112,7 @@ ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
* note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
* Always ensure result fits within application's authorized limits.
* Each application can set its own limits.
* note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameParams() to know more. */
* note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameHeader() to know more. */
ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
@@ -140,29 +137,35 @@ ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx);
/*! ZSTD_compressCCtx() :
* Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()). */
ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel);
/*= Decompression context
* When decompressing many times,
* it is recommended to allocate a context just once, and re-use it for each successive compression operation.
* it is recommended to allocate a context only once,
* and re-use it for each successive compression operation.
* This will make workload friendlier for system's memory.
* Use one context per thread for parallel execution in multi-threaded environments. */
* Use one context per thread for parallel execution. */
typedef struct ZSTD_DCtx_s ZSTD_DCtx;
ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void);
ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
/*! ZSTD_decompressDCtx() :
* Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()). */
ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
* Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) */
ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize);
/**************************
* Simple dictionary API
***************************/
/*! ZSTD_compress_usingDict() :
* Compression using a predefined Dictionary (see dictBuilder/zdict.h).
* Note : This function loads the dictionary, resulting in significant startup delay.
* Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
* Compression using a predefined Dictionary (see dictBuilder/zdict.h).
* Note : This function loads the dictionary, resulting in significant startup delay.
* Note : 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,
@@ -170,30 +173,31 @@ ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
int compressionLevel);
/*! ZSTD_decompress_usingDict() :
* Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
* Dictionary must be identical to the one used during compression.
* Note : This function loads the dictionary, resulting in significant startup delay.
* Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
* Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
* Dictionary must be identical to the one used during compression.
* Note : This function loads the dictionary, resulting in significant startup delay.
* 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);
/****************************
* Fast dictionary API
****************************/
/**********************************
* Bulk processing dictionary API
*********************************/
typedef struct ZSTD_CDict_s ZSTD_CDict;
/*! ZSTD_createCDict() :
* When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
* ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
* ZSTD_CDict can be created once and used by multiple threads concurrently, as its usage is read-only.
* `dictBuffer` can be released after ZSTD_CDict creation, as its content is copied within CDict */
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, int compressionLevel);
* When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
* ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
* 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, since its content is copied within CDict */
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
int compressionLevel);
/*! ZSTD_freeCDict() :
* Function frees memory allocated by ZSTD_createCDict(). */
* Function frees memory allocated by ZSTD_createCDict(). */
ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict);
/*! ZSTD_compress_usingCDict() :
@@ -210,17 +214,17 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
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 */
* 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() */
* Function frees memory allocated with ZSTD_createDDict() */
ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict);
/*! ZSTD_decompress_usingDDict() :
* Decompression using a digested Dictionary.
* Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */
* Decompression using a digested Dictionary.
* Faster startup than ZSTD_decompress_usingDict(), 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,
@@ -277,15 +281,17 @@ typedef struct ZSTD_outBuffer_s {
* 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.
* Similar to ZSTD_flushStream(), it may not be able to flush the full content if `output->size` is too small.
* ZSTD_endStream() may not be able to flush full data if `output->size` is too small.
* In which case, call again ZSTD_endStream() to complete the flush.
* @return : nb of bytes still present within internal buffer (0 if it's empty, hence compression completed)
* @return : 0 if frame fully completed and fully flushed,
or >0 if some data is still present within internal buffer
(value is minimum size estimation for remaining data to flush, but it could be more)
* or an error code, which can be tested using ZSTD_isError().
*
* *******************************************************************/
typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are effectively same object */
/* Continue due distinghish them for compatibility with versions <= v1.2.0 */
typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
/* But continue to distinguish them for compatibility with versions <= v1.2.0 */
/*===== ZSTD_CStream management functions =====*/
ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
@@ -323,7 +329,8 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output
* The return value is a suggested next input size (a hint to improve latency) that will never load more than the current frame.
* *******************************************************************************/
typedef struct ZSTD_DStream_s ZSTD_DStream;
typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
/* But continue to distinguish them for compatibility with versions <= v1.2.0 */
/*===== ZSTD_DStream management functions =====*/
ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
@@ -338,8 +345,6 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output
#endif /* ZSTD_H_235446 */
#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
/****************************************************************************************
* START OF ADVANCED AND EXPERIMENTAL FUNCTIONS
@@ -349,6 +354,9 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output
* 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
/* --- Constants ---*/
#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */
#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U
@@ -378,7 +386,8 @@ static const size_t ZSTD_skippableHeaderSize = 8; /* magic number + skippable f
/*--- Advanced types ---*/
typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; /* from faster to stronger */
typedef enum { ZSTD_fast=1, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2,
ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; /* from faster to stronger */
typedef struct {
unsigned windowLog; /**< largest match distance : larger == more compression, more memory needed during decompression */
@@ -412,6 +421,9 @@ typedef struct {
typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
typedef void (*ZSTD_freeFunction) (void* opaque, void* address);
typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
/* use this constant to defer to stdlib's functions */
static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
/***************************************
* Frame size functions
@@ -485,21 +497,22 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
* These functions make it possible to estimate memory usage
* of a future target object, before its allocation,
* given a set of parameters, which vary depending on target object.
* The objective is to guide decision before allocation. */
* The objective is to guide decision before allocation.
* Note : CCtx estimation is only correct for single-threaded compression */
ZSTDLIB_API size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams);
ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
/*! ZSTD_estimate?StreamSize() :
* Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
* an internal ?Dict will be created, which size is not estimated.
* In this case, get additional size by using ZSTD_estimate?DictSize */
* an internal ?Dict will be created, which size is not estimated here.
* In this case, get total size by adding ZSTD_estimate?DictSize */
ZSTDLIB_API size_t ZSTD_estimateCStreamSize(ZSTD_compressionParameters cParams);
ZSTDLIB_API size_t ZSTD_estimateDStreamSize(ZSTD_frameHeader fHeader);
/*! ZSTD_estimate?DictSize() :
* Note : if dictionary is created "byReference", reduce estimation by dictSize */
ZSTDLIB_API size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize);
ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize);
* Note : dictionary created "byReference" are smaller */
ZSTDLIB_API size_t ZSTD_estimateCDictSize(ZSTD_compressionParameters cParams, size_t dictSize, unsigned byReference);
ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference);
/***************************************
@@ -509,6 +522,25 @@ ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize);
* Create a ZSTD compression context using external alloc and free functions */
ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
/*! ZSTD_initStaticCCtx() : initialize a fixed-size zstd compression context
* workspace: The memory area to emplace the context into.
* Provided pointer must 8-bytes aligned.
* It must outlive context usage.
* workspaceSize: Use ZSTD_estimateCCtxSize() or ZSTD_estimateCStreamSize()
* to determine how large workspace must be to support scenario.
* @return : pointer to ZSTD_CCtx*, or NULL if error (size too small)
* Note : zstd will never resize nor malloc() when using a static cctx.
* If it needs more memory than available, it will simply error out.
* Note 2 : there is no corresponding "free" function.
* Since workspace was allocated externally, it must be freed externally too.
* Limitation 1 : currently not compatible with internal CDict creation, such as
* ZSTD_CCtx_loadDictionary() or ZSTD_initCStream_usingDict().
* Limitation 2 : currently not compatible with multi-threading
*/
ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize);
/* !!! To be deprecated !!! */
typedef enum {
ZSTD_p_forceWindow, /* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0) */
ZSTD_p_forceRawDict /* Force loading dictionary in "content-only" mode (no header analysis) */
@@ -518,17 +550,40 @@ typedef enum {
* @result : 0, or an error code (which can be tested with ZSTD_isError()) */
ZSTDLIB_API size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value);
/*! ZSTD_createCDict_byReference() :
* Create a digested dictionary for compression
* Dictionary content is simply referenced, and therefore stays in dictBuffer.
* It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict */
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
typedef enum { ZSTD_dm_auto=0, ZSTD_dm_rawContent, ZSTD_dm_fullDict } ZSTD_dictMode_e;
/*! ZSTD_createCDict_advanced() :
* Create a ZSTD_CDict using external alloc and free, and customized compression parameters */
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference,
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams, ZSTD_customMem customMem);
/*! ZSTD_initStaticCDict_advanced() :
* Generate a digested dictionary in provided memory area.
* workspace: The memory area to emplace the dictionary into.
* Provided pointer must 8-bytes aligned.
* It must outlive dictionary usage.
* workspaceSize: Use ZSTD_estimateCDictSize()
* to determine how large workspace must be.
* cParams : use ZSTD_getCParams() to transform a compression level
* into its relevants cParams.
* @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
* Note : there is no corresponding "free" function.
* Since workspace was allocated externally, it must be freed externally.
*/
ZSTDLIB_API ZSTD_CDict* ZSTD_initStaticCDict(
void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams);
/*! ZSTD_getCParams() :
* @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
* `estimatedSrcSize` value is optional, select 0 if not known */
@@ -544,8 +599,8 @@ ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long l
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. */
* optimize params for a given `srcSize` and `dictSize`.
* both values are optional, select `0` if unknown. */
ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
/*! ZSTD_compress_advanced() :
@@ -577,10 +632,28 @@ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
* Create a ZSTD decompression context using external alloc and free functions */
ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
/*! ZSTD_initStaticDCtx() : initialize a fixed-size zstd decompression context
* workspace: The memory area to emplace the context into.
* Provided pointer must 8-bytes aligned.
* It must outlive context usage.
* workspaceSize: Use ZSTD_estimateDCtxSize() or ZSTD_estimateDStreamSize()
* to determine how large workspace must be to support scenario.
* @return : pointer to ZSTD_DCtx*, or NULL if error (size too small)
* Note : zstd will never resize nor malloc() when using a static dctx.
* If it needs more memory than available, it will simply error out.
* Note 2 : static dctx is incompatible with legacy support
* Note 3 : there is no corresponding "free" function.
* Since workspace was allocated externally, it must be freed externally.
* Limitation : currently not compatible with internal DDict creation,
* such as ZSTD_initDStream_usingDict().
*/
ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize);
/*! ZSTD_createDDict_byReference() :
* Create a digested dictionary, ready to start decompression operation without startup delay.
* Dictionary content is simply referenced, and therefore stays in dictBuffer.
* It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict */
* Dictionary content is referenced, and therefore stays in dictBuffer.
* It is important that dictBuffer outlives DDict,
* it must remain read accessible throughout the lifetime of DDict */
ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
/*! ZSTD_createDDict_advanced() :
@@ -588,6 +661,21 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, siz
ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
unsigned byReference, ZSTD_customMem customMem);
/*! ZSTD_initStaticDDict() :
* Generate a digested dictionary in provided memory area.
* workspace: The memory area to emplace the dictionary into.
* Provided pointer must 8-bytes aligned.
* It must outlive dictionary usage.
* workspaceSize: Use ZSTD_estimateDDictSize()
* to determine how large workspace must be.
* @return : pointer to ZSTD_DDict*, or NULL if error (size too small)
* Note : there is no corresponding "free" function.
* Since workspace was allocated externally, it must be freed externally.
*/
ZSTDLIB_API ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
const void* dict, size_t dictSize,
unsigned byReference);
/*! ZSTD_getDictID_fromDict() :
* Provides the dictID stored within dictionary.
* if @return == 0, the dictionary is not conformant with Zstandard specification.
@@ -609,7 +697,7 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
* 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_getFrameParams(), which will provide a more precise error code. */
* 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);
@@ -620,11 +708,11 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
/*===== Advanced Streaming compression functions =====*/
ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */
ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< note: a dict will not be used if dict == NULL or dictSize < 8. This result in the creation of an internal CDict */
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. */
ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */
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, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
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 */
/*! ZSTD_resetCStream() :
* start a new compression job, using same parameters from previous job.
@@ -704,7 +792,7 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
A ZSTD_DCtx object can be re-used multiple times.
First typical operation is to retrieve frame parameters, using ZSTD_getFrameParams().
First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
It fills a ZSTD_frameParams structure which provide important information to correctly decode the frame,
such as the minimum rolling buffer size to allocate to decompress data (`windowSize`),
and the dictionary ID used.
@@ -751,7 +839,7 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
c) Frame Content - any content (User Data) of length equal to Frame Size
For skippable frames ZSTD_decompressContinue() always returns 0.
For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
For skippable frames ZSTD_getFrameHeader() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
Note : If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might actually be a Zstd encoded frame with no content.
For purposes of decompression, it is valid in both cases to skip the frame using
ZSTD_findFrameCompressedSize to find its size in bytes.
@@ -770,6 +858,221 @@ ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t ds
typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
/*=== New advanced API (experimental, and compression only) ===*/
/* notes on API design :
* In this proposal, parameters are pushed one by one into an existing CCtx,
* and then applied on all subsequent compression jobs.
* When no parameter is ever provided, CCtx is created with compression level ZSTD_CLEVEL_DEFAULT.
*
* This API is intended to replace all others experimental API.
* It can basically do all other use cases, and even new ones.
* It stands a good chance to become "stable",
* after a reasonable testing period.
*/
/* note on naming convention :
* Initially, the API favored names like ZSTD_setCCtxParameter() .
* In this proposal, convention is changed towards ZSTD_CCtx_setParameter() .
* The main driver is that it identifies more clearly the target object type.
* It feels clearer in light of potential variants :
* ZSTD_CDict_setParameter() (rather than ZSTD_setCDictParameter())
* ZSTD_DCtx_setParameter() (rather than ZSTD_setDCtxParameter() )
* Left variant feels easier to distinguish.
*/
/* note on enum design :
* All enum will be manually set to explicit values before reaching "stable API" status */
typedef enum {
/* compression parameters */
ZSTD_p_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table
* Default level is ZSTD_CLEVEL_DEFAULT==3.
* Special: value 0 means "do not change cLevel". */
ZSTD_p_windowLog, /* Maximum allowed back-reference distance, expressed as power of 2.
* Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX.
* Special: value 0 means "do not change windowLog". */
ZSTD_p_hashLog, /* Size of the probe table, as a power of 2.
* Resulting table size is (1 << (hashLog+2)).
* Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX.
* Larger tables improve compression ratio of strategies <= dFast,
* and improve speed of strategies > dFast.
* Special: value 0 means "do not change hashLog". */
ZSTD_p_chainLog, /* Size of the full-search table, as a power of 2.
* Resulting table size is (1 << (chainLog+2)).
* Larger tables result in better and slower compression.
* This parameter is useless when using "fast" strategy.
* Special: value 0 means "do not change chainLog". */
ZSTD_p_searchLog, /* Number of search attempts, as a power of 2.
* More attempts result in better and slower compression.
* This parameter is useless when using "fast" and "dFast" strategies.
* Special: value 0 means "do not change searchLog". */
ZSTD_p_minMatch, /* Minimum size of searched matches (note : repCode matches can be smaller).
* Larger values make faster compression and decompression, but decrease ratio.
* Must be clamped between ZSTD_SEARCHLENGTH_MIN and ZSTD_SEARCHLENGTH_MAX.
* Note that currently, for all strategies < btopt, effective minimum is 4.
* Note that currently, for all strategies > fast, effective maximum is 6.
* Special: value 0 means "do not change minMatchLength". */
ZSTD_p_targetLength, /* Only useful for strategies >= btopt.
* Length of Match considered "good enough" to stop search.
* Larger values make compression stronger and slower.
* Special: value 0 means "do not change targetLength". */
ZSTD_p_compressionStrategy, /* See ZSTD_strategy enum definition.
* Cast selected strategy as unsigned for ZSTD_CCtx_setParameter() compatibility.
* The higher the value of selected strategy, the more complex it is,
* resulting in stronger and slower compression.
* Special: value 0 means "do not change strategy". */
#if 0
ZSTD_p_windowSize, /* Maximum allowed back-reference distance.
* Can be set to a more precise value than windowLog.
* Will be transparently reduced to closest possible inferior value
* (see Zstandard compression format) */
/* Not ready yet ! */
#endif
/* frame parameters */
ZSTD_p_contentSizeFlag=200, /* Content size is written into frame header _whenever known_ (default:1) */
ZSTD_p_checksumFlag, /* A 32-bits checksum of content is written at end of frame (default:0) */
ZSTD_p_dictIDFlag, /* When applicable, dictID of dictionary is provided in frame header (default:1) */
/* dictionary parameters */
ZSTD_p_refDictContent=300, /* Content of dictionary content will be referenced, instead of copied (default:0).
* This avoids duplicating dictionary content.
* But it also requires that dictionary buffer outlives its users */
/* Not ready yet ! <=================================== */
ZSTD_p_dictMode, /* Select how dictionary must be interpreted. Value must be from type ZSTD_dictMode_e.
* default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
/* multi-threading parameters */
ZSTD_p_nbThreads=400, /* Select how many threads a compression job can spawn (default:1)
* More threads improve speed, but also increase memory usage.
* Can only receive a value > 1 if ZSTD_MULTITHREAD is enabled.
* Special: value 0 means "do not change nbThreads" */
ZSTD_p_jobSize, /* Size of a compression job. Each compression job is completed in parallel.
* 0 means default, which is dynamically determined based on compression parameters.
* Job size must be a minimum of overlapSize, or 1 KB, whichever is largest
* The minimum size is automatically and transparently enforced */
ZSTD_p_overlapSizeLog, /* Size of previous input reloaded at the beginning of each job.
* 0 => no overlap, 6(default) => use 1/8th of windowSize, >=9 => use full windowSize */
/* advanced parameters - may not remain available after API update */
ZSTD_p_forceMaxWindow=1100, /* Force back-references to remain < windowSize,
* even when referencing into Dictionary content.
* default : 0 when using a CDict, 1 when using a Prefix */
} ZSTD_cParameter;
/*! ZSTD_CCtx_setParameter() :
* Set one compression parameter, selected by enum ZSTD_cParameter.
* Note : when `value` is an enum, cast it to unsigned for proper type checking.
* @result : 0, or an error code (which can be tested with ZSTD_isError()). */
ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value);
/*! ZSTD_CCtx_setPledgedSrcSize() :
* Total input data size to be compressed as a single frame.
* This value will be controlled at the end, and result in error if not respected.
* @result : 0, or an error code (which can be tested with ZSTD_isError()).
* Note 1 : 0 means zero, empty.
* In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
* Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
* Note 2 : If all data is provided and consumed in a single round,
* this value is overriden by srcSize instead. */
ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
/*! ZSTD_CCtx_loadDictionary() :
* Create an internal CDict from dict buffer.
* Decompression will have to use same buffer.
* @result : 0, or an error code (which can be tested with ZSTD_isError()).
* Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary,
* meaning "return to no-dictionary mode".
* Note 1 : Dictionary content will be copied internally,
* except if ZSTD_p_refDictContent is set.
* Note 2 : Loading a dictionary involves building tables, which are dependent on compression parameters.
* For this reason, compression parameters cannot be changed anymore after loading a dictionary.
* It's also a CPU-heavy operation, with non-negligible impact on latency.
* Note 3 : Dictionary will be used for all future compression jobs.
* To return to "no-dictionary" situation, load a NULL dictionary */
ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
/*! ZSTD_CCtx_refCDict() :
* Ref a prepared dictionary, to be used for all next compression jobs.
* 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 compression jobs using same CCtx.
* @result : 0, or an error code (which can be tested with ZSTD_isError()).
* Special : adding a NULL CDict means "return to no-dictionary mode".
* Note 1 : Currently, only one dictionary can be managed.
* Adding a new dictionary effectively "discards" any previous one.
* Note 2 : CDict is just referenced, its lifetime must outlive CCtx.
*/
ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
/*! ZSTD_CCtx_refPrefix() :
* Reference a prefix (content-only dictionary) to bootstrap next compression job.
* Decompression will have to use same prefix.
* Prefix is only used once. Tables are discarded at end of compression job.
* If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict.
* @result : 0, or an error code (which can be tested with ZSTD_isError()).
* Special : Adding a NULL (or 0-size) dictionary invalidates any previous prefix, meaning "return to no-dictionary mode".
* Note 1 : Prefix buffer is referenced. It must outlive compression job.
* Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
* It's a CPU-heavy operation, with non-negligible impact on latency. */
ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); /* Not ready yet ! <===================================== */
typedef enum {
ZSTD_e_continue=0, /* collect more data, encoder transparently decides when to output result, for optimal conditions */
ZSTD_e_flush, /* flush any data provided so far - frame will continue, future data can still reference previous data for better compression */
ZSTD_e_end /* flush any remaining data and ends current frame. Any future compression starts a new frame. */
} ZSTD_EndDirective;
/*! ZSTD_compress_generic() :
* Behave about the same as ZSTD_compressStream. To note :
* - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_setParameter()
* - Compression parameters cannot be changed once compression is started.
* - *dstPos must be <= dstCapacity, *srcPos must be <= srcSize
* - *dspPos and *srcPos will be updated. They are guaranteed to remain below their respective limit.
* - @return provides the minimum amount of data still to flush from internal buffers
* or an error code, which can be tested using ZSTD_isError().
* if @return != 0, flush is not fully completed, there is some data left within internal buffers.
* - after a ZSTD_e_end directive, if internal buffer is not fully flushed,
* only ZSTD_e_end or ZSTD_e_flush operations are allowed.
* It is necessary to fully flush internal buffers
* before starting a new compression job, or changing compression parameters.
*/
ZSTDLIB_API size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
ZSTD_outBuffer* output,
ZSTD_inBuffer* input,
ZSTD_EndDirective endOp);
/*! ZSTD_CCtx_reset() :
* Return a CCtx to clean state.
* Useful after an error, or to interrupt an ongoing compression job and start a new one.
* Any internal data not yet flushed is cancelled.
* Dictionary (if any) is dropped.
* It's possible to modify compression parameters after a reset.
*/
ZSTDLIB_API void ZSTD_CCtx_reset(ZSTD_CCtx* cctx); /* Not ready yet ! */
/*! ZSTD_compress_generic_simpleArgs() :
* Same as ZSTD_compress_generic(),
* but using only integral types as arguments.
* Argument list is larger and less expressive than ZSTD_{in,out}Buffer,
* but can be helpful for binders from dynamic languages
* which have troubles handling structures containing memory pointers.
*/
size_t ZSTD_compress_generic_simpleArgs (
ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity, size_t* dstPos,
const void* src, size_t srcSize, size_t* srcPos,
ZSTD_EndDirective endOp);
/**
Block functions
@@ -784,7 +1087,7 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+ compression : any ZSTD_compressBegin*() variant, including with dictionary
+ decompression : any ZSTD_decompressBegin*() variant, including with dictionary
+ copyCCtx() and copyDCtx() can be used too
- Block size is limited, it must be <= ZSTD_getBlockSizeMax() <= ZSTD_BLOCKSIZE_ABSOLUTEMAX
- Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX
+ If input is larger than a block size, it's necessary to split input data into multiple blocks
+ For inputs larger than a single block size, consider using the regular ZSTD_compress() instead.
Frame metadata is not that costly, and quickly becomes negligible as source size grows larger.
@@ -797,9 +1100,10 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
Use ZSTD_insertBlock() for such a case.
*/
#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) /* define, for static allocation */
#define ZSTD_BLOCKSIZELOG_MAX 17
#define ZSTD_BLOCKSIZE_MAX (1<<ZSTD_BLOCKSIZELOG_MAX) /* define, for static allocation */
/*===== Raw zstd block functions =====*/
ZSTDLIB_API size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx);
ZSTDLIB_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx);
ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
ZSTDLIB_API size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /**< insert block into `dctx` history. Useful for uncompressed blocks */
programs/bench.c
+48 -20
View File
@@ -86,14 +86,13 @@ static clock_t g_time = 0;
#ifndef DEBUG
# define DEBUG 0
#endif
#define DEBUGOUTPUT(...) if (DEBUG) DISPLAY(__VA_ARGS__);
#define EXM_THROW(error, ...) \
{ \
DEBUGOUTPUT("%s: %i: \n", __FILE__, __LINE__); \
DISPLAYLEVEL(1, "Error %i : ", error); \
DISPLAYLEVEL(1, __VA_ARGS__); \
DISPLAYLEVEL(1, " \n"); \
exit(error); \
#define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }
#define EXM_THROW(error, ...) { \
DEBUGOUTPUT("%s: %i: \n", __FILE__, __LINE__); \
DISPLAYLEVEL(1, "Error %i : ", error); \
DISPLAYLEVEL(1, __VA_ARGS__); \
DISPLAYLEVEL(1, " \n"); \
exit(error); \
}
@@ -159,7 +158,6 @@ static int BMK_benchMem(const void* srcBuffer, size_t srcSize,
const ZSTD_compressionParameters* comprParams)
{
size_t const blockSize = ((g_blockSize>=32 && !g_decodeOnly) ? g_blockSize : srcSize) + (!srcSize) /* avoid div by 0 */ ;
size_t const avgSize = MIN(blockSize, (srcSize / nbFiles));
U32 const maxNbBlocks = (U32) ((srcSize + (blockSize-1)) / blockSize) + nbFiles;
blockParam_t* const blockTable = (blockParam_t*) malloc(maxNbBlocks * sizeof(blockParam_t));
size_t const maxCompressedSize = ZSTD_compressBound(srcSize) + (maxNbBlocks * 1024); /* add some room for safety */
@@ -262,42 +260,72 @@ static int BMK_benchMem(const void* srcBuffer, size_t srcSize,
UTIL_getTime(&clockStart);
if (!cCompleted) { /* still some time to do compression tests */
ZSTD_customMem const cmem = { NULL, NULL, NULL };
U64 const clockLoop = g_nbSeconds ? TIMELOOP_MICROSEC : 1;
U32 nbLoops = 0;
ZSTD_CDict* cdict = NULL;
#ifdef ZSTD_NEWAPI
ZSTD_CCtx_setParameter(ctx, ZSTD_p_nbThreads, g_nbThreads);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_compressionLevel, cLevel);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_windowLog, comprParams->windowLog);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_chainLog, comprParams->chainLog);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_searchLog, comprParams->searchLog);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_minMatch, comprParams->searchLength);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_targetLength, comprParams->targetLength);
ZSTD_CCtx_setParameter(ctx, ZSTD_p_compressionStrategy, comprParams->strategy);
ZSTD_CCtx_loadDictionary(ctx, dictBuffer, dictBufferSize);
#else
size_t const avgSize = MIN(blockSize, (srcSize / nbFiles));
ZSTD_parameters zparams = ZSTD_getParams(cLevel, avgSize, dictBufferSize);
ZSTD_CDict* cdict;
ZSTD_customMem const cmem = { NULL, NULL, NULL };
if (comprParams->windowLog) zparams.cParams.windowLog = comprParams->windowLog;
if (comprParams->chainLog) zparams.cParams.chainLog = comprParams->chainLog;
if (comprParams->hashLog) zparams.cParams.hashLog = comprParams->hashLog;
if (comprParams->searchLog) zparams.cParams.searchLog = comprParams->searchLog;
if (comprParams->searchLength) zparams.cParams.searchLength = comprParams->searchLength;
if (comprParams->targetLength) zparams.cParams.targetLength = comprParams->targetLength;
if (comprParams->strategy) zparams.cParams.strategy = (ZSTD_strategy)(comprParams->strategy - 1);
cdict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, 1, zparams.cParams, cmem);
if (comprParams->strategy) zparams.cParams.strategy = comprParams->strategy;
cdict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, 1 /*byRef*/, ZSTD_dm_auto, zparams.cParams, cmem);
if (cdict==NULL) EXM_THROW(1, "ZSTD_createCDict_advanced() allocation failure");
#endif
do {
U32 blockNb;
size_t rSize;
for (blockNb=0; blockNb<nbBlocks; blockNb++) {
size_t rSize;
#ifdef ZSTD_NEWAPI
ZSTD_outBuffer out = { blockTable[blockNb].cPtr, blockTable[blockNb].cRoom, 0 };
ZSTD_inBuffer in = { blockTable[blockNb].srcPtr, blockTable[blockNb].srcSize, 0 };
size_t cError = 1;
while (cError) {
cError = ZSTD_compress_generic(ctx,
&out, &in, ZSTD_e_end);
if (ZSTD_isError(cError))
EXM_THROW(1, "ZSTD_compress_generic() error : %s",
ZSTD_getErrorName(cError));
}
rSize = out.pos;
#else /* ! ZSTD_NEWAPI */
if (dictBufferSize) {
rSize = ZSTD_compress_usingCDict(ctx,
blockTable[blockNb].cPtr, blockTable[blockNb].cRoom,
blockTable[blockNb].srcPtr,blockTable[blockNb].srcSize,
cdict);
} else {
#ifdef ZSTD_MULTITHREAD /* note : limitation : MT single-pass does not support compression with dictionary */
# ifdef ZSTD_MULTITHREAD /* note : limitation : MT single-pass does not support compression with dictionary */
rSize = ZSTDMT_compressCCtx(mtctx,
blockTable[blockNb].cPtr, blockTable[blockNb].cRoom,
blockTable[blockNb].srcPtr,blockTable[blockNb].srcSize,
cLevel);
#else
# else
rSize = ZSTD_compress_advanced (ctx,
blockTable[blockNb].cPtr, blockTable[blockNb].cRoom,
blockTable[blockNb].srcPtr,blockTable[blockNb].srcSize, NULL, 0, zparams);
#endif
blockTable[blockNb].srcPtr,blockTable[blockNb].srcSize,
NULL, 0, zparams);
# endif
}
if (ZSTD_isError(rSize)) EXM_THROW(1, "ZSTD_compress_usingCDict() failed : %s", ZSTD_getErrorName(rSize));
if (ZSTD_isError(rSize))
EXM_THROW(1, "ZSTD_compress_usingCDict() failed : %s",
ZSTD_getErrorName(rSize));
#endif /* ZSTD_NEWAPI */
blockTable[blockNb].cSize = rSize;
}
nbLoops++;
@@ -383,7 +411,7 @@ static int BMK_benchMem(const void* srcBuffer, size_t srcSize,
}
pos = (U32)(u - bacc);
bNb = pos / (128 KB);
DISPLAY("(block %u, sub %u, pos %u) \n", segNb, bNb, pos);
DISPLAY("(sample %u, block %u, pos %u) \n", segNb, bNb, pos);
if (u>5) {
int n;
for (n=-5; n<0; n++) DISPLAY("%02X ", ((const BYTE*)srcBuffer)[u+n]);
programs/fileio.c
+135 -89
View File
@@ -77,10 +77,7 @@
#define BLOCKSIZE (128 KB)
#define ROLLBUFFERSIZE (BLOCKSIZE*8*64)
#define FIO_FRAMEHEADERSIZE 5 /* as a define, because needed to allocated table on stack */
#define FSE_CHECKSUM_SEED 0
#define CACHELINE 64
#define FIO_FRAMEHEADERSIZE 5 /* as a define, because needed to allocated table on stack */
#define DICTSIZE_MAX (32 MB) /* protection against large input (attack scenario) */
@@ -93,7 +90,7 @@
#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 */
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 DISPLAYUPDATE(l, ...) { if (g_displayLevel>=l) { \
@@ -103,10 +100,35 @@ void FIO_setNotificationLevel(unsigned level) { g_displayLevel=level; }
static const clock_t refreshRate = CLOCKS_PER_SEC * 15 / 100;
static clock_t g_time = 0;
#undef MIN
#undef MIN /* in case it would be already defined */
#define MIN(a,b) ((a) < (b) ? (a) : (b))
/*-*************************************
* Errors
***************************************/
#ifndef ZSTD_DEBUG
# define ZSTD_DEBUG 0
#endif
#define DEBUGLOG(l,...) if (l<=ZSTD_DEBUG) DISPLAY(__VA_ARGS__);
#define EXM_THROW(error, ...) \
{ \
DISPLAYLEVEL(1, "zstd: "); \
DEBUGLOG(1, "Error defined at %s, line %i : \n", __FILE__, __LINE__); \
DISPLAYLEVEL(1, "error %i : ", error); \
DISPLAYLEVEL(1, __VA_ARGS__); \
DISPLAYLEVEL(1, " \n"); \
exit(error); \
}
#define CHECK(f) { \
size_t const err = f; \
if (ZSTD_isError(err)) { \
DEBUGLOG(1, "%s \n", #f); \
EXM_THROW(11, "%s", ZSTD_getErrorName(err)); \
} }
/* ************************************************************
* Avoid fseek()'s 2GiB barrier with MSVC, MacOS, *BSD, MinGW
***************************************************************/
@@ -146,7 +168,7 @@ 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 = 1; /* 0 : no sparse allowed; 1: auto (file yes, stdout no); 2: force sparse */
static U32 g_sparseFileSupport = 1; /* 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; }
@@ -182,23 +204,6 @@ void FIO_setOverlapLog(unsigned overlapLog){
}
/*-*************************************
* Exceptions
***************************************/
#ifndef DEBUG
# define DEBUG 0
#endif
#define DEBUGOUTPUT(...) if (DEBUG) DISPLAY(__VA_ARGS__);
#define EXM_THROW(error, ...) \
{ \
DEBUGOUTPUT("Error defined at %s, line %i : \n", __FILE__, __LINE__); \
DISPLAYLEVEL(1, "Error %i : ", error); \
DISPLAYLEVEL(1, __VA_ARGS__); \
DISPLAYLEVEL(1, " \n"); \
exit(error); \
}
/*-*************************************
* Functions
***************************************/
@@ -226,12 +231,14 @@ static FILE* FIO_openSrcFile(const char* srcFileName)
f = stdin;
SET_BINARY_MODE(stdin);
} else {
if (!UTIL_isRegFile(srcFileName)) {
DISPLAYLEVEL(1, "zstd: %s is not a regular file -- ignored \n", srcFileName);
if (!UTIL_isRegularFile(srcFileName)) {
DISPLAYLEVEL(1, "zstd: %s is not a regular file -- ignored \n",
srcFileName);
return NULL;
}
f = fopen(srcFileName, "rb");
if ( f==NULL ) DISPLAYLEVEL(1, "zstd: %s: %s \n", srcFileName, strerror(errno));
if ( f==NULL )
DISPLAYLEVEL(1, "zstd: %s: %s \n", srcFileName, strerror(errno));
}
return f;
@@ -256,26 +263,28 @@ static FILE* FIO_openDstFile(const char* dstFileName)
if (g_sparseFileSupport == 1) {
g_sparseFileSupport = ZSTD_SPARSE_DEFAULT;
}
if (strcmp (dstFileName, nulmark)) { /* Check if destination file already exists */
if (strcmp (dstFileName, nulmark)) {
/* Check if destination file already exists */
f = fopen( dstFileName, "rb" );
if (f != 0) { /* dest file exists, prompt for overwrite authorization */
if (f != 0) { /* dst file exists, prompt for overwrite authorization */
fclose(f);
if (!g_overwrite) {
if (g_displayLevel <= 1) {
/* No interaction possible */
DISPLAY("zstd: %s already exists; not overwritten \n", dstFileName);
DISPLAY("zstd: %s already exists; not overwritten \n",
dstFileName);
return NULL;
}
DISPLAY("zstd: %s already exists; do you wish to overwrite (y/N) ? ", dstFileName);
DISPLAY("zstd: %s already exists; do you wish to overwrite (y/N) ? ",
dstFileName);
{ int ch = getchar();
if ((ch!='Y') && (ch!='y')) {
DISPLAY(" not overwritten \n");
return NULL;
}
while ((ch!=EOF) && (ch!='\n')) ch = getchar(); /* flush rest of input line */
}
}
/* flush rest of input line */
while ((ch!=EOF) && (ch!='\n')) ch = getchar();
} }
/* need to unlink */
FIO_remove(dstFileName);
} }
@@ -303,11 +312,13 @@ static size_t FIO_createDictBuffer(void** bufferPtr, const char* fileName)
DISPLAYLEVEL(4,"Loading %s as dictionary \n", fileName);
fileHandle = fopen(fileName, "rb");
if (fileHandle==0) EXM_THROW(31, "zstd: %s: %s", fileName, strerror(errno));
if (fileHandle==0) EXM_THROW(31, "%s: %s", fileName, strerror(errno));
fileSize = UTIL_getFileSize(fileName);
if (fileSize > DICTSIZE_MAX) EXM_THROW(32, "Dictionary file %s is too large (> %u MB)", fileName, DICTSIZE_MAX >> 20); /* avoid extreme cases */
if (fileSize > DICTSIZE_MAX)
EXM_THROW(32, "Dictionary file %s is too large (> %u MB)",
fileName, DICTSIZE_MAX >> 20); /* avoid extreme cases */
*bufferPtr = malloc((size_t)fileSize);
if (*bufferPtr==NULL) EXM_THROW(34, "zstd: %s", strerror(errno));
if (*bufferPtr==NULL) EXM_THROW(34, "%s", strerror(errno));
{ size_t const readSize = fread(*bufferPtr, 1, (size_t)fileSize, fileHandle);
if (readSize!=fileSize) EXM_THROW(35, "Error reading dictionary file %s", fileName); }
fclose(fileHandle);
@@ -326,7 +337,7 @@ typedef struct {
size_t srcBufferSize;
void* dstBuffer;
size_t dstBufferSize;
#ifdef ZSTD_MULTITHREAD
#if !defined(ZSTD_NEWAPI) && defined(ZSTD_MULTITHREAD)
ZSTDMT_CCtx* cctx;
#else
ZSTD_CStream* cctx;
@@ -334,15 +345,19 @@ typedef struct {
} cRess_t;
static cRess_t FIO_createCResources(const char* dictFileName, int cLevel,
U64 srcSize, int srcRegFile,
U64 srcSize, int srcIsRegularFile,
ZSTD_compressionParameters* comprParams) {
cRess_t ress;
memset(&ress, 0, sizeof(ress));
#ifdef ZSTD_MULTITHREAD
#ifdef ZSTD_NEWAPI
ress.cctx = ZSTD_createCCtx();
if (ress.cctx == NULL)
EXM_THROW(30, "allocation error : can't create ZSTD_CCtx");
#elif defined(ZSTD_MULTITHREAD)
ress.cctx = ZSTDMT_createCCtx(g_nbThreads);
if (ress.cctx == NULL)
EXM_THROW(30, "zstd: allocation error : can't create ZSTD_CStream");
EXM_THROW(30, "allocation error : can't create ZSTDMT_CCtx");
if ((cLevel==ZSTD_maxCLevel()) && (g_overlapLog==FIO_OVERLAP_LOG_NOTSET))
/* use complete window for overlap */
ZSTDMT_setMTCtxParameter(ress.cctx, ZSTDMT_p_overlapSectionLog, 9);
@@ -351,22 +366,44 @@ static cRess_t FIO_createCResources(const char* dictFileName, int cLevel,
#else
ress.cctx = ZSTD_createCStream();
if (ress.cctx == NULL)
EXM_THROW(30, "zstd: allocation error : can't create ZSTD_CStream");
EXM_THROW(30, "allocation error : can't create ZSTD_CStream");
#endif
ress.srcBufferSize = ZSTD_CStreamInSize();
ress.srcBuffer = malloc(ress.srcBufferSize);
ress.dstBufferSize = ZSTD_CStreamOutSize();
ress.dstBuffer = malloc(ress.dstBufferSize);
if (!ress.srcBuffer || !ress.dstBuffer)
EXM_THROW(31, "zstd: allocation error : not enough memory");
EXM_THROW(31, "allocation error : not enough memory");
/* dictionary */
{ void* dictBuffer;
size_t const dictBuffSize = FIO_createDictBuffer(&dictBuffer, dictFileName); /* works with dictFileName==NULL */
if (dictFileName && (dictBuffer==NULL))
EXM_THROW(32, "zstd: allocation error : can't create dictBuffer");
EXM_THROW(32, "allocation error : can't create dictBuffer");
#ifdef ZSTD_NEWAPI
{ /* frame parameters */
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_contentSizeFlag, srcIsRegularFile) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_dictIDFlag, g_dictIDFlag) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_checksumFlag, g_checksumFlag) );
CHECK( ZSTD_CCtx_setPledgedSrcSize(ress.cctx, srcSize) );
/* compression parameters */
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_compressionLevel, cLevel) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_windowLog, comprParams->windowLog) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_chainLog, comprParams->chainLog) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_hashLog, comprParams->hashLog) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_searchLog, comprParams->searchLog) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_minMatch, comprParams->searchLength) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_targetLength, comprParams->targetLength) );
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_compressionStrategy, (U32)comprParams->strategy) );
/* multi-threading */
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_p_nbThreads, g_nbThreads) );
/* dictionary */
CHECK( ZSTD_CCtx_loadDictionary(ress.cctx, dictBuffer, dictBuffSize) );
}
#elif defined(ZSTD_MULTITHREAD)
{ ZSTD_parameters params = ZSTD_getParams(cLevel, srcSize, dictBuffSize);
params.fParams.contentSizeFlag = srcRegFile;
params.fParams.contentSizeFlag = srcIsRegularFile;
params.fParams.checksumFlag = g_checksumFlag;
params.fParams.noDictIDFlag = !g_dictIDFlag;
if (comprParams->windowLog) params.cParams.windowLog = comprParams->windowLog;
@@ -376,15 +413,24 @@ static cRess_t FIO_createCResources(const char* dictFileName, int cLevel,
if (comprParams->searchLength) params.cParams.searchLength = comprParams->searchLength;
if (comprParams->targetLength) params.cParams.targetLength = comprParams->targetLength;
if (comprParams->strategy) params.cParams.strategy = (ZSTD_strategy) comprParams->strategy;
#ifdef ZSTD_MULTITHREAD
{ size_t const errorCode = ZSTDMT_initCStream_advanced(ress.cctx, dictBuffer, dictBuffSize, params, srcSize);
if (ZSTD_isError(errorCode)) EXM_THROW(33, "Error initializing CStream : %s", ZSTD_getErrorName(errorCode));
ZSTDMT_setMTCtxParameter(ress.cctx, ZSTDMT_p_sectionSize, g_blockSize);
CHECK( ZSTDMT_initCStream_advanced(ress.cctx, dictBuffer, dictBuffSize, params, srcSize) );
ZSTDMT_setMTCtxParameter(ress.cctx, ZSTDMT_p_sectionSize, g_blockSize);
}
#else
{ size_t const errorCode = ZSTD_initCStream_advanced(ress.cctx, dictBuffer, dictBuffSize, params, srcSize);
if (ZSTD_isError(errorCode)) EXM_THROW(33, "Error initializing CStream : %s", ZSTD_getErrorName(errorCode));
{ ZSTD_parameters params = ZSTD_getParams(cLevel, srcSize, dictBuffSize);
params.fParams.contentSizeFlag = srcIsRegularFile;
params.fParams.checksumFlag = g_checksumFlag;
params.fParams.noDictIDFlag = !g_dictIDFlag;
if (comprParams->windowLog) params.cParams.windowLog = comprParams->windowLog;
if (comprParams->chainLog) params.cParams.chainLog = comprParams->chainLog;
if (comprParams->hashLog) params.cParams.hashLog = comprParams->hashLog;
if (comprParams->searchLog) params.cParams.searchLog = comprParams->searchLog;
if (comprParams->searchLength) params.cParams.searchLength = comprParams->searchLength;
if (comprParams->targetLength) params.cParams.targetLength = comprParams->targetLength;
if (comprParams->strategy) params.cParams.strategy = (ZSTD_strategy) comprParams->strategy;
CHECK( ZSTD_initCStream_advanced(ress.cctx, dictBuffer, dictBuffSize, params, srcSize) );
}
#endif
} }
free(dictBuffer);
}
@@ -395,7 +441,7 @@ static void FIO_freeCResources(cRess_t ress)
{
free(ress.srcBuffer);
free(ress.dstBuffer);
#ifdef ZSTD_MULTITHREAD
#if !defined(ZSTD_NEWAPI) && defined(ZSTD_MULTITHREAD)
ZSTDMT_freeCCtx(ress.cctx);
#else
ZSTD_freeCStream(ress.cctx); /* never fails */
@@ -700,41 +746,40 @@ static int FIO_compressFilename_internal(cRess_t ress,
}
/* init */
#ifdef ZSTD_MULTITHREAD
{ size_t const resetError = ZSTDMT_resetCStream(ress.cctx, fileSize);
#ifdef ZSTD_NEWAPI
/* nothing, reset is implied */
#elif defined(ZSTD_MULTITHREAD)
CHECK( ZSTDMT_resetCStream(ress.cctx, fileSize) );
#else
{ size_t const resetError = ZSTD_resetCStream(ress.cctx, fileSize);
CHECK( ZSTD_resetCStream(ress.cctx, fileSize) );
#endif
if (ZSTD_isError(resetError))
EXM_THROW(21, "Error initializing compression : %s",
ZSTD_getErrorName(resetError));
}
/* Main compression loop */
while (1) {
/* Fill input Buffer */
size_t const inSize = fread(ress.srcBuffer, (size_t)1, ress.srcBufferSize, srcFile);
ZSTD_inBuffer inBuff = { ress.srcBuffer, inSize, 0 };
if (inSize==0) break;
readsize += inSize;
{ ZSTD_inBuffer inBuff = { ress.srcBuffer, inSize, 0 };
while (inBuff.pos != inBuff.size) {
ZSTD_outBuffer outBuff = { ress.dstBuffer, ress.dstBufferSize, 0 };
#ifdef ZSTD_MULTITHREAD
size_t const result = ZSTDMT_compressStream(ress.cctx, &outBuff, &inBuff);
while (inBuff.pos != inBuff.size) {
ZSTD_outBuffer outBuff = { ress.dstBuffer, ress.dstBufferSize, 0 };
#ifdef ZSTD_NEWAPI
CHECK( ZSTD_compress_generic(ress.cctx,
&outBuff, &inBuff, ZSTD_e_continue) );
#elif defined(ZSTD_MULTITHREAD)
CHECK( ZSTDMT_compressStream(ress.cctx, &outBuff, &inBuff) );
#else
size_t const result = ZSTD_compressStream(ress.cctx, &outBuff, &inBuff);
CHECK( ZSTD_compressStream(ress.cctx, &outBuff, &inBuff) );
#endif
if (ZSTD_isError(result))
EXM_THROW(23, "Compression error : %s ", ZSTD_getErrorName(result));
/* Write compressed stream */
if (outBuff.pos) {
size_t const sizeCheck = fwrite(ress.dstBuffer, 1, outBuff.pos, dstFile);
if (sizeCheck!=outBuff.pos)
EXM_THROW(25, "Write error : cannot write compressed block into %s", dstFileName);
compressedfilesize += outBuff.pos;
} } }
/* Write compressed stream */
if (outBuff.pos) {
size_t const sizeCheck = fwrite(ress.dstBuffer, 1, outBuff.pos, dstFile);
if (sizeCheck!=outBuff.pos)
EXM_THROW(25, "Write error : cannot write compressed block into %s", dstFileName);
compressedfilesize += outBuff.pos;
} }
if (g_nbThreads > 1) {
if (!fileSize)
DISPLAYUPDATE(2, "\rRead : %u MB", (U32)(readsize>>20))
@@ -757,12 +802,18 @@ static int FIO_compressFilename_internal(cRess_t ress,
{ size_t result = 1;
while (result!=0) { /* note : is there any possibility of endless loop ? */
ZSTD_outBuffer outBuff = { ress.dstBuffer, ress.dstBufferSize, 0 };
#ifdef ZSTD_MULTITHREAD
#ifdef ZSTD_NEWAPI
ZSTD_inBuffer inBuff = { NULL, 0, 0};
result = ZSTD_compress_generic(ress.cctx,
&outBuff, &inBuff, ZSTD_e_end);
#elif defined(ZSTD_MULTITHREAD)
result = ZSTDMT_endStream(ress.cctx, &outBuff);
#else
result = ZSTD_endStream(ress.cctx, &outBuff);
#endif
if (ZSTD_isError(result)) EXM_THROW(26, "Compression error during frame end : %s", ZSTD_getErrorName(result));
if (ZSTD_isError(result))
EXM_THROW(26, "Compression error during frame end : %s",
ZSTD_getErrorName(result));
{ size_t const sizeCheck = fwrite(ress.dstBuffer, 1, outBuff.pos, dstFile);
if (sizeCheck!=outBuff.pos) EXM_THROW(27, "Write error : cannot write frame end into %s", dstFileName); }
compressedfilesize += outBuff.pos;
@@ -851,9 +902,9 @@ int FIO_compressFilename(const char* dstFileName, const char* srcFileName,
{
clock_t const start = clock();
U64 const srcSize = UTIL_getFileSize(srcFileName);
int const regFile = UTIL_isRegFile(srcFileName);
int const isRegularFile = UTIL_isRegularFile(srcFileName);
cRess_t const ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, regFile, comprParams);
cRess_t const ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, isRegularFile, comprParams);
int const result = FIO_compressFilename_dstFile(ress, dstFileName, srcFileName, compressionLevel);
double const seconds = (double)(clock() - start) / CLOCKS_PER_SEC;
@@ -1098,8 +1149,8 @@ int FIO_compressMultipleFilenames(const char** inFileNamesTable, unsigned nbFile
char* dstFileName = (char*)malloc(FNSPACE);
size_t const suffixSize = suffix ? strlen(suffix) : 0;
U64 const srcSize = (nbFiles != 1) ? 0 : UTIL_getFileSize(inFileNamesTable[0]) ;
int const regFile = (nbFiles != 1) ? 0 : UTIL_isRegFile(inFileNamesTable[0]);
cRess_t ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, regFile, comprParams);
int const isRegularFile = (nbFiles != 1) ? 0 : UTIL_isRegularFile(inFileNamesTable[0]);
cRess_t ress = FIO_createCResources(dictFileName, compressionLevel, srcSize, isRegularFile, comprParams);
/* init */
if (dstFileName==NULL)
@@ -1177,9 +1228,7 @@ static dRess_t FIO_createDResources(const char* dictFileName)
/* dictionary */
{ void* dictBuffer;
size_t const dictBufferSize = FIO_createDictBuffer(&dictBuffer, dictFileName);
size_t const initError = ZSTD_initDStream_usingDict(ress.dctx, dictBuffer, dictBufferSize);
if (ZSTD_isError(initError))
EXM_THROW(61, "ZSTD_initDStream_usingDict error : %s", ZSTD_getErrorName(initError));
CHECK( ZSTD_initDStream_usingDict(ress.dctx, dictBuffer, dictBufferSize) );
free(dictBuffer);
}
@@ -1188,10 +1237,7 @@ static dRess_t FIO_createDResources(const char* dictFileName)
static void FIO_freeDResources(dRess_t ress)
{
size_t const errorCode = ZSTD_freeDStream(ress.dctx);
if (ZSTD_isError(errorCode))
EXM_THROW(69, "Error : can't free ZSTD_DStream context resource : %s",
ZSTD_getErrorName(errorCode));
CHECK( ZSTD_freeDStream(ress.dctx) );
free(ress.srcBuffer);
free(ress.dstBuffer);
}
programs/util.h
+1 -1
View File
@@ -208,7 +208,7 @@ UTIL_STATIC int UTIL_getFileStat(const char* infilename, stat_t *statbuf)
}
UTIL_STATIC int UTIL_isRegFile(const char* infilename)
UTIL_STATIC int UTIL_isRegularFile(const char* infilename)
{
stat_t statbuf;
return UTIL_getFileStat(infilename, &statbuf); /* Only need to know whether it is a regular file */
programs/windres/zstd32.res
BIN
View File
Binary file not shown.
programs/windres/zstd64.res
BIN
View File
Binary file not shown.
programs/zstd.1
+3 -3
View File
@@ -1,5 +1,5 @@
.
.TH "ZSTD" "1" "May 2017" "zstd 1.3.0" "User Commands"
.TH "ZSTD" "1" "June 2017" "zstd 1.3.0" "User Commands"
.
.SH "NAME"
\fBzstd\fR \- zstd, zstdmt, unzstd, zstdcat \- Compress or decompress \.zst files
@@ -235,8 +235,8 @@ benchmark file(s) using multiple compression levels, from \fB\-b#\fR to \fB\-e#\
minimum evaluation time, in seconds (default : 3s), benchmark mode only
.
.TP
\fB\-B#\fR
cut file into independent blocks of size # (default: no block)
\fB\-B#\fR, \fB\-\-block\-size=#\fR
cut file(s) into independent blocks of size # (default: no block)
.
.TP
\fB\-\-priority=rt\fR
programs/zstd.1.md
+4 -4
View File
@@ -234,8 +234,8 @@ BENCHMARK
benchmark file(s) using multiple compression levels, from `-b#` to `-e#` (inclusive)
* `-i#`:
minimum evaluation time, in seconds (default : 3s), benchmark mode only
* `-B#`:
cut file into independent blocks of size # (default: no block)
* `-B#`, `--block-size=#`:
cut file(s) into independent blocks of size # (default: no block)
* `--priority=rt`:
set process priority to real-time
@@ -255,8 +255,8 @@ The list of available _options_:
Specify a strategy used by a match finder.
There are 8 strategies numbered from 0 to 7, from faster to stronger:
0=ZSTD\_fast, 1=ZSTD\_dfast, 2=ZSTD\_greedy, 3=ZSTD\_lazy,
4=ZSTD\_lazy2, 5=ZSTD\_btlazy2, 6=ZSTD\_btopt, 7=ZSTD\_btultra.
1=ZSTD\_fast, 2=ZSTD\_dfast, 3=ZSTD\_greedy, 4=ZSTD\_lazy,
5=ZSTD\_lazy2, 6=ZSTD\_btlazy2, 7=ZSTD\_btopt, 8=ZSTD\_btultra.
- `windowLog`=_wlog_, `wlog`=_wlog_:
Specify the maximum number of bits for a match distance.
programs/zstdcli.c
+1 -1
View File
@@ -300,7 +300,7 @@ static unsigned parseCompressionParameters(const char* stringPtr, ZSTD_compressi
if (longCommandWArg(&stringPtr, "searchLog=") || longCommandWArg(&stringPtr, "slog=")) { params->searchLog = readU32FromChar(&stringPtr); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
if (longCommandWArg(&stringPtr, "searchLength=") || longCommandWArg(&stringPtr, "slen=")) { params->searchLength = readU32FromChar(&stringPtr); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
if (longCommandWArg(&stringPtr, "targetLength=") || longCommandWArg(&stringPtr, "tlen=")) { params->targetLength = readU32FromChar(&stringPtr); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
if (longCommandWArg(&stringPtr, "strategy=") || longCommandWArg(&stringPtr, "strat=")) { params->strategy = (ZSTD_strategy)(1 + readU32FromChar(&stringPtr)); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
if (longCommandWArg(&stringPtr, "strategy=") || longCommandWArg(&stringPtr, "strat=")) { params->strategy = (ZSTD_strategy)(readU32FromChar(&stringPtr)); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
if (longCommandWArg(&stringPtr, "overlapLog=") || longCommandWArg(&stringPtr, "ovlog=")) { g_overlapLog = readU32FromChar(&stringPtr); if (stringPtr[0]==',') { stringPtr++; continue; } else break; }
return 0;
}
tests/Makefile
+13 -11
View File
@@ -26,18 +26,18 @@ PYTHON ?= python3
TESTARTEFACT := versionsTest namespaceTest
DEBUGFLAGS=-g -DZSTD_DEBUG=1
CPPFLAGS+= -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
-I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR) \
$(DEBUGFLAG)
CFLAGS ?= -O3
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
DEBUGFLAGS= -g -DZSTD_DEBUG=1
CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
-I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR)
CFLAGS ?= -O3
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-Wstrict-prototypes -Wundef -Wformat-security \
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
-Wstrict-prototypes -Wundef -Wformat-security \
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
-Wredundant-decls
CFLAGS += $(MOREFLAGS)
FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS)
CFLAGS += $(DEBUGFLAGS)
CFLAGS += $(MOREFLAGS)
FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS)
ZSTDCOMMON_FILES := $(ZSTDDIR)/common/*.c
@@ -159,7 +159,7 @@ zstreamtest-dll : $(ZSTDDIR)/common/xxhash.c $(PRGDIR)/datagen.c zstreamtest.c
$(MAKE) -C $(ZSTDDIR) libzstd
$(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@$(EXT)
paramgrill : DEBUGFLAG =
paramgrill : DEBUGFLAGS =
paramgrill : $(ZSTD_FILES) $(PRGDIR)/datagen.c paramgrill.c
$(CC) $(FLAGS) $^ -lm -o $@$(EXT)
@@ -321,6 +321,8 @@ test-zbuff32: zbufftest32
test-zstream: zstreamtest
$(QEMU_SYS) ./zstreamtest $(ZSTREAM_TESTTIME) $(FUZZER_FLAGS)
$(QEMU_SYS) ./zstreamtest --mt $(ZSTREAM_TESTTIME) $(FUZZER_FLAGS)
$(QEMU_SYS) ./zstreamtest --newapi $(ZSTREAM_TESTTIME) $(FUZZER_FLAGS)
test-zstream32: zstreamtest32
$(QEMU_SYS) ./zstreamtest32 $(ZSTREAM_TESTTIME) $(FUZZER_FLAGS)
tests/decodecorpus.c
-2
View File
@@ -73,8 +73,6 @@ static clock_t clockSpan(clock_t cStart)
/*-*******************************************************
* Random function
*********************************************************/
#define CLAMP(x, a, b) ((x) < (a) ? (a) : ((x) > (b) ? (b) : (x)))
static unsigned RAND(unsigned* src)
{
#define RAND_rotl32(x,r) ((x << r) | (x >> (32 - r)))
tests/fuzzer.c
+174 -28
View File
@@ -12,9 +12,9 @@
* Compiler specific
**************************************/
#ifdef _MSC_VER /* Visual Studio */
# define _CRT_SECURE_NO_WARNINGS /* fgets */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
# define _CRT_SECURE_NO_WARNINGS /* fgets */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
#endif
@@ -25,7 +25,7 @@
#include <stdio.h> /* fgets, sscanf */
#include <string.h> /* strcmp */
#include <time.h> /* clock_t */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_compressContinue, ZSTD_compressBlock */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_compressContinue, ZSTD_compressBlock */
#include "zstd.h" /* ZSTD_VERSION_STRING */
#include "zstd_errors.h" /* ZSTD_getErrorCode */
#include "zstdmt_compress.h"
@@ -74,7 +74,6 @@ static clock_t FUZ_clockSpan(clock_t cStart)
return clock() - cStart; /* works even when overflow; max span ~ 30mn */
}
#define FUZ_rotl32(x,r) ((x << r) | (x >> (32 - r)))
static unsigned FUZ_rand(unsigned* src)
{
@@ -104,6 +103,7 @@ static unsigned FUZ_highbit32(U32 v32)
#define CHECK_V(var, fn) size_t const var = fn; if (ZSTD_isError(var)) goto _output_error
#define CHECK(fn) { CHECK_V(err, fn); }
#define CHECKPLUS(var, fn, more) { CHECK_V(var, fn); more; }
static int basicUnitTests(U32 seed, double compressibility)
{
size_t const CNBuffSize = 5 MB;
@@ -190,6 +190,90 @@ static int basicUnitTests(U32 seed, double compressibility)
DISPLAYLEVEL(4, "OK \n");
/* Static CCtx tests */
#define STATIC_CCTX_LEVEL 3
DISPLAYLEVEL(4, "test%3i : create static CCtx for level %u :", testNb++, STATIC_CCTX_LEVEL);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(STATIC_CCTX_LEVEL, 0, 0);
size_t const staticCCtxSize = ZSTD_estimateCStreamSize(cParams);
void* const staticCCtxBuffer = malloc(staticCCtxSize);
size_t const staticDCtxSize = ZSTD_estimateDCtxSize();
void* const staticDCtxBuffer = malloc(staticDCtxSize);
if (staticCCtxBuffer==NULL || staticDCtxBuffer==NULL) {
free(staticCCtxBuffer);
free(staticDCtxBuffer);
DISPLAY("Not enough memory, aborting\n");
testResult = 1;
goto _end;
}
{ ZSTD_CCtx* staticCCtx = ZSTD_initStaticCCtx(staticCCtxBuffer, staticCCtxSize);
ZSTD_DCtx* staticDCtx = ZSTD_initStaticDCtx(staticDCtxBuffer, staticDCtxSize);
if ((staticCCtx==NULL) || (staticDCtx==NULL)) goto _output_error;
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init CCtx for level %u : ", testNb++, STATIC_CCTX_LEVEL);
{ size_t const r = ZSTD_compressBegin(staticCCtx, STATIC_CCTX_LEVEL);
if (ZSTD_isError(r)) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : simple compression test with static CCtx : ", testNb++);
CHECKPLUS(r, ZSTD_compressCCtx(staticCCtx,
compressedBuffer, ZSTD_compressBound(CNBuffSize),
CNBuffer, CNBuffSize, STATIC_CCTX_LEVEL),
cSize=r );
DISPLAYLEVEL(4, "OK (%u bytes : %.2f%%)\n",
(U32)cSize, (double)cSize/CNBuffSize*100);
DISPLAYLEVEL(4, "test%3i : simple decompression test with static DCtx : ", testNb++);
{ size_t const r = ZSTD_decompressDCtx(staticDCtx,
decodedBuffer, CNBuffSize,
compressedBuffer, cSize);
if (r != CNBuffSize) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : check decompressed result : ", testNb++);
{ size_t u;
for (u=0; u<CNBuffSize; u++) {
if (((BYTE*)decodedBuffer)[u] != ((BYTE*)CNBuffer)[u])
goto _output_error;;
} }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init CCtx for too large level (must fail) : ", testNb++);
{ size_t const r = ZSTD_compressBegin(staticCCtx, ZSTD_maxCLevel());
if (!ZSTD_isError(r)) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init CCtx for small level %u (should work again) : ", testNb++, 1);
{ size_t const r = ZSTD_compressBegin(staticCCtx, 1);
if (ZSTD_isError(r)) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init CStream for small level %u : ", testNb++, 1);
{ size_t const r = ZSTD_initCStream(staticCCtx, 1);
if (ZSTD_isError(r)) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init CStream with dictionary (should fail) : ", testNb++);
{ size_t const r = ZSTD_initCStream_usingDict(staticCCtx, CNBuffer, 64 KB, 1);
if (!ZSTD_isError(r)) goto _output_error; }
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : init DStream (should fail) : ", testNb++);
{ size_t const r = ZSTD_initDStream(staticDCtx);
if (ZSTD_isError(r)) goto _output_error; }
{ ZSTD_outBuffer output = { decodedBuffer, CNBuffSize, 0 };
ZSTD_inBuffer input = { compressedBuffer, ZSTD_FRAMEHEADERSIZE_MAX+1, 0 };
size_t const r = ZSTD_decompressStream(staticDCtx, &output, &input);
if (!ZSTD_isError(r)) goto _output_error;
}
DISPLAYLEVEL(4, "OK \n");
}
free(staticCCtxBuffer);
free(staticDCtxBuffer);
}
/* ZSTDMT simple MT compression test */
DISPLAYLEVEL(4, "test%3i : create ZSTDMT CCtx : ", testNb++);
{ ZSTDMT_CCtx* mtctx = ZSTDMT_createCCtx(2);
@@ -321,13 +405,25 @@ static int basicUnitTests(U32 seed, double compressibility)
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : decompress with DDict : ", testNb++);
{ ZSTD_DDict* const ddict = ZSTD_createDDict_byReference(CNBuffer, dictSize);
{ ZSTD_DDict* const ddict = ZSTD_createDDict(CNBuffer, dictSize);
size_t const r = ZSTD_decompress_usingDDict(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize, ddict);
if (r != CNBuffSize - dictSize) goto _output_error;
DISPLAYLEVEL(4, "OK (size of DDict : %u) \n", (U32)ZSTD_sizeof_DDict(ddict));
ZSTD_freeDDict(ddict);
}
DISPLAYLEVEL(4, "test%3i : decompress with static DDict : ", testNb++);
{ size_t const ddictBufferSize = ZSTD_estimateDDictSize(dictSize, 0);
void* ddictBuffer = malloc(ddictBufferSize);
if (ddictBuffer == NULL) goto _output_error;
{ ZSTD_DDict* const ddict = ZSTD_initStaticDDict(ddictBuffer, ddictBufferSize, CNBuffer, dictSize, 0);
size_t const r = ZSTD_decompress_usingDDict(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize, ddict);
if (r != CNBuffSize - dictSize) goto _output_error;
}
free(ddictBuffer);
DISPLAYLEVEL(4, "OK (size of static DDict : %u) \n", (U32)ddictBufferSize);
}
DISPLAYLEVEL(4, "test%3i : check content size on duplicated context : ", testNb++);
{ size_t const testSize = CNBuffSize / 3;
{ ZSTD_parameters p = ZSTD_getParams(2, testSize, dictSize);
@@ -406,14 +502,16 @@ static int basicUnitTests(U32 seed, double compressibility)
DISPLAYLEVEL(4, "test%3i : estimate CDict size : ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
size_t const estimatedSize = ZSTD_estimateCDictSize(cParams, dictSize);
size_t const estimatedSize = ZSTD_estimateCDictSize(cParams, dictSize, 1 /*byReference*/);
DISPLAYLEVEL(4, "OK : %u \n", (U32)estimatedSize);
}
DISPLAYLEVEL(4, "test%3i : compress with preprocessed dictionary : ", testNb++);
DISPLAYLEVEL(4, "test%3i : compress with CDict ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
ZSTD_customMem customMem = { NULL, NULL, NULL };
ZSTD_CDict* cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize, 1, cParams, customMem);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize,
1 /* byReference */, ZSTD_dm_auto,
cParams, ZSTD_defaultCMem);
DISPLAYLEVEL(4, "(size : %u) : ", (U32)ZSTD_sizeof_CDict(cdict));
cSize = ZSTD_compress_usingCDict(cctx, compressedBuffer, ZSTD_compressBound(CNBuffSize),
CNBuffer, CNBuffSize, cdict);
ZSTD_freeCDict(cdict);
@@ -435,11 +533,34 @@ static int basicUnitTests(U32 seed, double compressibility)
if (r != CNBuffSize) goto _output_error);
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : compress with static CDict : ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
size_t const cdictSize = ZSTD_estimateCDictSize(cParams, dictSize, 0);
void* const cdictBuffer = malloc(cdictSize);
if (cdictBuffer==NULL) goto _output_error;
{ ZSTD_CDict* const cdict = ZSTD_initStaticCDict(cdictBuffer, cdictSize,
dictBuffer, dictSize,
0 /* by Reference */, ZSTD_dm_auto,
cParams);
if (cdict == NULL) {
DISPLAY("ZSTD_initStaticCDict failed ");
goto _output_error;
}
cSize = ZSTD_compress_usingCDict(cctx,
compressedBuffer, ZSTD_compressBound(CNBuffSize),
CNBuffer, CNBuffSize, cdict);
if (ZSTD_isError(cSize)) {
DISPLAY("ZSTD_compress_usingCDict failed ");
goto _output_error;
} }
free(cdictBuffer);
}
DISPLAYLEVEL(4, "OK (%u bytes : %.2f%%)\n", (U32)cSize, (double)cSize/CNBuffSize*100);
DISPLAYLEVEL(4, "test%3i : ZSTD_compress_usingCDict_advanced, no contentSize, no dictID : ", testNb++);
{ ZSTD_frameParameters const fParams = { 0 /* frameSize */, 1 /* checksum */, 1 /* noDictID*/ };
ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
ZSTD_customMem const customMem = { NULL, NULL, NULL };
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize, 1, cParams, customMem);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize, 1 /*byRef*/, ZSTD_dm_auto, cParams, ZSTD_defaultCMem);
cSize = ZSTD_compress_usingCDict_advanced(cctx, compressedBuffer, ZSTD_compressBound(CNBuffSize),
CNBuffer, CNBuffSize, cdict, fParams);
ZSTD_freeCDict(cdict);
@@ -488,6 +609,22 @@ static int basicUnitTests(U32 seed, double compressibility)
}
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : Building cdict w/ ZSTD_dm_fullDict on a good dictionary : ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictSize, 1 /*byRef*/, ZSTD_dm_fullDict, cParams, ZSTD_defaultCMem);
if (cdict==NULL) goto _output_error;
ZSTD_freeCDict(cdict);
}
DISPLAYLEVEL(4, "OK \n");
DISPLAYLEVEL(4, "test%3i : Building cdict w/ ZSTD_dm_fullDict on a rawContent (must fail) : ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBuffSize, dictSize);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced((const char*)dictBuffer+1, dictSize-1, 1 /*byRef*/, ZSTD_dm_fullDict, cParams, ZSTD_defaultCMem);
if (cdict!=NULL) goto _output_error;
ZSTD_freeCDict(cdict);
}
DISPLAYLEVEL(4, "OK \n");
ZSTD_freeCCtx(cctx);
free(dictBuffer);
free(samplesSizes);
@@ -566,9 +703,7 @@ static int basicUnitTests(U32 seed, double compressibility)
size_t const wrongSrcSize = (srcSize + 1000);
ZSTD_parameters params = ZSTD_getParams(1, wrongSrcSize, 0);
params.fParams.contentSizeFlag = 1;
{ size_t const result = ZSTD_compressBegin_advanced(cctx, NULL, 0, params, wrongSrcSize);
if (ZSTD_isError(result)) goto _output_error;
}
CHECK( ZSTD_compressBegin_advanced(cctx, NULL, 0, params, wrongSrcSize) );
{ size_t const result = ZSTD_compressEnd(cctx, decodedBuffer, CNBuffSize, CNBuffer, srcSize);
if (!ZSTD_isError(result)) goto _output_error;
if (ZSTD_getErrorCode(result) != ZSTD_error_srcSize_wrong) goto _output_error;
@@ -586,6 +721,7 @@ static int basicUnitTests(U32 seed, double compressibility)
/* basic block compression */
DISPLAYLEVEL(4, "test%3i : Block compression test : ", testNb++);
CHECK( ZSTD_compressBegin(cctx, 5) );
CHECK( ZSTD_getBlockSize(cctx) >= blockSize);
cSize = ZSTD_compressBlock(cctx, compressedBuffer, ZSTD_compressBound(blockSize), CNBuffer, blockSize);
if (ZSTD_isError(cSize)) goto _output_error;
DISPLAYLEVEL(4, "OK \n");
@@ -749,8 +885,23 @@ static size_t FUZ_randomLength(U32* seed, U32 maxLog)
}
#undef CHECK
#define CHECK(cond, ...) if (cond) { DISPLAY("Error => "); DISPLAY(__VA_ARGS__); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); goto _output_error; }
#define CHECK(cond, ...) { \
if (cond) { \
DISPLAY("Error => "); \
DISPLAY(__VA_ARGS__); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); \
goto _output_error; \
} }
#define CHECK_Z(f) { \
size_t const err = f; \
if (ZSTD_isError(err)) { \
DISPLAY("Error => %s : %s ", \
#f, ZSTD_getErrorName(err)); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); \
goto _output_error; \
} }
static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, U32 const maxDurationS, double compressibility, int bigTests)
{
@@ -863,8 +1014,7 @@ static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, U32 const maxD
/* frame header decompression test */
{ ZSTD_frameHeader dParams;
size_t const check = ZSTD_getFrameHeader(&dParams, cBuffer, cSize);
CHECK(ZSTD_isError(check), "Frame Parameters extraction failed");
CHECK_Z( ZSTD_getFrameHeader(&dParams, cBuffer, cSize) );
CHECK(dParams.frameContentSize != sampleSize, "Frame content size incorrect");
}
@@ -951,20 +1101,17 @@ static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, U32 const maxD
dict = srcBuffer + (FUZ_rand(&lseed) % (srcBufferSize - dictSize));
if (FUZ_rand(&lseed) & 0xF) {
size_t const errorCode = ZSTD_compressBegin_usingDict(refCtx, dict, dictSize, cLevel);
CHECK (ZSTD_isError(errorCode), "ZSTD_compressBegin_usingDict error : %s", ZSTD_getErrorName(errorCode));
CHECK_Z ( ZSTD_compressBegin_usingDict(refCtx, dict, dictSize, cLevel) );
} else {
ZSTD_compressionParameters const cPar = ZSTD_getCParams(cLevel, 0, dictSize);
ZSTD_frameParameters const fPar = { FUZ_rand(&lseed)&1 /* contentSizeFlag */,
!(FUZ_rand(&lseed)&3) /* contentChecksumFlag*/,
0 /*NodictID*/ }; /* note : since dictionary is fake, dictIDflag has no impact */
ZSTD_parameters const p = FUZ_makeParams(cPar, fPar);
size_t const errorCode = ZSTD_compressBegin_advanced(refCtx, dict, dictSize, p, 0);
CHECK (ZSTD_isError(errorCode), "ZSTD_compressBegin_advanced error : %s", ZSTD_getErrorName(errorCode));
CHECK_Z ( ZSTD_compressBegin_advanced(refCtx, dict, dictSize, p, 0) );
}
{ size_t const errorCode = ZSTD_copyCCtx(ctx, refCtx, 0);
CHECK (ZSTD_isError(errorCode), "ZSTD_copyCCtx error : %s", ZSTD_getErrorName(errorCode));
} }
CHECK_Z( ZSTD_copyCCtx(ctx, refCtx, 0) );
}
ZSTD_setCCtxParameter(ctx, ZSTD_p_forceWindow, FUZ_rand(&lseed) & 1);
{ U32 const nbChunks = (FUZ_rand(&lseed) & 127) + 2;
@@ -996,8 +1143,7 @@ static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, U32 const maxD
/* streaming decompression test */
if (dictSize<8) dictSize=0, dict=NULL; /* disable dictionary */
{ size_t const errorCode = ZSTD_decompressBegin_usingDict(dctx, dict, dictSize);
CHECK (ZSTD_isError(errorCode), "ZSTD_decompressBegin_usingDict error : %s", ZSTD_getErrorName(errorCode)); }
CHECK_Z( ZSTD_decompressBegin_usingDict(dctx, dict, dictSize) );
totalCSize = 0;
totalGenSize = 0;
while (totalCSize < cSize) {
tests/symbols.c
+1 -1
View File
@@ -95,7 +95,7 @@ static const void *symbols[] = {
&ZSTD_nextSrcSizeToDecompress,
&ZSTD_decompressContinue,
&ZSTD_nextInputType,
&ZSTD_getBlockSizeMax,
&ZSTD_getBlockSize,
&ZSTD_compressBlock,
&ZSTD_decompressBlock,
&ZSTD_insertBlock,
tests/zstreamtest.c
+614 -286
View File
@@ -12,9 +12,9 @@
* Compiler specific
**************************************/
#ifdef _MSC_VER /* Visual Studio */
# define _CRT_SECURE_NO_WARNINGS /* fgets */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 4146) /* disable: C4146: minus unsigned expression */
# define _CRT_SECURE_NO_WARNINGS /* fgets */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 4146) /* disable: C4146: minus unsigned expression */
#endif
@@ -25,8 +25,9 @@
#include <stdio.h> /* fgets, sscanf */
#include <time.h> /* clock_t, clock() */
#include <string.h> /* strcmp */
#include <assert.h> /* assert */
#include "mem.h"
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_maxCLevel, ZSTD_customMem, ZSTD_getDictID_fromFrame */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_maxCLevel, ZSTD_customMem, ZSTD_getDictID_fromFrame */
#include "zstd.h" /* ZSTD_compressBound */
#include "zstd_errors.h" /* ZSTD_error_srcSize_wrong */
#include "zstdmt_compress.h"
@@ -44,6 +45,7 @@
#define GB *(1U<<30)
static const U32 nbTestsDefault = 10000;
static const U32 g_cLevelMax_smallTests = 10;
#define COMPRESSIBLE_NOISE_LENGTH (10 MB)
#define FUZ_COMPRESSIBILITY_DEFAULT 50
static const U32 prime32 = 2654435761U;
@@ -189,7 +191,8 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
/* Basic compression test */
DISPLAYLEVEL(3, "test%3i : compress %u bytes : ", testNb++, COMPRESSIBLE_NOISE_LENGTH);
ZSTD_initCStream_usingDict(zc, CNBuffer, dictSize, 1);
{ size_t const r = ZSTD_initCStream_usingDict(zc, CNBuffer, dictSize, 1);
if (ZSTD_isError(r)) goto _output_error; }
outBuff.dst = (char*)(compressedBuffer)+cSize;
outBuff.size = compressedBufferSize;
outBuff.pos = 0;
@@ -208,15 +211,16 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
DISPLAYLEVEL(3, "test%3i : estimate CStream size : ", testNb++);
{ ZSTD_compressionParameters const cParams = ZSTD_getCParams(1, CNBufferSize, dictSize);
size_t const s = ZSTD_estimateCStreamSize(cParams)
+ ZSTD_estimateCDictSize(cParams, dictSize); /* uses ZSTD_initCStream_usingDict() */
/* uses ZSTD_initCStream_usingDict() */
+ ZSTD_estimateCDictSize(cParams, dictSize, 0);
if (ZSTD_isError(s)) goto _output_error;
DISPLAYLEVEL(3, "OK (%u bytes) \n", (U32)s);
}
DISPLAYLEVEL(3, "test%3i : check actual CStream size : ", testNb++);
{ size_t const s = ZSTD_sizeof_CStream(zc);
if (ZSTD_isError(s)) goto _output_error;
DISPLAYLEVEL(3, "OK (%u bytes) \n", (U32)s);
{ size_t const s = ZSTD_sizeof_CStream(zc);
if (ZSTD_isError(s)) goto _output_error;
DISPLAYLEVEL(3, "OK (%u bytes) \n", (U32)s);
}
/* Attempt bad compression parameters */
@@ -231,15 +235,18 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
/* skippable frame test */
DISPLAYLEVEL(3, "test%3i : decompress skippable frame : ", testNb++);
ZSTD_initDStream_usingDict(zd, CNBuffer, dictSize);
if (ZSTD_isError( ZSTD_initDStream_usingDict(zd, CNBuffer, dictSize) ))
goto _output_error;
inBuff.src = compressedBuffer;
inBuff.size = cSize;
inBuff.pos = 0;
outBuff.dst = decodedBuffer;
outBuff.size = CNBufferSize;
outBuff.pos = 0;
{ size_t const r = ZSTD_decompressStream(zd, &outBuff, &inBuff);
if (r != 0) goto _output_error; }
{ size_t const r = ZSTD_decompressStream(zd, &outBuff, &inBuff);
DISPLAYLEVEL(5, " ( ZSTD_decompressStream => %u ) ", (U32)r);
if (r != 0) goto _output_error;
}
if (outBuff.pos != 0) goto _output_error; /* skippable frame output len is 0 */
DISPLAYLEVEL(3, "OK \n");
@@ -280,7 +287,8 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
if (gfhError!=0) goto _output_error;
DISPLAYLEVEL(5, " (windowSize : %u) ", fhi.windowSize);
{ size_t const s = ZSTD_estimateDStreamSize(fhi)
+ ZSTD_estimateDDictSize(dictSize); /* uses ZSTD_initDStream_usingDict() */
/* uses ZSTD_initDStream_usingDict() */
+ ZSTD_estimateDDictSize(dictSize, 0);
if (ZSTD_isError(s)) goto _output_error;
DISPLAYLEVEL(3, "OK (%u bytes) \n", (U32)s);
} }
@@ -482,8 +490,8 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
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 */};
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictionary.start, dictionary.filled, 1 /* byReference */, cParams, customMem);
size_t const initError = ZSTD_initCStream_usingCDict_advanced(zc, cdict, CNBufferSize, fParams);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictionary.start, dictionary.filled, 1 /* byReference */, ZSTD_dm_auto, cParams, customMem);
size_t const initError = ZSTD_initCStream_usingCDict_advanced(zc, cdict, fParams, CNBufferSize);
if (ZSTD_isError(initError)) goto _output_error;
cSize = 0;
outBuff.dst = compressedBuffer;
@@ -494,7 +502,7 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo
inBuff.pos = 0;
{ size_t const r = ZSTD_compressStream(zc, &outBuff, &inBuff);
if (ZSTD_isError(r)) goto _output_error; }
if (inBuff.pos != inBuff.size) goto _output_error; /* entire input should be consumed */
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 */
cSize = outBuff.pos;
@@ -643,12 +651,26 @@ static size_t FUZ_randomLength(U32* seed, U32 maxLog)
#define MIN(a,b) ( (a) < (b) ? (a) : (b) )
#define CHECK(cond, ...) if (cond) { DISPLAY("Error => "); DISPLAY(__VA_ARGS__); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); goto _output_error; }
#define CHECK(cond, ...) { \
if (cond) { \
DISPLAY("Error => "); \
DISPLAY(__VA_ARGS__); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); \
goto _output_error; \
} }
#define CHECK_Z(f) { \
size_t const err = f; \
if (ZSTD_isError(err)) { \
DISPLAY("Error => %s : %s ", \
#f, ZSTD_getErrorName(err)); \
DISPLAY(" (seed %u, test nb %u) \n", seed, testNb); \
goto _output_error; \
} }
static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, double compressibility, int bigTests)
{
static const U32 maxSrcLog = 24;
U32 const maxSrcLog = bigTests ? 24 : 22;
static const U32 maxSampleLog = 19;
size_t const srcBufferSize = (size_t)1<<maxSrcLog;
BYTE* cNoiseBuffer[5];
@@ -668,247 +690,7 @@ static int fuzzerTests(U32 seed, U32 nbTests, unsigned startTest, double compres
const BYTE* dict=NULL; /* can keep same dict on 2 consecutive tests */
size_t dictSize = 0;
U32 oldTestLog = 0;
int const cLevelLimiter = bigTests ? 3 : 2;
/* allocations */
cNoiseBuffer[0] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[1] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[2] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[3] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[4] = (BYTE*)malloc (srcBufferSize);
CHECK (!cNoiseBuffer[0] || !cNoiseBuffer[1] || !cNoiseBuffer[2] || !cNoiseBuffer[3] || !cNoiseBuffer[4] ||
!copyBuffer || !dstBuffer || !cBuffer || !zc || !zd || !zd_noise ,
"Not enough memory, fuzzer tests cancelled");
/* Create initial samples */
RDG_genBuffer(cNoiseBuffer[0], srcBufferSize, 0.00, 0., coreSeed); /* pure noise */
RDG_genBuffer(cNoiseBuffer[1], srcBufferSize, 0.05, 0., coreSeed); /* barely compressible */
RDG_genBuffer(cNoiseBuffer[2], srcBufferSize, compressibility, 0., coreSeed);
RDG_genBuffer(cNoiseBuffer[3], srcBufferSize, 0.95, 0., coreSeed); /* highly compressible */
RDG_genBuffer(cNoiseBuffer[4], srcBufferSize, 1.00, 0., coreSeed); /* sparse content */
memset(copyBuffer, 0x65, copyBufferSize); /* make copyBuffer considered initialized */
ZSTD_initDStream_usingDict(zd, NULL, 0); /* ensure at least one init */
/* catch up testNb */
for (testNb=1; testNb < startTest; testNb++)
FUZ_rand(&coreSeed);
/* test loop */
for ( ; (testNb <= nbTests) || (FUZ_GetClockSpan(startClock) < g_clockTime) ; testNb++ ) {
U32 lseed;
const BYTE* srcBuffer;
size_t totalTestSize, totalGenSize, cSize;
XXH64_state_t xxhState;
U64 crcOrig;
U32 resetAllowed = 1;
size_t maxTestSize;
/* init */
if (nbTests >= testNb) { DISPLAYUPDATE(2, "\r%6u/%6u ", testNb, nbTests); }
else { DISPLAYUPDATE(2, "\r%6u ", testNb); }
FUZ_rand(&coreSeed);
lseed = coreSeed ^ prime32;
/* states full reset (deliberately not synchronized) */
/* some issues can only happen when reusing states */
if ((FUZ_rand(&lseed) & 0xFF) == 131) { ZSTD_freeCStream(zc); zc = ZSTD_createCStream(); resetAllowed=0; }
if ((FUZ_rand(&lseed) & 0xFF) == 132) { ZSTD_freeDStream(zd); zd = ZSTD_createDStream(); ZSTD_initDStream_usingDict(zd, NULL, 0); /* ensure at least one init */ }
/* srcBuffer selection [0-4] */
{ U32 buffNb = FUZ_rand(&lseed) & 0x7F;
if (buffNb & 7) buffNb=2; /* most common : compressible (P) */
else {
buffNb >>= 3;
if (buffNb & 7) {
const U32 tnb[2] = { 1, 3 }; /* barely/highly compressible */
buffNb = tnb[buffNb >> 3];
} else {
const U32 tnb[2] = { 0, 4 }; /* not compressible / sparse */
buffNb = tnb[buffNb >> 3];
} }
srcBuffer = cNoiseBuffer[buffNb];
}
/* compression init */
if ((FUZ_rand(&lseed)&1) /* at beginning, to keep same nb of rand */
&& oldTestLog /* at least one test happened */ && resetAllowed) {
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize)
maxTestSize = srcBufferSize-1;
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? 0 : maxTestSize;
size_t const resetError = ZSTD_resetCStream(zc, pledgedSrcSize);
CHECK(ZSTD_isError(resetError), "ZSTD_resetCStream error : %s", ZSTD_getErrorName(resetError));
}
} else {
U32 const testLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const dictLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const cLevel = ( FUZ_rand(&lseed) %
(ZSTD_maxCLevel() -
(MAX(testLog, dictLog) / cLevelLimiter)))
+ 1;
maxTestSize = FUZ_rLogLength(&lseed, testLog);
oldTestLog = testLog;
/* random dictionary selection */
dictSize = ((FUZ_rand(&lseed)&1)==1) ? FUZ_rLogLength(&lseed, dictLog) : 0;
{ size_t const dictStart = FUZ_rand(&lseed) % (srcBufferSize - dictSize);
dict = srcBuffer + dictStart;
}
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? 0 : maxTestSize;
ZSTD_parameters params = ZSTD_getParams(cLevel, pledgedSrcSize, dictSize);
params.fParams.checksumFlag = FUZ_rand(&lseed) & 1;
params.fParams.noDictIDFlag = FUZ_rand(&lseed) & 1;
{ size_t const initError = ZSTD_initCStream_advanced(zc, dict, dictSize, params, pledgedSrcSize);
CHECK (ZSTD_isError(initError),"ZSTD_initCStream_advanced error : %s", ZSTD_getErrorName(initError));
} } }
/* multi-segments compression test */
XXH64_reset(&xxhState, 0);
{ ZSTD_outBuffer outBuff = { cBuffer, cBufferSize, 0 } ;
U32 n;
for (n=0, cSize=0, totalTestSize=0 ; totalTestSize < maxTestSize ; n++) {
/* compress random chunks into randomly sized dst buffers */
{ size_t const randomSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const srcSize = MIN (maxTestSize-totalTestSize, randomSrcSize);
size_t const srcStart = FUZ_rand(&lseed) % (srcBufferSize - srcSize);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(cBufferSize - cSize, randomDstSize);
ZSTD_inBuffer inBuff = { srcBuffer+srcStart, srcSize, 0 };
outBuff.size = outBuff.pos + dstBuffSize;
{ size_t const compressionError = ZSTD_compressStream(zc, &outBuff, &inBuff);
CHECK (ZSTD_isError(compressionError), "compression error : %s", ZSTD_getErrorName(compressionError)); }
XXH64_update(&xxhState, srcBuffer+srcStart, inBuff.pos);
memcpy(copyBuffer+totalTestSize, srcBuffer+srcStart, inBuff.pos);
totalTestSize += inBuff.pos;
}
/* random flush operation, to mess around */
if ((FUZ_rand(&lseed) & 15) == 0) {
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
outBuff.size = outBuff.pos + adjustedDstSize;
{ size_t const flushError = ZSTD_flushStream(zc, &outBuff);
CHECK (ZSTD_isError(flushError), "flush error : %s", ZSTD_getErrorName(flushError));
} } }
/* final frame epilogue */
{ size_t remainingToFlush = (size_t)(-1);
while (remainingToFlush) {
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
U32 const enoughDstSize = (adjustedDstSize >= remainingToFlush);
outBuff.size = outBuff.pos + adjustedDstSize;
remainingToFlush = ZSTD_endStream(zc, &outBuff);
CHECK (ZSTD_isError(remainingToFlush), "flush error : %s", ZSTD_getErrorName(remainingToFlush));
CHECK (enoughDstSize && remainingToFlush,
"ZSTD_endStream() not fully flushed (%u remaining), but enough space available (%u)",
(U32)remainingToFlush, (U32)adjustedDstSize);
} }
crcOrig = XXH64_digest(&xxhState);
cSize = outBuff.pos;
}
/* multi - fragments decompression test */
if (!dictSize /* don't reset if dictionary : could be different */ && (FUZ_rand(&lseed) & 1)) {
CHECK (ZSTD_isError(ZSTD_resetDStream(zd)), "ZSTD_resetDStream failed");
} else {
ZSTD_initDStream_usingDict(zd, dict, dictSize);
}
{ size_t decompressionResult = 1;
ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
for (totalGenSize = 0 ; decompressionResult ; ) {
size_t const readCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(dstBufferSize - totalGenSize, randomDstSize);
inBuff.size = inBuff.pos + readCSrcSize;
outBuff.size = inBuff.pos + dstBuffSize;
decompressionResult = ZSTD_decompressStream(zd, &outBuff, &inBuff);
CHECK (ZSTD_isError(decompressionResult), "decompression error : %s", ZSTD_getErrorName(decompressionResult));
}
CHECK (decompressionResult != 0, "frame not fully decoded");
CHECK (outBuff.pos != totalTestSize, "decompressed data : wrong size")
CHECK (inBuff.pos != cSize, "compressed data should be fully read")
{ U64 const crcDest = XXH64(dstBuffer, totalTestSize, 0);
if (crcDest!=crcOrig) findDiff(copyBuffer, dstBuffer, totalTestSize);
CHECK (crcDest!=crcOrig, "decompressed data corrupted");
} }
/*===== noisy/erroneous src decompression test =====*/
/* add some noise */
{ U32 const nbNoiseChunks = (FUZ_rand(&lseed) & 7) + 2;
U32 nn; for (nn=0; nn<nbNoiseChunks; nn++) {
size_t const randomNoiseSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const noiseSize = MIN((cSize/3) , randomNoiseSize);
size_t const noiseStart = FUZ_rand(&lseed) % (srcBufferSize - noiseSize);
size_t const cStart = FUZ_rand(&lseed) % (cSize - noiseSize);
memcpy(cBuffer+cStart, srcBuffer+noiseStart, noiseSize);
} }
/* try decompression on noisy data */
ZSTD_initDStream(zd_noise); /* note : no dictionary */
{ ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
while (outBuff.pos < dstBufferSize) {
size_t const randomCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(dstBufferSize - outBuff.pos, randomDstSize);
size_t const adjustedCSrcSize = MIN(cSize - inBuff.pos, randomCSrcSize);
outBuff.size = outBuff.pos + adjustedDstSize;
inBuff.size = inBuff.pos + adjustedCSrcSize;
{ size_t const decompressError = ZSTD_decompressStream(zd, &outBuff, &inBuff);
if (ZSTD_isError(decompressError)) break; /* error correctly detected */
/* No forward progress possible */
if (outBuff.pos < outBuff.size && inBuff.pos == cSize) break;
} } } }
DISPLAY("\r%u fuzzer tests completed \n", testNb);
_cleanup:
ZSTD_freeCStream(zc);
ZSTD_freeDStream(zd);
ZSTD_freeDStream(zd_noise);
free(cNoiseBuffer[0]);
free(cNoiseBuffer[1]);
free(cNoiseBuffer[2]);
free(cNoiseBuffer[3]);
free(cNoiseBuffer[4]);
free(copyBuffer);
free(cBuffer);
free(dstBuffer);
return result;
_output_error:
result = 1;
goto _cleanup;
}
/* Multi-threading version of fuzzer Tests */
static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double compressibility, int bigTests)
{
static const U32 maxSrcLog = 24;
static const U32 maxSampleLog = 19;
size_t const srcBufferSize = (size_t)1<<maxSrcLog;
BYTE* cNoiseBuffer[5];
size_t const copyBufferSize= srcBufferSize + (1<<maxSampleLog);
BYTE* const copyBuffer = (BYTE*)malloc (copyBufferSize);
size_t const cBufferSize = ZSTD_compressBound(srcBufferSize);
BYTE* const cBuffer = (BYTE*)malloc (cBufferSize);
size_t const dstBufferSize = srcBufferSize;
BYTE* const dstBuffer = (BYTE*)malloc (dstBufferSize);
U32 result = 0;
U32 testNb = 0;
U32 coreSeed = seed;
ZSTDMT_CCtx* zc = ZSTDMT_createCCtx(2); /* will be reset sometimes */
ZSTD_DStream* zd = ZSTD_createDStream(); /* will be reset sometimes */
ZSTD_DStream* const zd_noise = ZSTD_createDStream();
clock_t const startClock = clock();
const BYTE* dict=NULL; /* can keep same dict on 2 consecutive tests */
size_t dictSize = 0;
U32 oldTestLog = 0;
int const cLevelLimiter = bigTests ? 3 : 2;
U32 const cLevelMax = bigTests ? (U32)ZSTD_maxCLevel() : g_cLevelMax_smallTests;
/* allocations */
cNoiseBuffer[0] = (BYTE*)malloc (srcBufferSize);
@@ -952,15 +734,262 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
/* states full reset (deliberately not synchronized) */
/* some issues can only happen when reusing states */
if ((FUZ_rand(&lseed) & 0xFF) == 131) {
U32 const nbThreads = (FUZ_rand(&lseed) % 6) + 1;
DISPLAYLEVEL(5, "Creating new context with %u threads \n", nbThreads);
ZSTDMT_freeCCtx(zc);
zc = ZSTDMT_createCCtx(nbThreads);
ZSTD_freeCStream(zc);
zc = ZSTD_createCStream();
CHECK(zc==NULL, "ZSTD_createCStream : allocation error");
resetAllowed=0;
}
if ((FUZ_rand(&lseed) & 0xFF) == 132) {
ZSTD_freeDStream(zd);
zd = ZSTD_createDStream();
CHECK(zd==NULL, "ZSTD_createDStream : allocation error");
CHECK_Z( ZSTD_initDStream_usingDict(zd, NULL, 0) ); /* ensure at least one init */
}
/* srcBuffer selection [0-4] */
{ U32 buffNb = FUZ_rand(&lseed) & 0x7F;
if (buffNb & 7) buffNb=2; /* most common : compressible (P) */
else {
buffNb >>= 3;
if (buffNb & 7) {
const U32 tnb[2] = { 1, 3 }; /* barely/highly compressible */
buffNb = tnb[buffNb >> 3];
} else {
const U32 tnb[2] = { 0, 4 }; /* not compressible / sparse */
buffNb = tnb[buffNb >> 3];
} }
srcBuffer = cNoiseBuffer[buffNb];
}
/* compression init */
if ((FUZ_rand(&lseed)&1) /* at beginning, to keep same nb of rand */
&& oldTestLog /* at least one test happened */ && resetAllowed) {
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize)
maxTestSize = srcBufferSize-1;
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? 0 : maxTestSize;
CHECK_Z( ZSTD_resetCStream(zc, pledgedSrcSize) );
}
} else {
U32 const testLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const dictLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const cLevelCandidate = ( FUZ_rand(&lseed) %
(ZSTD_maxCLevel() -
(MAX(testLog, dictLog) / 3)))
+ 1;
U32 const cLevel = MIN(cLevelCandidate, cLevelMax);
maxTestSize = FUZ_rLogLength(&lseed, testLog);
oldTestLog = testLog;
/* random dictionary selection */
dictSize = ((FUZ_rand(&lseed)&7)==1) ? FUZ_rLogLength(&lseed, dictLog) : 0;
{ size_t const dictStart = FUZ_rand(&lseed) % (srcBufferSize - dictSize);
dict = srcBuffer + dictStart;
}
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? 0 : maxTestSize;
ZSTD_parameters params = ZSTD_getParams(cLevel, pledgedSrcSize, dictSize);
params.fParams.checksumFlag = FUZ_rand(&lseed) & 1;
params.fParams.noDictIDFlag = FUZ_rand(&lseed) & 1;
CHECK_Z ( ZSTD_initCStream_advanced(zc, dict, dictSize, params, pledgedSrcSize) );
} }
/* multi-segments compression test */
XXH64_reset(&xxhState, 0);
{ ZSTD_outBuffer outBuff = { cBuffer, cBufferSize, 0 } ;
U32 n;
for (n=0, cSize=0, totalTestSize=0 ; totalTestSize < maxTestSize ; n++) {
/* compress random chunks into randomly sized dst buffers */
{ size_t const randomSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const srcSize = MIN (maxTestSize-totalTestSize, randomSrcSize);
size_t const srcStart = FUZ_rand(&lseed) % (srcBufferSize - srcSize);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(cBufferSize - cSize, randomDstSize);
ZSTD_inBuffer inBuff = { srcBuffer+srcStart, srcSize, 0 };
outBuff.size = outBuff.pos + dstBuffSize;
CHECK_Z( ZSTD_compressStream(zc, &outBuff, &inBuff) );
XXH64_update(&xxhState, srcBuffer+srcStart, inBuff.pos);
memcpy(copyBuffer+totalTestSize, srcBuffer+srcStart, inBuff.pos);
totalTestSize += inBuff.pos;
}
/* random flush operation, to mess around */
if ((FUZ_rand(&lseed) & 15) == 0) {
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
outBuff.size = outBuff.pos + adjustedDstSize;
CHECK_Z( ZSTD_flushStream(zc, &outBuff) );
} }
/* final frame epilogue */
{ size_t remainingToFlush = (size_t)(-1);
while (remainingToFlush) {
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
outBuff.size = outBuff.pos + adjustedDstSize;
remainingToFlush = ZSTD_endStream(zc, &outBuff);
CHECK (ZSTD_isError(remainingToFlush), "end error : %s", ZSTD_getErrorName(remainingToFlush));
} }
crcOrig = XXH64_digest(&xxhState);
cSize = outBuff.pos;
}
/* multi - fragments decompression test */
if (!dictSize /* don't reset if dictionary : could be different */ && (FUZ_rand(&lseed) & 1)) {
CHECK_Z ( ZSTD_resetDStream(zd) );
} else {
CHECK_Z ( ZSTD_initDStream_usingDict(zd, dict, dictSize) );
}
{ size_t decompressionResult = 1;
ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
for (totalGenSize = 0 ; decompressionResult ; ) {
size_t const readCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(dstBufferSize - totalGenSize, randomDstSize);
inBuff.size = inBuff.pos + readCSrcSize;
outBuff.size = inBuff.pos + dstBuffSize;
decompressionResult = ZSTD_decompressStream(zd, &outBuff, &inBuff);
CHECK (ZSTD_isError(decompressionResult), "decompression error : %s", ZSTD_getErrorName(decompressionResult));
}
CHECK (decompressionResult != 0, "frame not fully decoded");
CHECK (outBuff.pos != totalTestSize, "decompressed data : wrong size")
CHECK (inBuff.pos != cSize, "compressed data should be fully read")
{ U64 const crcDest = XXH64(dstBuffer, totalTestSize, 0);
if (crcDest!=crcOrig) findDiff(copyBuffer, dstBuffer, totalTestSize);
CHECK (crcDest!=crcOrig, "decompressed data corrupted");
} }
/*===== noisy/erroneous src decompression test =====*/
/* add some noise */
{ U32 const nbNoiseChunks = (FUZ_rand(&lseed) & 7) + 2;
U32 nn; for (nn=0; nn<nbNoiseChunks; nn++) {
size_t const randomNoiseSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const noiseSize = MIN((cSize/3) , randomNoiseSize);
size_t const noiseStart = FUZ_rand(&lseed) % (srcBufferSize - noiseSize);
size_t const cStart = FUZ_rand(&lseed) % (cSize - noiseSize);
memcpy(cBuffer+cStart, srcBuffer+noiseStart, noiseSize);
} }
/* try decompression on noisy data */
CHECK_Z( ZSTD_initDStream(zd_noise) ); /* note : no dictionary */
{ ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
while (outBuff.pos < dstBufferSize) {
size_t const randomCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(dstBufferSize - outBuff.pos, randomDstSize);
size_t const adjustedCSrcSize = MIN(cSize - inBuff.pos, randomCSrcSize);
outBuff.size = outBuff.pos + adjustedDstSize;
inBuff.size = inBuff.pos + adjustedCSrcSize;
{ size_t const decompressError = ZSTD_decompressStream(zd, &outBuff, &inBuff);
if (ZSTD_isError(decompressError)) break; /* error correctly detected */
/* No forward progress possible */
if (outBuff.pos < outBuff.size && inBuff.pos == cSize) break;
} } } }
DISPLAY("\r%u fuzzer tests completed \n", testNb);
_cleanup:
ZSTD_freeCStream(zc);
ZSTD_freeDStream(zd);
ZSTD_freeDStream(zd_noise);
free(cNoiseBuffer[0]);
free(cNoiseBuffer[1]);
free(cNoiseBuffer[2]);
free(cNoiseBuffer[3]);
free(cNoiseBuffer[4]);
free(copyBuffer);
free(cBuffer);
free(dstBuffer);
return result;
_output_error:
result = 1;
goto _cleanup;
}
/* Multi-threading version of fuzzer Tests */
static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double compressibility, int bigTests)
{
const U32 maxSrcLog = bigTests ? 24 : 22;
static const U32 maxSampleLog = 19;
size_t const srcBufferSize = (size_t)1<<maxSrcLog;
BYTE* cNoiseBuffer[5];
size_t const copyBufferSize= srcBufferSize + (1<<maxSampleLog);
BYTE* const copyBuffer = (BYTE*)malloc (copyBufferSize);
size_t const cBufferSize = ZSTD_compressBound(srcBufferSize);
BYTE* const cBuffer = (BYTE*)malloc (cBufferSize);
size_t const dstBufferSize = srcBufferSize;
BYTE* const dstBuffer = (BYTE*)malloc (dstBufferSize);
U32 result = 0;
U32 testNb = 0;
U32 coreSeed = seed;
ZSTDMT_CCtx* zc = ZSTDMT_createCCtx(2); /* will be reset sometimes */
ZSTD_DStream* zd = ZSTD_createDStream(); /* will be reset sometimes */
ZSTD_DStream* const zd_noise = ZSTD_createDStream();
clock_t const startClock = clock();
const BYTE* dict=NULL; /* can keep same dict on 2 consecutive tests */
size_t dictSize = 0;
U32 oldTestLog = 0;
U32 const cLevelMax = bigTests ? (U32)ZSTD_maxCLevel() : g_cLevelMax_smallTests;
U32 const nbThreadsMax = bigTests ? 5 : 2;
/* allocations */
cNoiseBuffer[0] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[1] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[2] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[3] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[4] = (BYTE*)malloc (srcBufferSize);
CHECK (!cNoiseBuffer[0] || !cNoiseBuffer[1] || !cNoiseBuffer[2] || !cNoiseBuffer[3] || !cNoiseBuffer[4] ||
!copyBuffer || !dstBuffer || !cBuffer || !zc || !zd || !zd_noise ,
"Not enough memory, fuzzer tests cancelled");
/* Create initial samples */
RDG_genBuffer(cNoiseBuffer[0], srcBufferSize, 0.00, 0., coreSeed); /* pure noise */
RDG_genBuffer(cNoiseBuffer[1], srcBufferSize, 0.05, 0., coreSeed); /* barely compressible */
RDG_genBuffer(cNoiseBuffer[2], srcBufferSize, compressibility, 0., coreSeed);
RDG_genBuffer(cNoiseBuffer[3], srcBufferSize, 0.95, 0., coreSeed); /* highly compressible */
RDG_genBuffer(cNoiseBuffer[4], srcBufferSize, 1.00, 0., coreSeed); /* sparse content */
memset(copyBuffer, 0x65, copyBufferSize); /* make copyBuffer considered initialized */
ZSTD_initDStream_usingDict(zd, NULL, 0); /* ensure at least one init */
/* catch up testNb */
for (testNb=1; testNb < startTest; testNb++)
FUZ_rand(&coreSeed);
/* test loop */
for ( ; (testNb <= nbTests) || (FUZ_GetClockSpan(startClock) < g_clockTime) ; testNb++ ) {
U32 lseed;
const BYTE* srcBuffer;
size_t totalTestSize, totalGenSize, cSize;
XXH64_state_t xxhState;
U64 crcOrig;
U32 resetAllowed = 1;
size_t maxTestSize;
/* init */
if (nbTests >= testNb) { DISPLAYUPDATE(2, "\r%6u/%6u ", testNb, nbTests); }
else { DISPLAYUPDATE(2, "\r%6u ", testNb); }
FUZ_rand(&coreSeed);
lseed = coreSeed ^ prime32;
/* states full reset (deliberately not synchronized) */
/* some issues can only happen when reusing states */
if ((FUZ_rand(&lseed) & 0xFF) == 131) {
U32 const nbThreadsCandidate = (FUZ_rand(&lseed) % 6) + 1;
U32 const nbThreads = MIN(nbThreadsCandidate, nbThreadsMax);
DISPLAYLEVEL(5, "Creating new context with %u threads \n", nbThreads);
ZSTDMT_freeCCtx(zc);
zc = ZSTDMT_createCCtx(nbThreads);
CHECK(zc==NULL, "ZSTDMT_createCCtx allocation error")
resetAllowed=0;
}
if ((FUZ_rand(&lseed) & 0xFF) == 132) {
ZSTD_freeDStream(zd);
zd = ZSTD_createDStream();
CHECK(zd==NULL, "ZSTDMT_createCCtx allocation error")
ZSTD_initDStream_usingDict(zd, NULL, 0); /* ensure at least one init */
}
@@ -985,16 +1014,16 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize) maxTestSize = srcBufferSize-1;
{ int const compressionLevel = (FUZ_rand(&lseed) % 5) + 1;
size_t const resetError = ZSTDMT_initCStream(zc, compressionLevel);
CHECK(ZSTD_isError(resetError), "ZSTDMT_initCStream error : %s", ZSTD_getErrorName(resetError));
CHECK_Z( ZSTDMT_initCStream(zc, compressionLevel) );
}
} else {
U32 const testLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const dictLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const cLevel = (FUZ_rand(&lseed) %
(ZSTD_maxCLevel() -
(MAX(testLog, dictLog) / cLevelLimiter))) +
U32 const cLevelCandidate = (FUZ_rand(&lseed) %
(ZSTD_maxCLevel() -
(MAX(testLog, dictLog) / 3))) +
1;
U32 const cLevel = MIN(cLevelCandidate, cLevelMax);
maxTestSize = FUZ_rLogLength(&lseed, testLog);
oldTestLog = testLog;
/* random dictionary selection */
@@ -1010,10 +1039,9 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
params.fParams.noDictIDFlag = FUZ_rand(&lseed) & 1;
params.fParams.contentSizeFlag = pledgedSrcSize>0;
DISPLAYLEVEL(5, "checksumFlag : %u \n", params.fParams.checksumFlag);
{ size_t const initError = ZSTDMT_initCStream_advanced(zc, dict, dictSize, params, pledgedSrcSize);
CHECK (ZSTD_isError(initError),"ZSTDMT_initCStream_advanced error : %s", ZSTD_getErrorName(initError)); }
ZSTDMT_setMTCtxParameter(zc, ZSTDMT_p_overlapSectionLog, FUZ_rand(&lseed) % 12);
ZSTDMT_setMTCtxParameter(zc, ZSTDMT_p_sectionSize, FUZ_rand(&lseed) % (2*maxTestSize+1));
CHECK_Z( ZSTDMT_initCStream_advanced(zc, dict, dictSize, params, pledgedSrcSize) );
CHECK_Z( ZSTDMT_setMTCtxParameter(zc, ZSTDMT_p_overlapSectionLog, FUZ_rand(&lseed) % 12) );
CHECK_Z( ZSTDMT_setMTCtxParameter(zc, ZSTDMT_p_sectionSize, FUZ_rand(&lseed) % (2*maxTestSize+1)) );
} }
/* multi-segments compression test */
@@ -1031,8 +1059,7 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
outBuff.size = outBuff.pos + dstBuffSize;
DISPLAYLEVEL(5, "Sending %u bytes to compress \n", (U32)srcSize);
{ size_t const compressionError = ZSTDMT_compressStream(zc, &outBuff, &inBuff);
CHECK (ZSTD_isError(compressionError), "compression error : %s", ZSTD_getErrorName(compressionError)); }
CHECK_Z( ZSTDMT_compressStream(zc, &outBuff, &inBuff) );
DISPLAYLEVEL(5, "%u bytes read by ZSTDMT_compressStream \n", (U32)inBuff.pos);
XXH64_update(&xxhState, srcBuffer+srcStart, inBuff.pos);
@@ -1046,9 +1073,8 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
outBuff.size = outBuff.pos + adjustedDstSize;
DISPLAYLEVEL(5, "Flushing into dst buffer of size %u \n", (U32)adjustedDstSize);
{ size_t const flushError = ZSTDMT_flushStream(zc, &outBuff);
CHECK (ZSTD_isError(flushError), "ZSTDMT_flushStream error : %s", ZSTD_getErrorName(flushError));
} } }
CHECK_Z( ZSTDMT_flushStream(zc, &outBuff) );
} }
/* final frame epilogue */
{ size_t remainingToFlush = (size_t)(-1);
@@ -1068,9 +1094,9 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
/* multi - fragments decompression test */
if (!dictSize /* don't reset if dictionary : could be different */ && (FUZ_rand(&lseed) & 1)) {
CHECK (ZSTD_isError(ZSTD_resetDStream(zd)), "ZSTD_resetDStream failed");
CHECK_Z( ZSTD_resetDStream(zd) );
} else {
ZSTD_initDStream_usingDict(zd, dict, dictSize);
CHECK_Z( ZSTD_initDStream_usingDict(zd, dict, dictSize) );
}
{ size_t decompressionResult = 1;
ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
@@ -1106,7 +1132,7 @@ static int fuzzerTests_MT(U32 seed, U32 nbTests, unsigned startTest, double comp
} }
/* try decompression on noisy data */
ZSTD_initDStream(zd_noise); /* note : no dictionary */
CHECK_Z( ZSTD_initDStream(zd_noise) ); /* note : no dictionary */
{ ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
while (outBuff.pos < dstBufferSize) {
@@ -1143,6 +1169,292 @@ _output_error:
}
/* Tests for ZSTD_compress_generic() API */
static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double compressibility, int bigTests)
{
U32 const maxSrcLog = bigTests ? 24 : 22;
static const U32 maxSampleLog = 19;
size_t const srcBufferSize = (size_t)1<<maxSrcLog;
BYTE* cNoiseBuffer[5];
size_t const copyBufferSize= srcBufferSize + (1<<maxSampleLog);
BYTE* const copyBuffer = (BYTE*)malloc (copyBufferSize);
size_t const cBufferSize = ZSTD_compressBound(srcBufferSize);
BYTE* const cBuffer = (BYTE*)malloc (cBufferSize);
size_t const dstBufferSize = srcBufferSize;
BYTE* const dstBuffer = (BYTE*)malloc (dstBufferSize);
U32 result = 0;
U32 testNb = 0;
U32 coreSeed = seed;
ZSTD_CCtx* zc = ZSTD_createCCtx(); /* will be reset sometimes */
ZSTD_DStream* zd = ZSTD_createDStream(); /* will be reset sometimes */
ZSTD_DStream* const zd_noise = ZSTD_createDStream();
clock_t const startClock = clock();
const BYTE* dict = NULL; /* can keep same dict on 2 consecutive tests */
size_t dictSize = 0;
U32 oldTestLog = 0;
U32 const cLevelMax = bigTests ? (U32)ZSTD_maxCLevel() : g_cLevelMax_smallTests;
U32 const nbThreadsMax = bigTests ? 5 : 1;
/* allocations */
cNoiseBuffer[0] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[1] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[2] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[3] = (BYTE*)malloc (srcBufferSize);
cNoiseBuffer[4] = (BYTE*)malloc (srcBufferSize);
CHECK (!cNoiseBuffer[0] || !cNoiseBuffer[1] || !cNoiseBuffer[2] || !cNoiseBuffer[3] || !cNoiseBuffer[4] ||
!copyBuffer || !dstBuffer || !cBuffer || !zc || !zd || !zd_noise ,
"Not enough memory, fuzzer tests cancelled");
/* Create initial samples */
RDG_genBuffer(cNoiseBuffer[0], srcBufferSize, 0.00, 0., coreSeed); /* pure noise */
RDG_genBuffer(cNoiseBuffer[1], srcBufferSize, 0.05, 0., coreSeed); /* barely compressible */
RDG_genBuffer(cNoiseBuffer[2], srcBufferSize, compressibility, 0., coreSeed);
RDG_genBuffer(cNoiseBuffer[3], srcBufferSize, 0.95, 0., coreSeed); /* highly compressible */
RDG_genBuffer(cNoiseBuffer[4], srcBufferSize, 1.00, 0., coreSeed); /* sparse content */
memset(copyBuffer, 0x65, copyBufferSize); /* make copyBuffer considered initialized */
CHECK_Z( ZSTD_initDStream_usingDict(zd, NULL, 0) ); /* ensure at least one init */
/* catch up testNb */
for (testNb=1; testNb < startTest; testNb++)
FUZ_rand(&coreSeed);
/* test loop */
for ( ; (testNb <= nbTests) || (FUZ_GetClockSpan(startClock) < g_clockTime) ; testNb++ ) {
U32 lseed;
const BYTE* srcBuffer;
size_t totalTestSize, totalGenSize, cSize;
XXH64_state_t xxhState;
U64 crcOrig;
U32 resetAllowed = 1;
size_t maxTestSize;
/* init */
if (nbTests >= testNb) { DISPLAYUPDATE(2, "\r%6u/%6u ", testNb, nbTests); }
else { DISPLAYUPDATE(2, "\r%6u ", testNb); }
FUZ_rand(&coreSeed);
lseed = coreSeed ^ prime32;
/* states full reset (deliberately not synchronized) */
/* some issues can only happen when reusing states */
if ((FUZ_rand(&lseed) & 0xFF) == 131) {
DISPLAYLEVEL(5, "Creating new context \n");
ZSTD_freeCCtx(zc);
zc = ZSTD_createCCtx();
CHECK(zc==NULL, "ZSTD_createCCtx allocation error");
resetAllowed=0;
}
if ((FUZ_rand(&lseed) & 0xFF) == 132) {
ZSTD_freeDStream(zd);
zd = ZSTD_createDStream();
CHECK(zd==NULL, "ZSTD_createDStream allocation error");
ZSTD_initDStream_usingDict(zd, NULL, 0); /* ensure at least one init */
}
/* srcBuffer selection [0-4] */
{ U32 buffNb = FUZ_rand(&lseed) & 0x7F;
if (buffNb & 7) buffNb=2; /* most common : compressible (P) */
else {
buffNb >>= 3;
if (buffNb & 7) {
const U32 tnb[2] = { 1, 3 }; /* barely/highly compressible */
buffNb = tnb[buffNb >> 3];
} else {
const U32 tnb[2] = { 0, 4 }; /* not compressible / sparse */
buffNb = tnb[buffNb >> 3];
} }
srcBuffer = cNoiseBuffer[buffNb];
}
/* compression init */
if ((FUZ_rand(&lseed)&1) /* at beginning, to keep same nb of rand */
&& oldTestLog /* at least one test happened */ && resetAllowed) {
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize) maxTestSize = srcBufferSize-1;
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) );
{ int const compressionLevel = (FUZ_rand(&lseed) % 5) + 1;
CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_compressionLevel, compressionLevel) );
}
} else {
U32 const testLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const dictLog = FUZ_rand(&lseed) % maxSrcLog;
U32 const cLevelCandidate = (FUZ_rand(&lseed) %
(ZSTD_maxCLevel() -
(MAX(testLog, dictLog) / 3))) +
1;
U32 const cLevel = MIN(cLevelCandidate, cLevelMax);
maxTestSize = FUZ_rLogLength(&lseed, testLog);
oldTestLog = testLog;
/* random dictionary selection */
dictSize = ((FUZ_rand(&lseed)&63)==1) ? FUZ_rLogLength(&lseed, dictLog) : 0;
{ size_t const dictStart = FUZ_rand(&lseed) % (srcBufferSize - dictSize);
dict = srcBuffer + dictStart;
if (!dictSize) dict=NULL;
}
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? ZSTD_CONTENTSIZE_UNKNOWN : maxTestSize;
ZSTD_compressionParameters cParams = ZSTD_getCParams(cLevel, pledgedSrcSize, dictSize);
/* mess with compression parameters */
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) ); /* always cancel previous dict, to make user it's possible to pass compression parameters */
cParams.windowLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.hashLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.chainLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.searchLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.searchLength += (FUZ_rand(&lseed) & 3) - 1;
cParams.targetLength = (U32)(cParams.targetLength * (0.5 + ((double)(FUZ_rand(&lseed) & 127) / 128)));
cParams = ZSTD_adjustCParams(cParams, 0, 0);
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_windowLog, cParams.windowLog) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_hashLog, cParams.hashLog) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_chainLog, cParams.chainLog) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_searchLog, cParams.searchLog) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_minMatch, cParams.searchLength) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_targetLength, cParams.targetLength) );
/* unconditionally set, to be sync with decoder */
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, dict, dictSize) );
if (dict && dictSize) {
/* test that compression parameters are correctly rejected after setting a dictionary */
size_t const setError = ZSTD_CCtx_setParameter(zc, ZSTD_p_windowLog, cParams.windowLog-1) ;
CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParameter should have failed");
}
/* mess with frame parameters */
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_checksumFlag, FUZ_rand(&lseed) & 1) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_dictIDFlag, FUZ_rand(&lseed) & 1) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_contentSizeFlag, FUZ_rand(&lseed) & 1) );
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setPledgedSrcSize(zc, pledgedSrcSize) );
DISPLAYLEVEL(5, "pledgedSrcSize : %u \n", (U32)pledgedSrcSize);
/* multi-threading parameters */
{ U32 const nbThreadsCandidate = (FUZ_rand(&lseed) & 4) + 1;
U32 const nbThreads = MIN(nbThreadsCandidate, nbThreadsMax);
CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_nbThreads, nbThreads) );
if (nbThreads > 1) {
U32 const jobLog = FUZ_rand(&lseed) % (testLog+1);
CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_overlapSizeLog, FUZ_rand(&lseed) % 10) );
CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_jobSize, (U32)FUZ_rLogLength(&lseed, jobLog)) );
} } } }
/* multi-segments compression test */
XXH64_reset(&xxhState, 0);
{ ZSTD_outBuffer outBuff = { cBuffer, cBufferSize, 0 } ;
U32 n;
for (n=0, cSize=0, totalTestSize=0 ; totalTestSize < maxTestSize ; n++) {
/* compress random chunks into randomly sized dst buffers */
size_t const randomSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const srcSize = MIN(maxTestSize-totalTestSize, randomSrcSize);
size_t const srcStart = FUZ_rand(&lseed) % (srcBufferSize - srcSize);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(cBufferSize - cSize, randomDstSize);
ZSTD_EndDirective const flush = (FUZ_rand(&lseed) & 15) ? ZSTD_e_continue : ZSTD_e_flush;
ZSTD_inBuffer inBuff = { srcBuffer+srcStart, srcSize, 0 };
outBuff.size = outBuff.pos + dstBuffSize;
CHECK_Z( ZSTD_compress_generic(zc, &outBuff, &inBuff, flush) );
DISPLAYLEVEL(5, "compress consumed %u bytes (total : %u) \n",
(U32)inBuff.pos, (U32)(totalTestSize + inBuff.pos));
XXH64_update(&xxhState, srcBuffer+srcStart, inBuff.pos);
memcpy(copyBuffer+totalTestSize, srcBuffer+srcStart, inBuff.pos);
totalTestSize += inBuff.pos;
}
/* final frame epilogue */
{ size_t remainingToFlush = (size_t)(-1);
while (remainingToFlush) {
ZSTD_inBuffer inBuff = { NULL, 0, 0 };
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(cBufferSize - cSize, randomDstSize);
outBuff.size = outBuff.pos + adjustedDstSize;
DISPLAYLEVEL(5, "End-flush into dst buffer of size %u \n", (U32)adjustedDstSize);
remainingToFlush = ZSTD_compress_generic(zc, &outBuff, &inBuff, ZSTD_e_end);
CHECK(ZSTD_isError(remainingToFlush),
"ZSTD_compress_generic w/ ZSTD_e_end error : %s",
ZSTD_getErrorName(remainingToFlush) );
} }
crcOrig = XXH64_digest(&xxhState);
cSize = outBuff.pos;
DISPLAYLEVEL(5, "Frame completed : %u bytes \n", (U32)cSize);
}
/* multi - fragments decompression test */
if (!dictSize /* don't reset if dictionary : could be different */ && (FUZ_rand(&lseed) & 1)) {
CHECK_Z( ZSTD_resetDStream(zd) );
} else {
CHECK_Z( ZSTD_initDStream_usingDict(zd, dict, dictSize) );
}
{ size_t decompressionResult = 1;
ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
for (totalGenSize = 0 ; decompressionResult ; ) {
size_t const readCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const dstBuffSize = MIN(dstBufferSize - totalGenSize, randomDstSize);
inBuff.size = inBuff.pos + readCSrcSize;
outBuff.size = inBuff.pos + dstBuffSize;
DISPLAYLEVEL(5, "ZSTD_decompressStream input %u bytes \n", (U32)readCSrcSize);
decompressionResult = ZSTD_decompressStream(zd, &outBuff, &inBuff);
CHECK (ZSTD_isError(decompressionResult), "decompression error : %s", ZSTD_getErrorName(decompressionResult));
DISPLAYLEVEL(5, "inBuff.pos = %u \n", (U32)readCSrcSize);
}
CHECK (outBuff.pos != totalTestSize, "decompressed data : wrong size (%u != %u)", (U32)outBuff.pos, (U32)totalTestSize);
CHECK (inBuff.pos != cSize, "compressed data should be fully read (%u != %u)", (U32)inBuff.pos, (U32)cSize);
{ U64 const crcDest = XXH64(dstBuffer, totalTestSize, 0);
if (crcDest!=crcOrig) findDiff(copyBuffer, dstBuffer, totalTestSize);
CHECK (crcDest!=crcOrig, "decompressed data corrupted");
} }
/*===== noisy/erroneous src decompression test =====*/
/* add some noise */
{ U32 const nbNoiseChunks = (FUZ_rand(&lseed) & 7) + 2;
U32 nn; for (nn=0; nn<nbNoiseChunks; nn++) {
size_t const randomNoiseSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const noiseSize = MIN((cSize/3) , randomNoiseSize);
size_t const noiseStart = FUZ_rand(&lseed) % (srcBufferSize - noiseSize);
size_t const cStart = FUZ_rand(&lseed) % (cSize - noiseSize);
memcpy(cBuffer+cStart, srcBuffer+noiseStart, noiseSize);
} }
/* try decompression on noisy data */
CHECK_Z( ZSTD_initDStream(zd_noise) ); /* note : no dictionary */
{ ZSTD_inBuffer inBuff = { cBuffer, cSize, 0 };
ZSTD_outBuffer outBuff= { dstBuffer, dstBufferSize, 0 };
while (outBuff.pos < dstBufferSize) {
size_t const randomCSrcSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const randomDstSize = FUZ_randomLength(&lseed, maxSampleLog);
size_t const adjustedDstSize = MIN(dstBufferSize - outBuff.pos, randomDstSize);
size_t const adjustedCSrcSize = MIN(cSize - inBuff.pos, randomCSrcSize);
outBuff.size = outBuff.pos + adjustedDstSize;
inBuff.size = inBuff.pos + adjustedCSrcSize;
{ size_t const decompressError = ZSTD_decompressStream(zd, &outBuff, &inBuff);
if (ZSTD_isError(decompressError)) break; /* error correctly detected */
/* Good so far, but no more progress possible */
if (outBuff.pos < outBuff.size && inBuff.pos == cSize) break;
} } } }
DISPLAY("\r%u fuzzer tests completed \n", testNb-1);
_cleanup:
ZSTD_freeCCtx(zc);
ZSTD_freeDStream(zd);
ZSTD_freeDStream(zd_noise);
free(cNoiseBuffer[0]);
free(cNoiseBuffer[1]);
free(cNoiseBuffer[2]);
free(cNoiseBuffer[3]);
free(cNoiseBuffer[4]);
free(copyBuffer);
free(cBuffer);
free(dstBuffer);
return result;
_output_error:
result = 1;
goto _cleanup;
}
/*-*******************************************************
* Command line
*********************************************************/
@@ -1162,6 +1474,7 @@ int FUZ_usage(const char* programName)
return 0;
}
typedef enum { simple_api, mt_api, advanced_api } e_api;
int main(int argc, const char** argv)
{
@@ -1173,11 +1486,11 @@ int main(int argc, const char** argv)
int proba = FUZ_COMPRESSIBILITY_DEFAULT;
int result=0;
int mainPause = 0;
int mtOnly = 0;
int bigTests = 1;
e_api selected_api = simple_api;
const char* const programName = argv[0];
ZSTD_customMem const customMem = { allocFunction, freeFunction, NULL };
ZSTD_customMem const customNULL = { NULL, NULL, NULL };
ZSTD_customMem const customNULL = ZSTD_defaultCMem;
/* Check command line */
for(argNb=1; argNb<argc; argNb++) {
@@ -1187,7 +1500,8 @@ int main(int argc, const char** argv)
/* Parsing commands. Aggregated commands are allowed */
if (argument[0]=='-') {
if (!strcmp(argument, "--mt")) { mtOnly=1; continue; }
if (!strcmp(argument, "--mt")) { selected_api=mt_api; continue; }
if (!strcmp(argument, "--newapi")) { selected_api=advanced_api; continue; }
if (!strcmp(argument, "--no-big-tests")) { bigTests=0; continue; }
argument++;
@@ -1294,8 +1608,22 @@ int main(int argc, const char** argv)
result = basicUnitTests(0, ((double)proba) / 100, customMem); /* use custom memory allocation functions */
} }
if (!result && !mtOnly) result = fuzzerTests(seed, nbTests, testNb, ((double)proba) / 100, bigTests);
if (!result) result = fuzzerTests_MT(seed, nbTests, testNb, ((double)proba) / 100, bigTests);
if (!result) {
switch(selected_api)
{
case simple_api :
result = fuzzerTests(seed, nbTests, testNb, ((double)proba) / 100, bigTests);
break;
case mt_api :
result = fuzzerTests_MT(seed, nbTests, testNb, ((double)proba) / 100, bigTests);
break;
case advanced_api :
result = fuzzerTests_newAPI(seed, nbTests, testNb, ((double)proba) / 100, bigTests);
break;
default :
assert(0); /* impossible */
}
}
if (mainPause) {
int unused;
zlibWrapper/Makefile
+9 -6
View File
@@ -18,9 +18,12 @@ EXAMPLE_PATH = examples
PROGRAMS_PATH = ../programs
TEST_FILE = ../doc/zstd_compression_format.md
CPPFLAGS = -DXXH_NAMESPACE=ZSTD_ -I$(ZLIB_PATH) -I$(PROGRAMS_PATH) -I$(ZSTDLIBDIR) -I$(ZSTDLIBDIR)/common -I$(ZLIBWRAPPER_PATH)
CPPFLAGS = -DXXH_NAMESPACE=ZSTD_ -I$(ZLIB_PATH) -I$(PROGRAMS_PATH) \
-I$(ZSTDLIBDIR) -I$(ZSTDLIBDIR)/common -I$(ZLIBWRAPPER_PATH)
CFLAGS ?= $(MOREFLAGS) -O3 -std=gnu99
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow -Wswitch-enum -Wdeclaration-after-statement -Wstrict-prototypes -Wundef -Wstrict-aliasing=1
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow -Wswitch-enum \
-Wdeclaration-after-statement -Wstrict-prototypes -Wundef \
-Wstrict-aliasing=1
# Define *.exe as extension for Windows systems
@@ -48,8 +51,8 @@ test: example fitblk example_zstd fitblk_zstd zwrapbench minigzip minigzip_zstd
#cp example$(EXT).gz example$(EXT)_gz.gz
./minigzip_zstd -d example$(EXT).gz
@echo ---- minigzip end ----
./zwrapbench -qb3B1K $(TEST_FILE)
./zwrapbench -rqb1e5 ../lib ../programs ../tests
./zwrapbench -qi1b3B1K $(TEST_FILE)
./zwrapbench -rqi1b1e5 ../lib ../programs ../tests
#valgrindTest: ZSTDLIBRARY = $(ZSTDLIBDIR)/libzstd.so
valgrindTest: VALGRIND = LD_LIBRARY_PATH=$(ZSTDLIBDIR) valgrind --track-origins=yes --leak-check=full --error-exitcode=1
@@ -61,8 +64,8 @@ valgrindTest: clean example fitblk example_zstd fitblk_zstd zwrapbench
$(VALGRIND) ./fitblk 40960 <$(TEST_FILE)
$(VALGRIND) ./fitblk_zstd 10240 <$(TEST_FILE)
$(VALGRIND) ./fitblk_zstd 40960 <$(TEST_FILE)
$(VALGRIND) ./zwrapbench -qb3B1K $(TEST_FILE)
$(VALGRIND) ./zwrapbench -rqb1e5 ../lib ../programs ../tests
$(VALGRIND) ./zwrapbench -qi1b3B1K $(TEST_FILE)
$(VALGRIND) ./zwrapbench -rqi1b1e5 ../lib ../programs ../tests
#.c.o:
# $(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $<
zlibWrapper/examples/zwrapbench.c
+2 -2
View File
@@ -90,7 +90,7 @@ static clock_t g_time = 0;
#ifndef DEBUG
# define DEBUG 0
#endif
#define DEBUGOUTPUT(...) if (DEBUG) DISPLAY(__VA_ARGS__);
#define DEBUGOUTPUT(...) { if (DEBUG) DISPLAY(__VA_ARGS__); }
#define EXM_THROW(error, ...) \
{ \
DEBUGOUTPUT("Error defined at %s, line %i : \n", __FILE__, __LINE__); \
@@ -236,7 +236,7 @@ static int BMK_benchMem(z_const void* srcBuffer, size_t srcSize,
if (compressor == BMK_ZSTD) {
ZSTD_parameters const zparams = ZSTD_getParams(cLevel, avgSize, dictBufferSize);
ZSTD_customMem const cmem = { NULL, NULL, NULL };
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, 1, zparams.cParams, cmem);
ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, 1 /*byRef*/, ZSTD_dm_auto, zparams.cParams, cmem);
if (cdict==NULL) EXM_THROW(1, "ZSTD_createCDict_advanced() allocation failure");
do {
zlibWrapper/zstd_zlibwrapper.c
+326 -299
View File
@@ -8,35 +8,42 @@
*/
/* === Tuning parameters === */
#ifndef ZWRAP_USE_ZSTD
#define ZWRAP_USE_ZSTD 0
#endif
/* === Dependencies === */
#include <stdlib.h>
#include <stdio.h> /* vsprintf */
#include <stdarg.h> /* va_list, for z_gzprintf */
#define NO_DUMMY_DECL
#define ZLIB_CONST
#include <zlib.h> /* without #define Z_PREFIX */
#include "zstd_zlibwrapper.h"
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_MAGICNUMBER */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_isFrame, ZSTD_MAGICNUMBER */
#include "zstd.h"
#include "zstd_internal.h" /* defaultCustomMem */
#include "zstd_internal.h" /* ZSTD_malloc, ZSTD_free */
/* === Constants === */
#define Z_INFLATE_SYNC 8
#define ZLIB_HEADERSIZE 4
#define ZSTD_HEADERSIZE ZSTD_frameHeaderSize_min
#define ZWRAP_DEFAULT_CLEVEL 3 /* Z_DEFAULT_COMPRESSION is translated to ZWRAP_DEFAULT_CLEVEL for zstd */
#define LOG_WRAPPERC(...) /* printf(__VA_ARGS__) */
#define LOG_WRAPPERD(...) /* printf(__VA_ARGS__) */
/* === Debug === */
#define LOG_WRAPPERC(...) /* fprintf(stderr, __VA_ARGS__) */
#define LOG_WRAPPERD(...) /* fprintf(stderr, __VA_ARGS__) */
#define FINISH_WITH_GZ_ERR(msg) { (void)msg; return Z_STREAM_ERROR; }
#define FINISH_WITH_NULL_ERR(msg) { (void)msg; return NULL; }
#ifndef ZWRAP_USE_ZSTD
#define ZWRAP_USE_ZSTD 0
#endif
static int g_ZWRAP_useZSTDcompression = ZWRAP_USE_ZSTD; /* 0 = don't use ZSTD */
/* === Wrapper === */
static int g_ZWRAP_useZSTDcompression = ZWRAP_USE_ZSTD; /* 0 = don't use ZSTD */
void ZWRAP_useZSTDcompression(int turn_on) { g_ZWRAP_useZSTDcompression = turn_on; }
@@ -62,7 +69,7 @@ static void* ZWRAP_allocFunction(void* opaque, size_t size)
{
z_streamp strm = (z_streamp) opaque;
void* address = strm->zalloc(strm->opaque, 1, (uInt)size);
/* printf("ZWRAP alloc %p, %d \n", address, (int)size); */
/* LOG_WRAPPERC("ZWRAP alloc %p, %d \n", address, (int)size); */
return address;
}
@@ -70,12 +77,12 @@ static void ZWRAP_freeFunction(void* opaque, void* address)
{
z_streamp strm = (z_streamp) opaque;
strm->zfree(strm->opaque, address);
/* if (address) printf("ZWRAP free %p \n", address); */
/* if (address) LOG_WRAPPERC("ZWRAP free %p \n", address); */
}
/* *** Compression *** */
/* === Compression === */
typedef enum { ZWRAP_useInit, ZWRAP_useReset, ZWRAP_streamEnd } ZWRAP_state_t;
typedef struct {
@@ -95,16 +102,16 @@ typedef ZWRAP_CCtx internal_state;
size_t ZWRAP_freeCCtx(ZWRAP_CCtx* zwc)
static size_t ZWRAP_freeCCtx(ZWRAP_CCtx* zwc)
{
if (zwc==NULL) return 0; /* support free on NULL */
if (zwc->zbc) ZSTD_freeCStream(zwc->zbc);
zwc->customMem.customFree(zwc->customMem.opaque, zwc);
ZSTD_freeCStream(zwc->zbc);
ZSTD_free(zwc, zwc->customMem);
return 0;
}
ZWRAP_CCtx* ZWRAP_createCCtx(z_streamp strm)
static ZWRAP_CCtx* ZWRAP_createCCtx(z_streamp strm)
{
ZWRAP_CCtx* zwc;
@@ -113,37 +120,36 @@ ZWRAP_CCtx* ZWRAP_createCCtx(z_streamp strm)
if (zwc==NULL) return NULL;
memset(zwc, 0, sizeof(ZWRAP_CCtx));
memcpy(&zwc->allocFunc, strm, sizeof(z_stream));
{ ZSTD_customMem ZWRAP_customMem = { ZWRAP_allocFunction, ZWRAP_freeFunction, &zwc->allocFunc };
memcpy(&zwc->customMem, &ZWRAP_customMem, sizeof(ZSTD_customMem));
}
{ ZSTD_customMem const ZWRAP_customMem = { ZWRAP_allocFunction, ZWRAP_freeFunction, &zwc->allocFunc };
zwc->customMem = ZWRAP_customMem; }
} else {
zwc = (ZWRAP_CCtx*)defaultCustomMem.customAlloc(defaultCustomMem.opaque, sizeof(ZWRAP_CCtx));
zwc = (ZWRAP_CCtx*)calloc(1, sizeof(*zwc));
if (zwc==NULL) return NULL;
memset(zwc, 0, sizeof(ZWRAP_CCtx));
memcpy(&zwc->customMem, &defaultCustomMem, sizeof(ZSTD_customMem));
}
return zwc;
}
int ZWRAP_initializeCStream(ZWRAP_CCtx* zwc, const void* dict, size_t dictSize, unsigned long long pledgedSrcSize)
static int ZWRAP_initializeCStream(ZWRAP_CCtx* zwc, const void* dict, size_t dictSize, unsigned long long pledgedSrcSize)
{
LOG_WRAPPERC("- ZWRAP_initializeCStream=%p\n", zwc);
if (zwc == NULL || zwc->zbc == NULL) return Z_STREAM_ERROR;
if (!pledgedSrcSize) pledgedSrcSize = zwc->pledgedSrcSize;
{ ZSTD_parameters const params = ZSTD_getParams(zwc->compressionLevel, pledgedSrcSize, dictSize);
size_t errorCode;
LOG_WRAPPERC("pledgedSrcSize=%d windowLog=%d chainLog=%d hashLog=%d searchLog=%d searchLength=%d strategy=%d\n", (int)pledgedSrcSize, params.cParams.windowLog, params.cParams.chainLog, params.cParams.hashLog, params.cParams.searchLog, params.cParams.searchLength, params.cParams.strategy);
errorCode = ZSTD_initCStream_advanced(zwc->zbc, dict, dictSize, params, pledgedSrcSize);
if (ZSTD_isError(errorCode)) return Z_STREAM_ERROR; }
{ ZSTD_parameters const params = ZSTD_getParams(zwc->compressionLevel, pledgedSrcSize, dictSize);
size_t initErr;
LOG_WRAPPERC("pledgedSrcSize=%d windowLog=%d chainLog=%d hashLog=%d searchLog=%d searchLength=%d strategy=%d\n",
(int)pledgedSrcSize, params.cParams.windowLog, params.cParams.chainLog, params.cParams.hashLog, params.cParams.searchLog, params.cParams.searchLength, params.cParams.strategy);
initErr = ZSTD_initCStream_advanced(zwc->zbc, dict, dictSize, params, pledgedSrcSize);
if (ZSTD_isError(initErr)) return Z_STREAM_ERROR;
}
return Z_OK;
}
int ZWRAPC_finishWithError(ZWRAP_CCtx* zwc, z_streamp strm, int error)
static int ZWRAPC_finishWithError(ZWRAP_CCtx* zwc, z_streamp strm, int error)
{
LOG_WRAPPERC("- ZWRAPC_finishWithError=%d\n", error);
if (zwc) ZWRAP_freeCCtx(zwc);
@@ -152,7 +158,7 @@ int ZWRAPC_finishWithError(ZWRAP_CCtx* zwc, z_streamp strm, int error)
}
int ZWRAPC_finishWithErrorMsg(z_streamp strm, char* message)
static int ZWRAPC_finishWithErrorMsg(z_streamp strm, char* message)
{
ZWRAP_CCtx* zwc = (ZWRAP_CCtx*) strm->state;
strm->msg = message;
@@ -219,7 +225,7 @@ int ZWRAP_deflateReset_keepDict(z_streamp strm)
return deflateReset(strm);
{ ZWRAP_CCtx* zwc = (ZWRAP_CCtx*) strm->state;
if (zwc) {
if (zwc) {
zwc->streamEnd = 0;
zwc->totalInBytes = 0;
}
@@ -277,34 +283,36 @@ ZEXTERN int ZEXPORT z_deflate OF((z_streamp strm, int flush))
ZWRAP_CCtx* zwc;
if (!g_ZWRAP_useZSTDcompression) {
int res;
LOG_WRAPPERC("- deflate1 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
res = deflate(strm, flush);
return res;
LOG_WRAPPERC("- deflate1 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
return deflate(strm, flush);
}
zwc = (ZWRAP_CCtx*) strm->state;
if (zwc == NULL) { LOG_WRAPPERC("zwc == NULL\n"); return Z_STREAM_ERROR; }
if (zwc->zbc == NULL) {
int res;
zwc->zbc = ZSTD_createCStream_advanced(zwc->customMem);
if (zwc->zbc == NULL) return ZWRAPC_finishWithError(zwc, strm, 0);
res = ZWRAP_initializeCStream(zwc, NULL, 0, (flush == Z_FINISH) ? strm->avail_in : 0);
if (res != Z_OK) return ZWRAPC_finishWithError(zwc, strm, res);
{ int const initErr = ZWRAP_initializeCStream(zwc, NULL, 0, (flush == Z_FINISH) ? strm->avail_in : 0);
if (initErr != Z_OK) return ZWRAPC_finishWithError(zwc, strm, initErr); }
if (flush != Z_FINISH) zwc->comprState = ZWRAP_useReset;
} else {
if (zwc->totalInBytes == 0) {
if (zwc->comprState == ZWRAP_useReset) {
size_t const errorCode = ZSTD_resetCStream(zwc->zbc, (flush == Z_FINISH) ? strm->avail_in : zwc->pledgedSrcSize);
if (ZSTD_isError(errorCode)) { LOG_WRAPPERC("ERROR: ZSTD_resetCStream errorCode=%s\n", ZSTD_getErrorName(errorCode)); return ZWRAPC_finishWithError(zwc, strm, 0); }
size_t const resetErr = ZSTD_resetCStream(zwc->zbc, (flush == Z_FINISH) ? strm->avail_in : zwc->pledgedSrcSize);
if (ZSTD_isError(resetErr)) {
LOG_WRAPPERC("ERROR: ZSTD_resetCStream errorCode=%s\n",
ZSTD_getErrorName(resetErr));
return ZWRAPC_finishWithError(zwc, strm, 0);
}
} else {
int res = ZWRAP_initializeCStream(zwc, NULL, 0, (flush == Z_FINISH) ? strm->avail_in : 0);
int const res = ZWRAP_initializeCStream(zwc, NULL, 0, (flush == Z_FINISH) ? strm->avail_in : 0);
if (res != Z_OK) return ZWRAPC_finishWithError(zwc, strm, res);
if (flush != Z_FINISH) zwc->comprState = ZWRAP_useReset;
}
}
}
} /* (zwc->totalInBytes == 0) */
} /* ! (zwc->zbc == NULL) */
LOG_WRAPPERC("- deflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
if (strm->avail_in > 0) {
@@ -314,9 +322,9 @@ ZEXTERN int ZEXPORT z_deflate OF((z_streamp strm, int flush))
zwc->outBuffer.dst = strm->next_out;
zwc->outBuffer.size = strm->avail_out;
zwc->outBuffer.pos = 0;
{ size_t const errorCode = ZSTD_compressStream(zwc->zbc, &zwc->outBuffer, &zwc->inBuffer);
{ size_t const cErr = ZSTD_compressStream(zwc->zbc, &zwc->outBuffer, &zwc->inBuffer);
LOG_WRAPPERC("deflate ZSTD_compressStream srcSize=%d dstCapacity=%d\n", (int)zwc->inBuffer.size, (int)zwc->outBuffer.size);
if (ZSTD_isError(errorCode)) return ZWRAPC_finishWithError(zwc, strm, 0);
if (ZSTD_isError(cErr)) return ZWRAPC_finishWithError(zwc, strm, 0);
}
strm->next_out += zwc->outBuffer.pos;
strm->total_out += zwc->outBuffer.pos;
@@ -346,8 +354,12 @@ ZEXTERN int ZEXPORT z_deflate OF((z_streamp strm, int flush))
strm->next_out += zwc->outBuffer.pos;
strm->total_out += zwc->outBuffer.pos;
strm->avail_out -= zwc->outBuffer.pos;
if (bytesLeft == 0) { zwc->streamEnd = 1; LOG_WRAPPERC("Z_STREAM_END2 strm->total_in=%d strm->avail_out=%d strm->total_out=%d\n", (int)strm->total_in, (int)strm->avail_out, (int)strm->total_out); return Z_STREAM_END; }
}
if (bytesLeft == 0) {
zwc->streamEnd = 1;
LOG_WRAPPERC("Z_STREAM_END2 strm->total_in=%d strm->avail_out=%d strm->total_out=%d\n",
(int)strm->total_in, (int)strm->avail_out, (int)strm->total_out);
return Z_STREAM_END;
} }
else
if (flush == Z_SYNC_FLUSH || flush == Z_PARTIAL_FLUSH) {
size_t bytesLeft;
@@ -410,12 +422,13 @@ ZEXTERN int ZEXPORT z_deflateParams OF((z_streamp strm,
/* *** Decompression *** */
/* === Decompression === */
typedef enum { ZWRAP_ZLIB_STREAM, ZWRAP_ZSTD_STREAM, ZWRAP_UNKNOWN_STREAM } ZWRAP_stream_type;
typedef struct {
ZSTD_DStream* zbd;
char headerBuf[16]; /* should be equal or bigger than ZSTD_frameHeaderSize_min */
char headerBuf[16]; /* must be >= ZSTD_frameHeaderSize_min */
int errorCount;
unsigned long long totalInBytes; /* we need it as strm->total_in can be reset by user */
ZWRAP_state_t decompState;
@@ -427,10 +440,48 @@ typedef struct {
char *version;
int windowBits;
ZSTD_customMem customMem;
z_stream allocFunc; /* copy of zalloc, zfree, opaque */
z_stream allocFunc; /* just to copy zalloc, zfree, opaque */
} ZWRAP_DCtx;
static void ZWRAP_initDCtx(ZWRAP_DCtx* zwd)
{
zwd->errorCount = 0;
zwd->outBuffer.pos = 0;
zwd->outBuffer.size = 0;
}
static ZWRAP_DCtx* ZWRAP_createDCtx(z_streamp strm)
{
ZWRAP_DCtx* zwd;
MEM_STATIC_ASSERT(sizeof(zwd->headerBuf) >= ZSTD_FRAMEHEADERSIZE_MIN); /* check static buffer size condition */
if (strm->zalloc && strm->zfree) {
zwd = (ZWRAP_DCtx*)strm->zalloc(strm->opaque, 1, sizeof(ZWRAP_DCtx));
if (zwd==NULL) return NULL;
memset(zwd, 0, sizeof(ZWRAP_DCtx));
zwd->allocFunc = *strm; /* just to copy zalloc, zfree & opaque */
{ ZSTD_customMem const ZWRAP_customMem = { ZWRAP_allocFunction, ZWRAP_freeFunction, &zwd->allocFunc };
zwd->customMem = ZWRAP_customMem; }
} else {
zwd = (ZWRAP_DCtx*)calloc(1, sizeof(*zwd));
if (zwd==NULL) return NULL;
}
ZWRAP_initDCtx(zwd);
return zwd;
}
static size_t ZWRAP_freeDCtx(ZWRAP_DCtx* zwd)
{
if (zwd==NULL) return 0; /* support free on null */
ZSTD_freeDStream(zwd->zbd);
ZSTD_free(zwd->version, zwd->customMem);
ZSTD_free(zwd, zwd->customMem);
return 0;
}
int ZWRAP_isUsingZSTDdecompression(z_streamp strm)
{
if (strm == NULL) return 0;
@@ -438,61 +489,17 @@ int ZWRAP_isUsingZSTDdecompression(z_streamp strm)
}
void ZWRAP_initDCtx(ZWRAP_DCtx* zwd)
{
zwd->errorCount = 0;
zwd->outBuffer.pos = 0;
zwd->outBuffer.size = 0;
}
ZWRAP_DCtx* ZWRAP_createDCtx(z_streamp strm)
{
ZWRAP_DCtx* zwd;
if (strm->zalloc && strm->zfree) {
zwd = (ZWRAP_DCtx*)strm->zalloc(strm->opaque, 1, sizeof(ZWRAP_DCtx));
if (zwd==NULL) return NULL;
memset(zwd, 0, sizeof(ZWRAP_DCtx));
memcpy(&zwd->allocFunc, strm, sizeof(z_stream));
{ ZSTD_customMem ZWRAP_customMem = { ZWRAP_allocFunction, ZWRAP_freeFunction, &zwd->allocFunc };
memcpy(&zwd->customMem, &ZWRAP_customMem, sizeof(ZSTD_customMem));
}
} else {
zwd = (ZWRAP_DCtx*)defaultCustomMem.customAlloc(defaultCustomMem.opaque, sizeof(ZWRAP_DCtx));
if (zwd==NULL) return NULL;
memset(zwd, 0, sizeof(ZWRAP_DCtx));
memcpy(&zwd->customMem, &defaultCustomMem, sizeof(ZSTD_customMem));
}
MEM_STATIC_ASSERT(sizeof(zwd->headerBuf) >= ZSTD_FRAMEHEADERSIZE_MIN); /* if compilation fails here, assertion is false */
ZWRAP_initDCtx(zwd);
return zwd;
}
size_t ZWRAP_freeDCtx(ZWRAP_DCtx* zwd)
{
if (zwd==NULL) return 0; /* support free on null */
if (zwd->zbd) ZSTD_freeDStream(zwd->zbd);
if (zwd->version) zwd->customMem.customFree(zwd->customMem.opaque, zwd->version);
zwd->customMem.customFree(zwd->customMem.opaque, zwd);
return 0;
}
int ZWRAPD_finishWithError(ZWRAP_DCtx* zwd, z_streamp strm, int error)
static int ZWRAPD_finishWithError(ZWRAP_DCtx* zwd, z_streamp strm, int error)
{
LOG_WRAPPERD("- ZWRAPD_finishWithError=%d\n", error);
if (zwd) ZWRAP_freeDCtx(zwd);
if (strm) strm->state = NULL;
ZWRAP_freeDCtx(zwd);
strm->state = NULL;
return (error) ? error : Z_STREAM_ERROR;
}
int ZWRAPD_finishWithErrorMsg(z_streamp strm, char* message)
static int ZWRAPD_finishWithErrorMsg(z_streamp strm, char* message)
{
ZWRAP_DCtx* zwd = (ZWRAP_DCtx*) strm->state;
ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*) strm->state;
strm->msg = message;
if (zwd == NULL) return Z_STREAM_ERROR;
@@ -504,26 +511,25 @@ ZEXTERN int ZEXPORT z_inflateInit_ OF((z_streamp strm,
const char *version, int stream_size))
{
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB) {
strm->reserved = ZWRAP_ZLIB_STREAM; /* mark as zlib stream */
strm->reserved = ZWRAP_ZLIB_STREAM;
return inflateInit(strm);
}
{
ZWRAP_DCtx* zwd = ZWRAP_createDCtx(strm);
LOG_WRAPPERD("- inflateInit\n");
if (zwd == NULL) return ZWRAPD_finishWithError(zwd, strm, 0);
{ ZWRAP_DCtx* const zwd = ZWRAP_createDCtx(strm);
LOG_WRAPPERD("- inflateInit\n");
if (zwd == NULL) return ZWRAPD_finishWithError(zwd, strm, 0);
zwd->version = zwd->customMem.customAlloc(zwd->customMem.opaque, strlen(version) + 1);
if (zwd->version == NULL) return ZWRAPD_finishWithError(zwd, strm, 0);
strcpy(zwd->version, version);
zwd->version = ZSTD_malloc(strlen(version)+1, zwd->customMem);
if (zwd->version == NULL) return ZWRAPD_finishWithError(zwd, strm, 0);
strcpy(zwd->version, version);
zwd->stream_size = stream_size;
zwd->totalInBytes = 0;
strm->state = (struct internal_state*) zwd; /* use state which in not used by user */
strm->total_in = 0;
strm->total_out = 0;
strm->reserved = ZWRAP_UNKNOWN_STREAM; /* mark as unknown steam */
strm->adler = 0;
zwd->stream_size = stream_size;
zwd->totalInBytes = 0;
strm->state = (struct internal_state*) zwd;
strm->total_in = 0;
strm->total_out = 0;
strm->reserved = ZWRAP_UNKNOWN_STREAM;
strm->adler = 0;
}
return Z_OK;
@@ -537,15 +543,14 @@ ZEXTERN int ZEXPORT z_inflateInit2_ OF((z_streamp strm, int windowBits,
return inflateInit2_(strm, windowBits, version, stream_size);
}
{
int ret = z_inflateInit_ (strm, version, stream_size);
LOG_WRAPPERD("- inflateInit2 windowBits=%d\n", windowBits);
if (ret == Z_OK) {
ZWRAP_DCtx* zwd = (ZWRAP_DCtx*)strm->state;
if (zwd == NULL) return Z_STREAM_ERROR;
zwd->windowBits = windowBits;
}
return ret;
{ int const ret = z_inflateInit_ (strm, version, stream_size);
LOG_WRAPPERD("- inflateInit2 windowBits=%d\n", windowBits);
if (ret == Z_OK) {
ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*)strm->state;
if (zwd == NULL) return Z_STREAM_ERROR;
zwd->windowBits = windowBits;
}
return ret;
}
}
@@ -555,7 +560,7 @@ int ZWRAP_inflateReset_keepDict(z_streamp strm)
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved)
return inflateReset(strm);
{ ZWRAP_DCtx* zwd = (ZWRAP_DCtx*) strm->state;
{ ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*) strm->state;
if (zwd == NULL) return Z_STREAM_ERROR;
ZWRAP_initDCtx(zwd);
zwd->decompState = ZWRAP_useReset;
@@ -574,10 +579,10 @@ ZEXTERN int ZEXPORT z_inflateReset OF((z_streamp strm))
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved)
return inflateReset(strm);
{ int ret = ZWRAP_inflateReset_keepDict(strm);
{ int const ret = ZWRAP_inflateReset_keepDict(strm);
if (ret != Z_OK) return ret; }
{ ZWRAP_DCtx* zwd = (ZWRAP_DCtx*) strm->state;
{ ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*) strm->state;
if (zwd == NULL) return Z_STREAM_ERROR;
zwd->decompState = ZWRAP_useInit; }
@@ -592,9 +597,9 @@ ZEXTERN int ZEXPORT z_inflateReset2 OF((z_streamp strm,
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved)
return inflateReset2(strm, windowBits);
{ int ret = z_inflateReset (strm);
{ int const ret = z_inflateReset (strm);
if (ret == Z_OK) {
ZWRAP_DCtx* zwd = (ZWRAP_DCtx*)strm->state;
ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*)strm->state;
if (zwd == NULL) return Z_STREAM_ERROR;
zwd->windowBits = windowBits;
}
@@ -612,11 +617,10 @@ ZEXTERN int ZEXPORT z_inflateSetDictionary OF((z_streamp strm,
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved)
return inflateSetDictionary(strm, dictionary, dictLength);
{ size_t errorCode;
ZWRAP_DCtx* zwd = (ZWRAP_DCtx*) strm->state;
{ ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*) strm->state;
if (zwd == NULL || zwd->zbd == NULL) return Z_STREAM_ERROR;
errorCode = ZSTD_initDStream_usingDict(zwd->zbd, dictionary, dictLength);
if (ZSTD_isError(errorCode)) return ZWRAPD_finishWithError(zwd, strm, 0);
{ size_t const initErr = ZSTD_initDStream_usingDict(zwd->zbd, dictionary, dictLength);
if (ZSTD_isError(initErr)) return ZWRAPD_finishWithError(zwd, strm, 0); }
zwd->decompState = ZWRAP_useReset;
if (zwd->totalInBytes == ZSTD_HEADERSIZE) {
@@ -626,14 +630,14 @@ ZEXTERN int ZEXPORT z_inflateSetDictionary OF((z_streamp strm,
zwd->outBuffer.dst = strm->next_out;
zwd->outBuffer.size = 0;
zwd->outBuffer.pos = 0;
errorCode = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflateSetDictionary ZSTD_decompressStream errorCode=%d srcSize=%d dstCapacity=%d\n", (int)errorCode, (int)zwd->inBuffer.size, (int)zwd->outBuffer.size);
if (zwd->inBuffer.pos < zwd->outBuffer.size || ZSTD_isError(errorCode)) {
LOG_WRAPPERD("ERROR: ZSTD_decompressStream %s\n", ZSTD_getErrorName(errorCode));
return ZWRAPD_finishWithError(zwd, strm, 0);
}
}
}
{ size_t const errorCode = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflateSetDictionary ZSTD_decompressStream errorCode=%d srcSize=%d dstCapacity=%d\n",
(int)errorCode, (int)zwd->inBuffer.size, (int)zwd->outBuffer.size);
if (zwd->inBuffer.pos < zwd->outBuffer.size || ZSTD_isError(errorCode)) {
LOG_WRAPPERD("ERROR: ZSTD_decompressStream %s\n",
ZSTD_getErrorName(errorCode));
return ZWRAPD_finishWithError(zwd, strm, 0);
} } } }
return Z_OK;
}
@@ -642,156 +646,175 @@ ZEXTERN int ZEXPORT z_inflateSetDictionary OF((z_streamp strm,
ZEXTERN int ZEXPORT z_inflate OF((z_streamp strm, int flush))
{
ZWRAP_DCtx* zwd;
int res;
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved) {
LOG_WRAPPERD("- inflate1 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
res = inflate(strm, flush);
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, res);
return res;
int const result = inflate(strm, flush);
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, result);
return result;
}
if (strm->avail_in <= 0) return Z_OK;
{ size_t errorCode, srcSize;
zwd = (ZWRAP_DCtx*) strm->state;
LOG_WRAPPERD("- inflate1 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
zwd = (ZWRAP_DCtx*) strm->state;
LOG_WRAPPERD("- inflate1 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
if (zwd == NULL) return Z_STREAM_ERROR;
if (zwd->decompState == ZWRAP_streamEnd) return Z_STREAM_END;
if (zwd == NULL) return Z_STREAM_ERROR;
if (zwd->decompState == ZWRAP_streamEnd) return Z_STREAM_END;
if (zwd->totalInBytes < ZLIB_HEADERSIZE) {
if (zwd->totalInBytes == 0 && strm->avail_in >= ZLIB_HEADERSIZE) {
if (MEM_readLE32(strm->next_in) != ZSTD_MAGICNUMBER) {
if (zwd->windowBits)
errorCode = inflateInit2_(strm, zwd->windowBits, zwd->version, zwd->stream_size);
else
errorCode = inflateInit_(strm, zwd->version, zwd->stream_size);
strm->reserved = ZWRAP_ZLIB_STREAM; /* mark as zlib stream */
errorCode = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(errorCode)) goto error;
if (flush == Z_INFLATE_SYNC) res = inflateSync(strm);
else res = inflate(strm, flush);
LOG_WRAPPERD("- inflate3 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, res);
return res;
}
} else {
srcSize = MIN(strm->avail_in, ZLIB_HEADERSIZE - zwd->totalInBytes);
memcpy(zwd->headerBuf+zwd->totalInBytes, strm->next_in, srcSize);
strm->total_in += srcSize;
zwd->totalInBytes += srcSize;
strm->next_in += srcSize;
strm->avail_in -= srcSize;
if (zwd->totalInBytes < ZLIB_HEADERSIZE) return Z_OK;
if (MEM_readLE32(zwd->headerBuf) != ZSTD_MAGICNUMBER) {
z_stream strm2;
strm2.next_in = strm->next_in;
strm2.avail_in = strm->avail_in;
strm2.next_out = strm->next_out;
strm2.avail_out = strm->avail_out;
if (zwd->windowBits)
errorCode = inflateInit2_(strm, zwd->windowBits, zwd->version, zwd->stream_size);
else
errorCode = inflateInit_(strm, zwd->version, zwd->stream_size);
LOG_WRAPPERD("ZLIB inflateInit errorCode=%d\n", (int)errorCode);
if (errorCode != Z_OK) return ZWRAPD_finishWithError(zwd, strm, (int)errorCode);
/* inflate header */
strm->next_in = (unsigned char*)zwd->headerBuf;
strm->avail_in = ZLIB_HEADERSIZE;
strm->avail_out = 0;
errorCode = inflate(strm, Z_NO_FLUSH);
LOG_WRAPPERD("ZLIB inflate errorCode=%d strm->avail_in=%d\n", (int)errorCode, (int)strm->avail_in);
if (errorCode != Z_OK) return ZWRAPD_finishWithError(zwd, strm, (int)errorCode);
if (strm->avail_in > 0) goto error;
strm->next_in = strm2.next_in;
strm->avail_in = strm2.avail_in;
strm->next_out = strm2.next_out;
strm->avail_out = strm2.avail_out;
strm->reserved = ZWRAP_ZLIB_STREAM; /* mark as zlib stream */
errorCode = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(errorCode)) goto error;
if (flush == Z_INFLATE_SYNC) res = inflateSync(strm);
else res = inflate(strm, flush);
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, res);
return res;
}
}
}
strm->reserved = ZWRAP_ZSTD_STREAM; /* mark as zstd steam */
if (flush == Z_INFLATE_SYNC) { strm->msg = "inflateSync is not supported!"; goto error; }
if (!zwd->zbd) {
zwd->zbd = ZSTD_createDStream_advanced(zwd->customMem);
if (zwd->zbd == NULL) { LOG_WRAPPERD("ERROR: ZSTD_createDStream_advanced\n"); goto error; }
zwd->decompState = ZWRAP_useInit;
}
if (zwd->totalInBytes < ZSTD_HEADERSIZE)
{
if (zwd->totalInBytes == 0 && strm->avail_in >= ZSTD_HEADERSIZE) {
if (zwd->decompState == ZWRAP_useInit) {
errorCode = ZSTD_initDStream(zwd->zbd);
if (ZSTD_isError(errorCode)) { LOG_WRAPPERD("ERROR: ZSTD_initDStream errorCode=%s\n", ZSTD_getErrorName(errorCode)); goto error; }
} else {
errorCode = ZSTD_resetDStream(zwd->zbd);
if (ZSTD_isError(errorCode)) goto error;
}
} else {
srcSize = MIN(strm->avail_in, ZSTD_HEADERSIZE - zwd->totalInBytes);
memcpy(zwd->headerBuf+zwd->totalInBytes, strm->next_in, srcSize);
strm->total_in += srcSize;
zwd->totalInBytes += srcSize;
strm->next_in += srcSize;
strm->avail_in -= srcSize;
if (zwd->totalInBytes < ZSTD_HEADERSIZE) return Z_OK;
if (zwd->decompState == ZWRAP_useInit) {
errorCode = ZSTD_initDStream(zwd->zbd);
if (ZSTD_isError(errorCode)) { LOG_WRAPPERD("ERROR: ZSTD_initDStream errorCode=%s\n", ZSTD_getErrorName(errorCode)); goto error; }
} else {
errorCode = ZSTD_resetDStream(zwd->zbd);
if (ZSTD_isError(errorCode)) goto error;
if (zwd->totalInBytes < ZLIB_HEADERSIZE) {
if (zwd->totalInBytes == 0 && strm->avail_in >= ZLIB_HEADERSIZE) {
if (MEM_readLE32(strm->next_in) != ZSTD_MAGICNUMBER) {
{ int const initErr = (zwd->windowBits) ?
inflateInit2_(strm, zwd->windowBits, zwd->version, zwd->stream_size) :
inflateInit_(strm, zwd->version, zwd->stream_size);
LOG_WRAPPERD("ZLIB inflateInit errorCode=%d\n", initErr);
if (initErr != Z_OK) return ZWRAPD_finishWithError(zwd, strm, initErr);
}
zwd->inBuffer.src = zwd->headerBuf;
zwd->inBuffer.size = ZSTD_HEADERSIZE;
zwd->inBuffer.pos = 0;
zwd->outBuffer.dst = strm->next_out;
zwd->outBuffer.size = 0;
zwd->outBuffer.pos = 0;
errorCode = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflate ZSTD_decompressStream1 errorCode=%d srcSize=%d dstCapacity=%d\n", (int)errorCode, (int)zwd->inBuffer.size, (int)zwd->outBuffer.size);
if (ZSTD_isError(errorCode)) {
LOG_WRAPPERD("ERROR: ZSTD_decompressStream1 %s\n", ZSTD_getErrorName(errorCode));
strm->reserved = ZWRAP_ZLIB_STREAM;
{ size_t const freeErr = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(freeErr)) goto error; }
{ int const result = (flush == Z_INFLATE_SYNC) ?
inflateSync(strm) :
inflate(strm, flush);
LOG_WRAPPERD("- inflate3 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, res);
return result;
} }
} else { /* ! (zwd->totalInBytes == 0 && strm->avail_in >= ZLIB_HEADERSIZE) */
size_t const srcSize = MIN(strm->avail_in, ZLIB_HEADERSIZE - zwd->totalInBytes);
memcpy(zwd->headerBuf+zwd->totalInBytes, strm->next_in, srcSize);
strm->total_in += srcSize;
zwd->totalInBytes += srcSize;
strm->next_in += srcSize;
strm->avail_in -= srcSize;
if (zwd->totalInBytes < ZLIB_HEADERSIZE) return Z_OK;
if (MEM_readLE32(zwd->headerBuf) != ZSTD_MAGICNUMBER) {
z_stream strm2;
strm2.next_in = strm->next_in;
strm2.avail_in = strm->avail_in;
strm2.next_out = strm->next_out;
strm2.avail_out = strm->avail_out;
{ int const initErr = (zwd->windowBits) ?
inflateInit2_(strm, zwd->windowBits, zwd->version, zwd->stream_size) :
inflateInit_(strm, zwd->version, zwd->stream_size);
LOG_WRAPPERD("ZLIB inflateInit errorCode=%d\n", initErr);
if (initErr != Z_OK) return ZWRAPD_finishWithError(zwd, strm, initErr);
}
/* inflate header */
strm->next_in = (unsigned char*)zwd->headerBuf;
strm->avail_in = ZLIB_HEADERSIZE;
strm->avail_out = 0;
{ int const dErr = inflate(strm, Z_NO_FLUSH);
LOG_WRAPPERD("ZLIB inflate errorCode=%d strm->avail_in=%d\n",
dErr, (int)strm->avail_in);
if (dErr != Z_OK)
return ZWRAPD_finishWithError(zwd, strm, dErr);
}
if (strm->avail_in > 0) goto error;
strm->next_in = strm2.next_in;
strm->avail_in = strm2.avail_in;
strm->next_out = strm2.next_out;
strm->avail_out = strm2.avail_out;
strm->reserved = ZWRAP_ZLIB_STREAM; /* mark as zlib stream */
{ size_t const freeErr = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(freeErr)) goto error; }
{ int const result = (flush == Z_INFLATE_SYNC) ?
inflateSync(strm) :
inflate(strm, flush);
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, res);
return result;
} } } /* if ! (zwd->totalInBytes == 0 && strm->avail_in >= ZLIB_HEADERSIZE) */
} /* (zwd->totalInBytes < ZLIB_HEADERSIZE) */
strm->reserved = ZWRAP_ZSTD_STREAM; /* mark as zstd steam */
if (flush == Z_INFLATE_SYNC) { strm->msg = "inflateSync is not supported!"; goto error; }
if (!zwd->zbd) {
zwd->zbd = ZSTD_createDStream_advanced(zwd->customMem);
if (zwd->zbd == NULL) { LOG_WRAPPERD("ERROR: ZSTD_createDStream_advanced\n"); goto error; }
zwd->decompState = ZWRAP_useInit;
}
if (zwd->totalInBytes < ZSTD_HEADERSIZE) {
if (zwd->totalInBytes == 0 && strm->avail_in >= ZSTD_HEADERSIZE) {
if (zwd->decompState == ZWRAP_useInit) {
size_t const initErr = ZSTD_initDStream(zwd->zbd);
if (ZSTD_isError(initErr)) {
LOG_WRAPPERD("ERROR: ZSTD_initDStream errorCode=%s\n",
ZSTD_getErrorName(initErr));
goto error;
}
if (zwd->inBuffer.pos != zwd->inBuffer.size) goto error; /* not consumed */
} else {
size_t const resetErr = ZSTD_resetDStream(zwd->zbd);
if (ZSTD_isError(resetErr)) goto error;
}
}
} else {
size_t const srcSize = MIN(strm->avail_in, ZSTD_HEADERSIZE - zwd->totalInBytes);
memcpy(zwd->headerBuf+zwd->totalInBytes, strm->next_in, srcSize);
strm->total_in += srcSize;
zwd->totalInBytes += srcSize;
strm->next_in += srcSize;
strm->avail_in -= srcSize;
if (zwd->totalInBytes < ZSTD_HEADERSIZE) return Z_OK;
zwd->inBuffer.src = strm->next_in;
zwd->inBuffer.size = strm->avail_in;
zwd->inBuffer.pos = 0;
zwd->outBuffer.dst = strm->next_out;
zwd->outBuffer.size = strm->avail_out;
zwd->outBuffer.pos = 0;
errorCode = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflate ZSTD_decompressStream2 errorCode=%d srcSize=%d dstCapacity=%d\n", (int)errorCode, (int)strm->avail_in, (int)strm->avail_out);
if (ZSTD_isError(errorCode)) {
if (zwd->decompState == ZWRAP_useInit) {
size_t const initErr = ZSTD_initDStream(zwd->zbd);
if (ZSTD_isError(initErr)) {
LOG_WRAPPERD("ERROR: ZSTD_initDStream errorCode=%s\n",
ZSTD_getErrorName(initErr));
goto error;
}
} else {
size_t const resetErr = ZSTD_resetDStream(zwd->zbd);
if (ZSTD_isError(resetErr)) goto error;
}
zwd->inBuffer.src = zwd->headerBuf;
zwd->inBuffer.size = ZSTD_HEADERSIZE;
zwd->inBuffer.pos = 0;
zwd->outBuffer.dst = strm->next_out;
zwd->outBuffer.size = 0;
zwd->outBuffer.pos = 0;
{ size_t const dErr = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflate ZSTD_decompressStream1 errorCode=%d srcSize=%d dstCapacity=%d\n",
(int)dErr, (int)zwd->inBuffer.size, (int)zwd->outBuffer.size);
if (ZSTD_isError(dErr)) {
LOG_WRAPPERD("ERROR: ZSTD_decompressStream1 %s\n", ZSTD_getErrorName(dErr));
goto error;
} }
if (zwd->inBuffer.pos != zwd->inBuffer.size) goto error; /* not consumed */
}
} /* (zwd->totalInBytes < ZSTD_HEADERSIZE) */
zwd->inBuffer.src = strm->next_in;
zwd->inBuffer.size = strm->avail_in;
zwd->inBuffer.pos = 0;
zwd->outBuffer.dst = strm->next_out;
zwd->outBuffer.size = strm->avail_out;
zwd->outBuffer.pos = 0;
{ size_t const dErr = ZSTD_decompressStream(zwd->zbd, &zwd->outBuffer, &zwd->inBuffer);
LOG_WRAPPERD("inflate ZSTD_decompressStream2 errorCode=%d srcSize=%d dstCapacity=%d\n",
(int)dErr, (int)strm->avail_in, (int)strm->avail_out);
if (ZSTD_isError(dErr)) {
zwd->errorCount++;
LOG_WRAPPERD("ERROR: ZSTD_decompressStream2 %s zwd->errorCount=%d\n", ZSTD_getErrorName(errorCode), zwd->errorCount);
LOG_WRAPPERD("ERROR: ZSTD_decompressStream2 %s zwd->errorCount=%d\n",
ZSTD_getErrorName(dErr), zwd->errorCount);
if (zwd->errorCount<=1) return Z_NEED_DICT; else goto error;
}
LOG_WRAPPERD("inflate inBuffer.pos=%d inBuffer.size=%d outBuffer.pos=%d outBuffer.size=%d o\n", (int)zwd->inBuffer.pos, (int)zwd->inBuffer.size, (int)zwd->outBuffer.pos, (int)zwd->outBuffer.size);
LOG_WRAPPERD("inflate inBuffer.pos=%d inBuffer.size=%d outBuffer.pos=%d outBuffer.size=%d o\n",
(int)zwd->inBuffer.pos, (int)zwd->inBuffer.size, (int)zwd->outBuffer.pos, (int)zwd->outBuffer.size);
strm->next_out += zwd->outBuffer.pos;
strm->total_out += zwd->outBuffer.pos;
strm->avail_out -= zwd->outBuffer.pos;
@@ -799,13 +822,16 @@ ZEXTERN int ZEXPORT z_inflate OF((z_streamp strm, int flush))
zwd->totalInBytes += zwd->inBuffer.pos;
strm->next_in += zwd->inBuffer.pos;
strm->avail_in -= zwd->inBuffer.pos;
if (errorCode == 0) {
LOG_WRAPPERD("inflate Z_STREAM_END1 avail_in=%d avail_out=%d total_in=%d total_out=%d\n", (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
if (dErr == 0) {
LOG_WRAPPERD("inflate Z_STREAM_END1 avail_in=%d avail_out=%d total_in=%d total_out=%d\n",
(int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out);
zwd->decompState = ZWRAP_streamEnd;
return Z_STREAM_END;
}
}
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n", (int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, Z_OK);
} /* dErr lifetime */
LOG_WRAPPERD("- inflate2 flush=%d avail_in=%d avail_out=%d total_in=%d total_out=%d res=%d\n",
(int)flush, (int)strm->avail_in, (int)strm->avail_out, (int)strm->total_in, (int)strm->total_out, Z_OK);
return Z_OK;
error:
@@ -818,13 +844,13 @@ ZEXTERN int ZEXPORT z_inflateEnd OF((z_streamp strm))
if (g_ZWRAPdecompressionType == ZWRAP_FORCE_ZLIB || !strm->reserved)
return inflateEnd(strm);
LOG_WRAPPERD("- inflateEnd total_in=%d total_out=%d\n", (int)(strm->total_in), (int)(strm->total_out));
{ size_t errorCode;
ZWRAP_DCtx* zwd = (ZWRAP_DCtx*) strm->state;
LOG_WRAPPERD("- inflateEnd total_in=%d total_out=%d\n",
(int)(strm->total_in), (int)(strm->total_out));
{ ZWRAP_DCtx* const zwd = (ZWRAP_DCtx*) strm->state;
if (zwd == NULL) return Z_OK; /* structures are already freed */
{ size_t const freeErr = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(freeErr)) return Z_STREAM_ERROR; }
strm->state = NULL;
errorCode = ZWRAP_freeDCtx(zwd);
if (ZSTD_isError(errorCode)) return Z_STREAM_ERROR;
}
return Z_OK;
}
@@ -841,8 +867,6 @@ ZEXTERN int ZEXPORT z_inflateSync OF((z_streamp strm))
/* Advanced compression functions */
ZEXTERN int ZEXPORT z_deflateCopy OF((z_streamp dest,
z_streamp source))
@@ -982,7 +1006,7 @@ ZEXTERN uLong ZEXPORT z_zlibCompileFlags OF((void)) { return zlibCompileFlags();
/* utility functions */
/* === utility functions === */
#ifndef Z_SOLO
ZEXTERN int ZEXPORT z_compress OF((Bytef *dest, uLongf *destLen,
@@ -991,11 +1015,14 @@ ZEXTERN int ZEXPORT z_compress OF((Bytef *dest, uLongf *destLen,
if (!g_ZWRAP_useZSTDcompression)
return compress(dest, destLen, source, sourceLen);
{ size_t dstCapacity = *destLen;
size_t const errorCode = ZSTD_compress(dest, dstCapacity, source, sourceLen, ZWRAP_DEFAULT_CLEVEL);
LOG_WRAPPERD("z_compress sourceLen=%d dstCapacity=%d\n", (int)sourceLen, (int)dstCapacity);
if (ZSTD_isError(errorCode)) return Z_STREAM_ERROR;
*destLen = errorCode;
{ size_t dstCapacity = *destLen;
size_t const cSize = ZSTD_compress(dest, dstCapacity,
source, sourceLen,
ZWRAP_DEFAULT_CLEVEL);
LOG_WRAPPERD("z_compress sourceLen=%d dstCapacity=%d\n",
(int)sourceLen, (int)dstCapacity);
if (ZSTD_isError(cSize)) return Z_STREAM_ERROR;
*destLen = cSize;
}
return Z_OK;
}
@@ -1009,9 +1036,9 @@ ZEXTERN int ZEXPORT z_compress2 OF((Bytef *dest, uLongf *destLen,
return compress2(dest, destLen, source, sourceLen, level);
{ size_t dstCapacity = *destLen;
size_t const errorCode = ZSTD_compress(dest, dstCapacity, source, sourceLen, level);
if (ZSTD_isError(errorCode)) return Z_STREAM_ERROR;
*destLen = errorCode;
size_t const cSize = ZSTD_compress(dest, dstCapacity, source, sourceLen, level);
if (ZSTD_isError(cSize)) return Z_STREAM_ERROR;
*destLen = cSize;
}
return Z_OK;
}
@@ -1029,13 +1056,13 @@ ZEXTERN uLong ZEXPORT z_compressBound OF((uLong sourceLen))
ZEXTERN int ZEXPORT z_uncompress OF((Bytef *dest, uLongf *destLen,
const Bytef *source, uLong sourceLen))
{
if (sourceLen < 4 || MEM_readLE32(source) != ZSTD_MAGICNUMBER)
if (!ZSTD_isFrame(source, sourceLen))
return uncompress(dest, destLen, source, sourceLen);
{ size_t dstCapacity = *destLen;
size_t const errorCode = ZSTD_decompress(dest, dstCapacity, source, sourceLen);
if (ZSTD_isError(errorCode)) return Z_STREAM_ERROR;
*destLen = errorCode;
size_t const dSize = ZSTD_decompress(dest, dstCapacity, source, sourceLen);
if (ZSTD_isError(dSize)) return Z_STREAM_ERROR;
*destLen = dSize;
}
return Z_OK;
}