Commit 9915003e authored by Brad King's avatar Brad King Committed by Kitware Robot
Browse files

Merge topic 'import-zstd'

1761a9a5 CMake: Enable use of zstd in libarchive
2cf29217 zstd: Add CMake build system
f92b4b52 Merge branch 'upstream-zstd' into import-zstd
fbaf6563 zstd 2018-12-27 (470344d3)
9337cbfc

 zstd: add script to import zstd from upstream
Acked-by: Kitware Robot's avatarKitware Robot <kwrobot@kitware.com>
Acked-by: Bartosz's avatarBartosz <gang65@poczta.onet.pl>
Merge-request: !3092
parents 101621ee 1761a9a5
Pipeline #132198 passed with stage
in 0 seconds
......@@ -139,7 +139,7 @@ macro(CMAKE_HANDLE_SYSTEM_LIBRARIES)
# Allow the user to enable/disable all system utility library options by
# defining CMAKE_USE_SYSTEM_LIBRARIES or CMAKE_USE_SYSTEM_LIBRARY_${util}.
set(UTILITIES BZIP2 CURL EXPAT FORM JSONCPP LIBARCHIVE LIBLZMA LIBRHASH LIBUV ZLIB)
set(UTILITIES BZIP2 CURL EXPAT FORM JSONCPP LIBARCHIVE LIBLZMA LIBRHASH LIBUV ZLIB ZSTD)
foreach(util ${UTILITIES})
if(NOT DEFINED CMAKE_USE_SYSTEM_LIBRARY_${util}
AND DEFINED CMAKE_USE_SYSTEM_LIBRARIES)
......@@ -173,6 +173,8 @@ macro(CMAKE_HANDLE_SYSTEM_LIBRARIES)
"${CMAKE_USE_SYSTEM_LIBRARY_ZLIB}" "NOT CMAKE_USE_SYSTEM_LIBARCHIVE;NOT CMAKE_USE_SYSTEM_CURL" ON)
CMAKE_DEPENDENT_OPTION(CMAKE_USE_SYSTEM_BZIP2 "Use system-installed bzip2"
"${CMAKE_USE_SYSTEM_LIBRARY_BZIP2}" "NOT CMAKE_USE_SYSTEM_LIBARCHIVE" ON)
CMAKE_DEPENDENT_OPTION(CMAKE_USE_SYSTEM_ZSTD "Use system-installed zstd"
"${CMAKE_USE_SYSTEM_LIBRARY_ZSTD}" "NOT CMAKE_USE_SYSTEM_LIBARCHIVE" ON)
CMAKE_DEPENDENT_OPTION(CMAKE_USE_SYSTEM_LIBLZMA "Use system-installed liblzma"
"${CMAKE_USE_SYSTEM_LIBRARY_LIBLZMA}" "NOT CMAKE_USE_SYSTEM_LIBARCHIVE" ON)
option(CMAKE_USE_SYSTEM_FORM "Use system-installed libform" "${CMAKE_USE_SYSTEM_LIBRARY_FORM}")
......@@ -475,6 +477,17 @@ macro (CMAKE_BUILD_UTILITIES)
endif()
endif()
#---------------------------------------------------------------------
# Build or use system zstd for libarchive.
if(NOT CMAKE_USE_SYSTEM_LIBARCHIVE)
if(NOT CMAKE_USE_SYSTEM_ZSTD)
set(ZSTD_INCLUDE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/Utilities/cmzstd")
set(ZSTD_LIBRARY cmzstd)
add_subdirectory(Utilities/cmzstd)
CMAKE_SET_TARGET_FOLDER(cmzstd "Utilities/3rdParty")
endif()
endif()
#---------------------------------------------------------------------
# Build or use system liblzma for libarchive.
if(NOT CMAKE_USE_SYSTEM_LIBARCHIVE)
......
#!/usr/bin/env bash
set -e
set -x
shopt -s dotglob
readonly name="zstd"
readonly ownership="zstd upstream <kwrobot@kitware.com>"
readonly subtree="Utilities/cmzstd"
readonly repo="https://github.com/facebook/zstd.git"
readonly tag="v1.3.8"
readonly shortlog=false
readonly paths="
LICENSE
README.md
lib/common/*.c
lib/common/*.h
lib/compress/*.c
lib/compress/*.h
lib/decompress/*.c
lib/decompress/*.h
lib/deprecated/*.c
lib/deprecated/*.h
lib/dictBuilder/*.c
lib/dictBuilder/*.h
lib/zstd.h
"
extract_source () {
git_archive
pushd "${extractdir}/${name}-reduced"
echo "* -whitespace" > .gitattributes
popd
}
. "${BASH_SOURCE%/*}/update-third-party.bash"
......@@ -15,5 +15,6 @@
#cmakedefine CMAKE_USE_SYSTEM_JSONCPP
#cmakedefine CMAKE_USE_SYSTEM_LIBRHASH
#cmakedefine CMAKE_USE_SYSTEM_LIBUV
#cmakedefine CMAKE_USE_SYSTEM_ZSTD
#endif
/* Distributed under the OSI-approved BSD 3-Clause License. See accompanying
file Copyright.txt or https://cmake.org/licensing for details. */
#ifndef cm_zstd_h
#define cm_zstd_h
/* Use the libzstd configured for CMake. */
#include "cmThirdParty.h"
#ifdef CMAKE_USE_SYSTEM_ZSTD
# include <zstd.h>
#else
# include <cmzstd/lib/zstd.h>
#endif
#endif
......@@ -376,6 +376,7 @@ IF(LZ4_FOUND)
ENDIF(LZ4_FOUND)
MARK_AS_ADVANCED(CLEAR LZ4_INCLUDE_DIR)
MARK_AS_ADVANCED(CLEAR LZ4_LIBRARY)
ENDIF()
#
# Find Zstd
#
......@@ -392,16 +393,13 @@ IF(ZSTD_FOUND)
SET(HAVE_ZSTD_H 1)
INCLUDE_DIRECTORIES(${ZSTD_INCLUDE_DIR})
LIST(APPEND ADDITIONAL_LIBS ${ZSTD_LIBRARY})
SET(CMAKE_REQUIRED_LIBRARIES ${ZSTD_LIBRARY})
SET(CMAKE_REQUIRED_INCLUDES ${ZSTD_INCLUDE_DIR})
CHECK_FUNCTION_EXISTS(ZSTD_compressStream HAVE_LIBZSTD)
SET(HAVE_LIBZSTD 1)
#
# TODO: test for static library.
#
ENDIF(ZSTD_FOUND)
MARK_AS_ADVANCED(CLEAR ZSTD_INCLUDE_DIR)
MARK_AS_ADVANCED(CLEAR ZSTD_LIBRARY)
ENDIF()
#
# Check headers
......
......@@ -45,7 +45,7 @@ __FBSDID("$FreeBSD$");
#include <unistd.h>
#endif
#if HAVE_ZSTD_H
#include <zstd.h>
#include <cm_zstd.h>
#endif
#include "archive.h"
......
......@@ -46,7 +46,7 @@ __FBSDID("$FreeBSD: head/lib/libarchive/archive_util.c 201098 2009-12-28 02:58:1
#include <lz4.h>
#endif
#ifdef HAVE_ZSTD_H
#include <zstd.h>
#include <cm_zstd.h>
#endif
#include "archive.h"
......
......@@ -38,7 +38,7 @@ __FBSDID("$FreeBSD$");
#include <string.h>
#endif
#ifdef HAVE_ZSTD_H
#include <zstd.h>
#include <cm_zstd.h>
#endif
#include "archive.h"
......
project(zstd C)
# Disable warnings to avoid changing 3rd party code.
if(CMAKE_C_COMPILER_ID MATCHES
"^(GNU|Clang|AppleClang|XLClang|XL|VisualAge|SunPro|HP|Intel)$")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w")
elseif(CMAKE_C_COMPILER_ID STREQUAL "PathScale")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -woffall")
endif()
include_directories(lib lib/common)
add_library(cmzstd STATIC
lib/common/entropy_common.c
lib/common/error_private.c
lib/common/fse_decompress.c
lib/common/pool.c
lib/common/threading.c
lib/common/xxhash.c
lib/common/zstd_common.c
lib/compress/fse_compress.c
lib/compress/hist.c
lib/compress/huf_compress.c
lib/compress/zstd_compress.c
lib/compress/zstd_double_fast.c
lib/compress/zstd_fast.c
lib/compress/zstd_lazy.c
lib/compress/zstd_ldm.c
lib/compress/zstdmt_compress.c
lib/compress/zstd_opt.c
lib/decompress/huf_decompress.c
lib/decompress/zstd_ddict.c
lib/decompress/zstd_decompress_block.c
lib/decompress/zstd_decompress.c
lib/deprecated/zbuff_common.c
lib/deprecated/zbuff_compress.c
lib/deprecated/zbuff_decompress.c
lib/dictBuilder/cover.c
lib/dictBuilder/divsufsort.c
lib/dictBuilder/fastcover.c
lib/dictBuilder/zdict.c
)
install(FILES LICENSE DESTINATION ${CMAKE_DOC_DIR}/cmzstd)
BSD License
For Zstandard software
Copyright (c) 2016-present, Facebook, Inc. All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name Facebook nor the names of its contributors may be used to
endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
<p align="center"><img src="https://raw.githubusercontent.com/facebook/zstd/dev/doc/images/zstd_logo86.png" alt="Zstandard"></p>
__Zstandard__, or `zstd` as short version, is a fast lossless compression algorithm,
targeting real-time compression scenarios at zlib-level and better compression ratios.
It's backed by a very fast entropy stage, provided by [Huff0 and FSE library](https://github.com/Cyan4973/FiniteStateEntropy).
The project is provided as an open-source dual [BSD](LICENSE) and [GPLv2](COPYING) licensed **C** library,
and a command line utility producing and decoding `.zst`, `.gz`, `.xz` and `.lz4` files.
Should your project require another programming language,
a list of known ports and bindings is provided on [Zstandard homepage](http://www.zstd.net/#other-languages).
**Development branch status:**
[![Build Status][travisDevBadge]][travisLink]
[![Build status][AppveyorDevBadge]][AppveyorLink]
[![Build status][CircleDevBadge]][CircleLink]
[travisDevBadge]: https://travis-ci.org/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
[travisLink]: https://travis-ci.org/facebook/zstd
[AppveyorDevBadge]: https://ci.appveyor.com/api/projects/status/xt38wbdxjk5mrbem/branch/dev?svg=true "Windows test suite"
[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
[CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
[CircleLink]: https://circleci.com/gh/facebook/zstd
## Benchmarks
For reference, several fast compression algorithms were tested and compared
on a server running Linux Debian (`Linux version 4.14.0-3-amd64`),
with a Core i7-6700K CPU @ 4.0GHz,
using [lzbench], an open-source in-memory benchmark by @inikep
compiled with [gcc] 7.3.0,
on the [Silesia compression corpus].
[lzbench]: https://github.com/inikep/lzbench
[Silesia compression corpus]: http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
[gcc]: https://gcc.gnu.org/
| Compressor name | Ratio | Compression| Decompress.|
| --------------- | ------| -----------| ---------- |
| **zstd 1.3.4 -1** | 2.877 | 470 MB/s | 1380 MB/s |
| zlib 1.2.11 -1 | 2.743 | 110 MB/s | 400 MB/s |
| brotli 1.0.2 -0 | 2.701 | 410 MB/s | 430 MB/s |
| quicklz 1.5.0 -1 | 2.238 | 550 MB/s | 710 MB/s |
| lzo1x 2.09 -1 | 2.108 | 650 MB/s | 830 MB/s |
| lz4 1.8.1 | 2.101 | 750 MB/s | 3700 MB/s |
| snappy 1.1.4 | 2.091 | 530 MB/s | 1800 MB/s |
| lzf 3.6 -1 | 2.077 | 400 MB/s | 860 MB/s |
[zlib]: http://www.zlib.net/
[LZ4]: http://www.lz4.org/
Zstd can also offer stronger compression ratios at the cost of compression speed.
Speed vs Compression trade-off is configurable by small increments.
Decompression speed is preserved and remains roughly the same at all settings,
a property shared by most LZ compression algorithms, such as [zlib] or lzma.
The following tests were run
on a server running Linux Debian (`Linux version 4.14.0-3-amd64`)
with a Core i7-6700K CPU @ 4.0GHz,
using [lzbench], an open-source in-memory benchmark by @inikep
compiled with [gcc] 7.3.0,
on the [Silesia compression corpus].
Compression Speed vs Ratio | Decompression Speed
---------------------------|--------------------
![Compression Speed vs Ratio](doc/images/CSpeed2.png "Compression Speed vs Ratio") | ![Decompression Speed](doc/images/DSpeed3.png "Decompression Speed")
A few other algorithms can produce higher compression ratios at slower speeds, falling outside of the graph.
For a larger picture including slow modes, [click on this link](doc/images/DCspeed5.png).
## The case for Small Data compression
Previous charts provide results applicable to typical file and stream scenarios (several MB). Small data comes with different perspectives.
The smaller the amount of data to compress, the more difficult it is to compress. This problem is common to all compression algorithms, and reason is, compression algorithms learn from past data how to compress future data. But at the beginning of a new data set, there is no "past" to build upon.
To solve this situation, Zstd offers a __training mode__, which can be used to tune the algorithm for a selected type of data.
Training Zstandard is achieved by providing it with a few samples (one file per sample). The result of this training is stored in a file called "dictionary", which must be loaded before compression and decompression.
Using this dictionary, the compression ratio achievable on small data improves dramatically.
The following example uses the `github-users` [sample set](https://github.com/facebook/zstd/releases/tag/v1.1.3), created from [github public API](https://developer.github.com/v3/users/#get-all-users).
It consists of roughly 10K records weighing about 1KB each.
Compression Ratio | Compression Speed | Decompression Speed
------------------|-------------------|--------------------
![Compression Ratio](doc/images/dict-cr.png "Compression Ratio") | ![Compression Speed](doc/images/dict-cs.png "Compression Speed") | ![Decompression Speed](doc/images/dict-ds.png "Decompression Speed")
These compression gains are achieved while simultaneously providing _faster_ compression and decompression speeds.
Training works if there is some correlation in a family of small data samples. The more data-specific a dictionary is, the more efficient it is (there is no _universal dictionary_).
Hence, deploying one dictionary per type of data will provide the greatest benefits.
Dictionary gains are mostly effective in the first few KB. Then, the compression algorithm will gradually use previously decoded content to better compress the rest of the file.
### Dictionary compression How To:
1. Create the dictionary
`zstd --train FullPathToTrainingSet/* -o dictionaryName`
2. Compress with dictionary
`zstd -D dictionaryName FILE`
3. Decompress with dictionary
`zstd -D dictionaryName --decompress FILE.zst`
## Build instructions
### Makefile
If your system is compatible with standard `make` (or `gmake`),
invoking `make` in root directory will generate `zstd` cli in root directory.
Other available options include:
- `make install` : create and install zstd cli, library and man pages
- `make check` : create and run `zstd`, tests its behavior on local platform
### cmake
A `cmake` project generator is provided within `build/cmake`.
It can generate Makefiles or other build scripts
to create `zstd` binary, and `libzstd` dynamic and static libraries.
By default, `CMAKE_BUILD_TYPE` is set to `Release`.
### Meson
A Meson project is provided within [`build/meson`](build/meson). Follow
build instructions in that directory.
You can also take a look at [`.travis.yml`](.travis.yml) file for an
example about how Meson is used to build this project.
Note that default build type is **release**.
### Visual Studio (Windows)
Going into `build` directory, you will find additional possibilities:
- Projects for Visual Studio 2005, 2008 and 2010.
+ VS2010 project is compatible with VS2012, VS2013, VS2015 and VS2017.
- Automated build scripts for Visual compiler by [@KrzysFR](https://github.com/KrzysFR), in `build/VS_scripts`,
which will build `zstd` cli and `libzstd` library without any need to open Visual Studio solution.
### Buck
You can build the zstd binary via buck by executing: `buck build programs:zstd` from the root of the repo.
The output binary will be in `buck-out/gen/programs/`.
## Status
Zstandard is currently deployed within Facebook. It is used continuously to compress large amounts of data in multiple formats and use cases.
Zstandard is considered safe for production environments.
## License
Zstandard is dual-licensed under [BSD](LICENSE) and [GPLv2](COPYING).
## Contributing
The "dev" branch is the one where all contributions are merged before reaching "master".
If you plan to propose a patch, please commit into the "dev" branch, or its own feature branch.
Direct commit to "master" are not permitted.
For more information, please read [CONTRIBUTING](CONTRIBUTING.md).
/* ******************************************************************
bitstream
Part of FSE library
Copyright (C) 2013-present, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
****************************************************************** */
#ifndef BITSTREAM_H_MODULE
#define BITSTREAM_H_MODULE
#if defined (__cplusplus)
extern "C" {
#endif
/*
* This API consists of small unitary functions, which must be inlined for best performance.
* Since link-time-optimization is not available for all compilers,
* these functions are defined into a .h to be included.
*/
/*-****************************************
* Dependencies
******************************************/
#include "mem.h" /* unaligned access routines */
#include "debug.h" /* assert(), DEBUGLOG(), RAWLOG() */
#include "error_private.h" /* error codes and messages */
/*=========================================
* Target specific
=========================================*/
#if defined(__BMI__) && defined(__GNUC__)
# include <immintrin.h> /* support for bextr (experimental) */
#endif
#define STREAM_ACCUMULATOR_MIN_32 25
#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)
********************************************/
/* bitStream can mix input from multiple sources.
* A critical property of these streams is that they encode and decode in **reverse** direction.
* So the first bit sequence you add will be the last to be read, like a LIFO stack.
*/
typedef struct {
size_t bitContainer;
unsigned bitPos;
char* startPtr;
char* ptr;
char* endPtr;
} BIT_CStream_t;
MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC);
MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
/* Start with initCStream, providing the size of buffer to write into.
* bitStream will never write outside of this buffer.
* `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
*
* bits are first added to a local register.
* Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
* Writing data into memory is an explicit operation, performed by the flushBits function.
* Hence keep track how many bits are potentially stored into local register to avoid register overflow.
* After a flushBits, a maximum of 7 bits might still be stored into local register.
*
* Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers.
*
* Last operation is to close the bitStream.
* The function returns the final size of CStream in bytes.
* If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable)
*/
/*-********************************************
* bitStream decoding API (read backward)
**********************************************/
typedef struct {
size_t bitContainer;
unsigned bitsConsumed;
const char* ptr;
const char* start;
const char* limitPtr;
} BIT_DStream_t;
typedef enum { BIT_DStream_unfinished = 0,
BIT_DStream_endOfBuffer = 1,
BIT_DStream_completed = 2,
BIT_DStream_overflow = 3 } BIT_DStream_status; /* result of BIT_reloadDStream() */
/* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
/* Start by invoking BIT_initDStream().
* A chunk of the bitStream is then stored into a local register.
* Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
* You can then retrieve bitFields stored into the local register, **in reverse order**.
* Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
* A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
* Otherwise, it can be less than that, so proceed accordingly.
* Checking if DStream has reached its end can be performed with BIT_endOfDStream().
*/
/*-****************************************
* unsafe API
******************************************/
MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
/* unsafe version; does not check buffer overflow */
MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits);
/* faster, but works only if nbBits >= 1 */
/*-**************************************************************
* Internal functions
****************************************************************/
MEM_STATIC unsigned BIT_highbit32 (U32 val)
{
assert(val != 0);
{
# if defined(_MSC_VER) /* Visual */
unsigned long r=0;
_BitScanReverse ( &r, val );
return (unsigned) r;
# elif defined(__GNUC__) && (__GNUC__ >= 3) /* Use GCC Intrinsic */
return 31 - __builtin_clz (val);
# else /* Software version */
static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29,
11, 14, 16, 18, 22, 25, 3, 30,
8, 12, 20, 28, 15, 17, 24, 7,
19, 27, 23, 6, 26, 5, 4, 31 };
U32 v = val;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
# endif
}
}
/*===== Local Constants =====*/
static const unsigned BIT_mask[] = {
0, 1, 3, 7, 0xF, 0x1F,
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF,
0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,
0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF,
0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */
#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0]))
/*-**************************************************************
* bitStream encoding
****************************************************************/
/*! BIT_initCStream() :
* `dstCapacity` must be > sizeof(size_t)
* @return : 0 if success,
* otherwise an error code (can be tested using ERR_isError()) */
MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
void* startPtr, size_t dstCapacity)
{
bitC->bitContainer = 0;
bitC->bitPos = 0;
bitC->startPtr = (char*)startPtr;
bitC->ptr = bitC->startPtr;
bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer);
if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall);
return 0;
}
/*! BIT_addBits() :
* can add up to 31 bits into `bitC`.
* Note : does not check for register overflow ! */
MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
size_t value, unsigned nbBits)