You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by om...@apache.org on 2016/08/08 21:19:21 UTC
[5/5] orc git commit: ORC-81 Add lzo and lz4 support for the C++
reader. (omalley)
ORC-81 Add lzo and lz4 support for the C++ reader. (omalley)
Fixes #47.
Signed-off-by: Owen O'Malley <om...@apache.org>
Project: http://git-wip-us.apache.org/repos/asf/orc/repo
Commit: http://git-wip-us.apache.org/repos/asf/orc/commit/9aba074b
Tree: http://git-wip-us.apache.org/repos/asf/orc/tree/9aba074b
Diff: http://git-wip-us.apache.org/repos/asf/orc/diff/9aba074b
Branch: refs/heads/master
Commit: 9aba074bb19110b9f7bbc5b2c2a18bddd9f5e840
Parents: 62fe950
Author: Owen O'Malley <om...@apache.org>
Authored: Thu Jul 7 16:44:07 2016 -0700
Committer: Owen O'Malley <om...@apache.org>
Committed: Mon Aug 8 14:18:59 2016 -0700
----------------------------------------------------------------------
CMakeLists.txt | 4 +
c++/libs/CMakeLists.txt | 1 +
c++/libs/lz4-r131/CMakeLists.txt | 23 +
c++/libs/lz4-r131/NEWS | 178 ++
c++/libs/lz4-r131/README.md | 88 +
c++/libs/lz4-r131/lib/LICENSE | 24 +
c++/libs/lz4-r131/lib/Makefile | 117 ++
c++/libs/lz4-r131/lib/README.md | 21 +
c++/libs/lz4-r131/lib/liblz4.pc.in | 14 +
c++/libs/lz4-r131/lib/lz4.c | 1516 ++++++++++++++++++
c++/libs/lz4-r131/lib/lz4.h | 360 +++++
c++/libs/lz4-r131/lib/lz4frame.c | 1479 +++++++++++++++++
c++/libs/lz4-r131/lib/lz4frame.h | 303 ++++
c++/libs/lz4-r131/lib/lz4frame_static.h | 81 +
c++/libs/lz4-r131/lib/lz4hc.c | 731 +++++++++
c++/libs/lz4-r131/lib/lz4hc.h | 189 +++
c++/libs/lz4-r131/lib/xxhash.c | 915 +++++++++++
c++/libs/lz4-r131/lib/xxhash.h | 192 +++
c++/libs/lz4-r131/lz4_Block_format.md | 127 ++
c++/libs/lz4-r131/lz4_Frame_format.md | 385 +++++
c++/src/CMakeLists.txt | 3 +
c++/src/Compression.cc | 185 ++-
c++/src/LzoDecompressor.cc | 391 +++++
c++/src/LzoDecompressor.hh | 42 +
c++/test/CMakeLists.txt | 5 +-
c++/test/TestCompression.cc | 153 +-
examples/TestVectorOrcFile.testLz4.orc | Bin 0 -> 121309 bytes
examples/TestVectorOrcFile.testLzo.orc | Bin 0 -> 121311 bytes
.../expected/TestVectorOrcFile.testLz4.jsn.gz | Bin 0 -> 197589 bytes
.../expected/TestVectorOrcFile.testLzo.jsn.gz | Bin 0 -> 197560 bytes
.../test/org/apache/orc/TestVectorOrcFile.java | 24 +-
tools/test/TestMatch.cc | 22 +
32 files changed, 7517 insertions(+), 56 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/CMakeLists.txt
----------------------------------------------------------------------
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 3c75ce0..31d0134 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -47,6 +47,10 @@ if(NOT APPLE AND NOT MSVC)
list (APPEND GMOCK_LIBRARIES pthread)
endif(NOT APPLE AND NOT MSVC)
+set (LZ4_VERSION "r131")
+set (LZ4_INCLUDE_DIRS "${CMAKE_SOURCE_DIR}/c++/libs/lz4-${LZ4_VERSION}/lib")
+set (LZ4_LIBRARIES lz4)
+
set (PROTOBUF_VERSION "2.6.0")
set (PROTOBUF_INCLUDE_DIRS
"${CMAKE_SOURCE_DIR}/c++/libs/protobuf-${PROTOBUF_VERSION}/src")
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/CMakeLists.txt
----------------------------------------------------------------------
diff --git a/c++/libs/CMakeLists.txt b/c++/libs/CMakeLists.txt
index 7d8fa22..e1eb80c 100644
--- a/c++/libs/CMakeLists.txt
+++ b/c++/libs/CMakeLists.txt
@@ -14,3 +14,4 @@ add_subdirectory(gmock-${GMOCK_VERSION})
add_subdirectory(zlib-${ZLIB_VERSION})
add_subdirectory(protobuf-${PROTOBUF_VERSION})
add_subdirectory(snappy-${SNAPPY_VERSION})
+add_subdirectory(lz4-${LZ4_VERSION})
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/CMakeLists.txt
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/CMakeLists.txt b/c++/libs/lz4-r131/CMakeLists.txt
new file mode 100644
index 0000000..832b6c3
--- /dev/null
+++ b/c++/libs/lz4-r131/CMakeLists.txt
@@ -0,0 +1,23 @@
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+cmake_minimum_required(VERSION 2.4.4)
+
+project(lz4 C)
+
+set(VERSION "r131")
+
+add_library (lz4 STATIC
+ lib/lz4.c
+ )
+
+install(TARGETS lz4 DESTINATION lib)
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/NEWS
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/NEWS b/c++/libs/lz4-r131/NEWS
new file mode 100644
index 0000000..781687d
--- /dev/null
+++ b/c++/libs/lz4-r131/NEWS
@@ -0,0 +1,178 @@
+r131
+New : Dos/DJGPP target, thanks to Louis Santillan (#114)
+Added : Example using lz4frame library, by Zbigniew J\u0119drzejewski-Szmek (#118)
+Changed: xxhash symbols are modified (namespace emulation) within liblz4
+
+r130:
+Fixed : incompatibility sparse mode vs console, reported by Yongwoon Cho (#105)
+Fixed : LZ4IO exits too early when frame crc not present, reported by Yongwoon Cho (#106)
+Fixed : incompatibility sparse mode vs append mode, reported by Takayuki Matsuoka (#110)
+Performance fix : big compression speed boost for clang (+30%)
+New : cross-version test, by Takayuki Matsuoka
+
+r129:
+Added : LZ4_compress_fast(), LZ4_compress_fast_continue()
+Added : LZ4_compress_destSize()
+Changed: New lz4 and lz4hc compression API. Previous function prototypes still supported.
+Changed: Sparse file support enabled by default
+New : LZ4 CLI improved performance compressing/decompressing multiple files (#86, kind contribution from Kyle J. Harper & Takayuki Matsuoka)
+Fixed : GCC 4.9+ optimization bug - Reported by Markus Trippelsdorf, Greg Slazinski & Evan Nemerson
+Changed: Enums converted to LZ4F_ namespace convention - by Takayuki Matsuoka
+Added : AppVeyor CI environment, for Visual tests - Suggested by Takayuki Matsuoka
+Modified:Obsolete functions generate warnings - Suggested by Evan Nemerson, contributed by Takayuki Matsuoka
+Fixed : Bug #75 (unfinished stream), reported by Yongwoon Cho
+Updated: Documentation converted to MarkDown format
+
+r128:
+New : lz4cli sparse file support (Requested by Neil Wilson, and contributed by Takayuki Matsuoka)
+New : command -m, to compress multiple files in a single command (suggested by Kyle J. Harper)
+Fixed : Restored lz4hc compression ratio (slightly lower since r124)
+New : lz4 cli supports long commands (suggested by Takayuki Matsuoka)
+New : lz4frame & lz4cli frame content size support
+New : lz4frame supports skippable frames, as requested by Sergey Cherepanov
+Changed: Default "make install" directory is /usr/local, as notified by Ron Johnson
+New : lz4 cli supports "pass-through" mode, requested by Neil Wilson
+New : datagen can generate sparse files
+New : scan-build tests, thanks to kind help by Takayuki Matsuoka
+New : g++ compatibility tests
+New : arm cross-compilation test, thanks to kind help by Takayuki Matsuoka
+Fixed : Fuzzer + frametest compatibility with NetBSD (issue #48, reported by Thomas Klausner)
+Added : Visual project directory
+Updated: Man page & Specification
+
+r127:
+N/A : added a file on SVN
+
+r126:
+New : lz4frame API is now integrated into liblz4
+Fixed : GCC 4.9 bug on highest performance settings, reported by Greg Slazinski
+Fixed : bug within LZ4 HC streaming mode, reported by James Boyle
+Fixed : older compiler don't like nameless unions, reported by Cheyi Lin
+Changed : lz4 is C90 compatible
+Changed : added -pedantic option, fixed a few mminor warnings
+
+r125:
+Changed : endian and alignment code
+Changed : directory structure : new "lib" directory
+Updated : lz4io, now uses lz4frame
+Improved: slightly improved decoding speed
+Fixed : LZ4_compress_limitedOutput(); Special thanks to Christopher Speller !
+Fixed : some alignment warnings under clang
+Fixed : deprecated function LZ4_slideInputBufferHC()
+
+r124:
+New : LZ4 HC streaming mode
+Fixed : LZ4F_compressBound() using null preferencesPtr
+Updated : xxHash to r38
+Updated library number, to 1.4.0
+
+r123:
+Added : experimental lz4frame API, thanks to Takayuki Matsuoka and Christopher Jackson for testings
+Fix : s390x support, thanks to Nobuhiro Iwamatsu
+Fix : test mode (-t) no longer requires confirmation, thanks to Thary Nguyen
+
+r122:
+Fix : AIX & AIX64 support (SamG)
+Fix : mips 64-bits support (lew van)
+Added : Examples directory, using code examples from Takayuki Matsuoka
+Updated : Framing specification, to v1.4.1
+Updated : xxHash, to r36
+
+r121:
+Added : Makefile : install for kFreeBSD and Hurd (Nobuhiro Iwamatsu)
+Fix : Makefile : install for OS-X and BSD, thanks to Takayuki Matsuoka
+
+r120:
+Modified : Streaming API, using strong types
+Added : LZ4_versionNumber(), thanks to Takayuki Matsuoka
+Fix : OS-X : library install name, thanks to Clemens Lang
+Updated : Makefile : synchronize library version number with lz4.h, thanks to Takayuki Matsuoka
+Updated : Makefile : stricter compilation flags
+Added : pkg-config, thanks to Zbigniew J\u0119drzejewski-Szmek (issue 135)
+Makefile : lz4-test only test native binaries, as suggested by Micha\u0142 G�rny (issue 136)
+Updated : xxHash to r35
+
+r119:
+Fix : Issue 134 : extended malicious address space overflow in 32-bits mode for some specific configurations
+
+r118:
+New : LZ4 Streaming API (Fast version), special thanks to Takayuki Matsuoka
+New : datagen : parametrable synthetic data generator for tests
+Improved : fuzzer, support more test cases, more parameters, ability to jump to specific test
+fix : support ppc64le platform (issue 131)
+fix : Issue 52 (malicious address space overflow in 32-bits mode when using large custom format)
+fix : Makefile : minor issue 130 : header files permissions
+
+r117:
+Added : man pages for lz4c and lz4cat
+Added : automated tests on Travis, thanks to Takayuki Matsuoka !
+fix : block-dependency command line (issue 127)
+fix : lz4fullbench (issue 128)
+
+r116:
+hotfix (issue 124 & 125)
+
+r115:
+Added : lz4cat utility, installed on POSX systems (issue 118)
+OS-X compatible compilation of dynamic library (issue 115)
+
+r114:
+Makefile : library correctly compiled with -O3 switch (issue 114)
+Makefile : library compilation compatible with clang
+Makefile : library is versioned and linked (issue 119)
+lz4.h : no more static inline prototypes (issue 116)
+man : improved header/footer (issue 111)
+Makefile : Use system default $(CC) & $(MAKE) variables (issue 112)
+xxhash : updated to r34
+
+r113:
+Large decompression speed improvement for GCC 32-bits. Thanks to Valery Croizier !
+LZ4HC : Compression Level is now a programmable parameter (CLI from 4 to 9)
+Separated IO routines from command line (lz4io.c)
+Version number into lz4.h (suggested by Francesc Alted)
+
+r112:
+quickfix
+
+r111 :
+Makefile : added capability to install libraries
+Modified Directory tree, to better separate libraries from programs.
+
+r110 :
+lz4 & lz4hc : added capability to allocate state & stream state with custom allocator (issue 99)
+fuzzer & fullbench : updated to test new functions
+man : documented -l command (Legacy format, for Linux kernel compression) (issue 102)
+cmake : improved version by Mika Attila, building programs and libraries (issue 100)
+xxHash : updated to r33
+Makefile : clean also delete local package .tar.gz
+
+r109 :
+lz4.c : corrected issue 98 (LZ4_compress_limitedOutput())
+Makefile : can specify version number from makefile
+
+r108 :
+lz4.c : corrected compression efficiency issue 97 in 64-bits chained mode (-BD) for streams > 4 GB (thanks Roman Strashkin for reporting)
+
+r107 :
+Makefile : support DESTDIR for staged installs. Thanks Jorge Aparicio.
+Makefile : make install installs both lz4 and lz4c (Jorge Aparicio)
+Makefile : removed -Wno-implicit-declaration compilation switch
+lz4cli.c : include <stduni.h> for isatty() (Luca Barbato)
+lz4.h : introduced LZ4_MAX_INPUT_SIZE constant (Shay Green)
+lz4.h : LZ4_compressBound() : unified macro and inline definitions (Shay Green)
+lz4.h : LZ4_decompressSafe_partial() : clarify comments (Shay Green)
+lz4.c : LZ4_compress() verify input size condition (Shay Green)
+bench.c : corrected a bug in free memory size evaluation
+cmake : install into bin/ directory (Richard Yao)
+cmake : check for just C compiler (Elan Ruusamae)
+
+r106 :
+Makefile : make dist modify text files in the package to respect Unix EoL convention
+lz4cli.c : corrected small display bug in HC mode
+
+r105 :
+Makefile : New install script and man page, contributed by Prasad Pandit
+lz4cli.c : Minor modifications, for easier extensibility
+COPYING : added license file
+LZ4_Streaming_Format.odt : modified file name to remove white space characters
+Makefile : .exe suffix now properly added only for Windows target
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/README.md
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/README.md b/c++/libs/lz4-r131/README.md
new file mode 100644
index 0000000..a6ba716
--- /dev/null
+++ b/c++/libs/lz4-r131/README.md
@@ -0,0 +1,88 @@
+LZ4 - Extremely fast compression
+================================
+
+LZ4 is lossless compression algorithm,
+providing compression speed at 400 MB/s per core,
+scalable with multi-cores CPU.
+It also features an extremely fast decoder,
+with speed in multiple GB/s per core,
+typically reaching RAM speed limits on multi-core systems.
+
+Speed can be tuned dynamically, selecting an "acceleration" factor
+which trades compression ratio for more speed up.
+On the other end, a high compression derivative, LZ4_HC, is also provided,
+trading CPU time for improved compression ratio.
+All versions feature the same excellent decompression speed.
+
+
+|Branch |Status |
+|------------|---------|
+|master | [![Build Status][travisMasterBadge]][travisLink] [![Build status][AppveyorMasterBadge]][AppveyorLink] [![coverity][coverBadge]][coverlink] |
+|dev | [![Build Status][travisDevBadge]][travisLink] [![Build status][AppveyorDevBadge]][AppveyorLink] |
+
+[travisMasterBadge]: https://travis-ci.org/Cyan4973/lz4.svg?branch=master "Continuous Integration test suite"
+[travisDevBadge]: https://travis-ci.org/Cyan4973/lz4.svg?branch=dev "Continuous Integration test suite"
+[travisLink]: https://ci.appveyor.com/project/YannCollet/lz4
+[AppveyorMasterBadge]: https://ci.appveyor.com/api/projects/status/v6kxv9si529477cq/branch/master?svg=true "Visual test suite"
+[AppveyorDevBadge]: https://ci.appveyor.com/api/projects/status/v6kxv9si529477cq/branch/dev?svg=true "Visual test suite"
+[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/lz4
+[coverBadge]: https://scan.coverity.com/projects/4735/badge.svg "Static code analysis of Master branch"
+[coverlink]: https://scan.coverity.com/projects/4735
+
+> **Branch Policy:**
+
+> - The "master" branch is considered stable, at all times.
+> - The "dev" branch is the one where all contributions must be merged
+ before being promoted to 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.
+
+Benchmarks
+-------------------------
+
+The benchmark uses the [Open-Source Benchmark program by m^2 (v0.14.3)]
+compiled with GCC v4.8.2 on Linux Mint 64-bits v17.
+The reference system uses a Core i5-4300U @1.9GHz.
+Benchmark evaluates the compression of reference [Silesia Corpus]
+in single-thread mode.
+
+| Compressor | Ratio | Compression | Decompression |
+| ---------- | ----- | ----------- | ------------- |
+| memcpy | 1.000 | 4200 MB/s | 4200 MB/s |
+|**LZ4 fast 17 (r129)**| 1.607 |**690 MB/s** | **2220 MB/s** |
+|**LZ4 default (r129)**|**2.101**|**385 MB/s** | **1850 MB/s** |
+| LZO 2.06 | 2.108 | 350 MB/s | 510 MB/s |
+| QuickLZ 1.5.1.b6 | 2.238 | 320 MB/s | 380 MB/s |
+| Snappy 1.1.0 | 2.091 | 250 MB/s | 960 MB/s |
+| LZF v3.6 | 2.073 | 175 MB/s | 500 MB/s |
+| zlib 1.2.8 -1 | 2.730 | 59 MB/s | 250 MB/s |
+|**LZ4 HC (r129)** |**2.720**| 22 MB/s | **1830 MB/s** |
+| zlib 1.2.8 -6 | 3.099 | 18 MB/s | 270 MB/s |
+
+
+Documentation
+-------------------------
+
+The raw LZ4 block compression format is detailed within [lz4_Block_format].
+
+To compress an arbitrarily long file or data stream, multiple blocks are required.
+Organizing these blocks and providing a common header format to handle their content
+is the purpose of the Frame format, defined into [lz4_Frame_format].
+Interoperable versions of LZ4 must respect this frame format.
+
+
+Other source versions
+-------------------------
+
+Beyond the C reference source,
+many contributors have created versions of lz4 in multiple languages
+(Java, C#, Python, Perl, Ruby, etc.).
+A list of known source ports is maintained on the [LZ4 Homepage].
+
+
+[Open-Source Benchmark program by m^2 (v0.14.3)]: http://encode.ru/threads/1371-Filesystem-benchmark?p=34029&viewfull=1#post34029
+[Silesia Corpus]: http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia
+[lz4_Block_format]: lz4_Block_format.md
+[lz4_Frame_format]: lz4_Frame_format.md
+[LZ4 Homepage]: http://www.lz4.org
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/lib/LICENSE
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/LICENSE b/c++/libs/lz4-r131/lib/LICENSE
new file mode 100644
index 0000000..b566df3
--- /dev/null
+++ b/c++/libs/lz4-r131/lib/LICENSE
@@ -0,0 +1,24 @@
+LZ4 Library
+Copyright (c) 2011-2014, Yann Collet
+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.
+
+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.
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/lib/Makefile
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/Makefile b/c++/libs/lz4-r131/lib/Makefile
new file mode 100644
index 0000000..02ddd3b
--- /dev/null
+++ b/c++/libs/lz4-r131/lib/Makefile
@@ -0,0 +1,117 @@
+# ################################################################
+# LZ4 library - Makefile
+# Copyright (C) Yann Collet 2011-2015
+# All rights reserved.
+#
+# BSD license
+# 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 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.
+#
+# You can contact the author at :
+# - LZ4 source repository : https://github.com/Cyan4973/lz4
+# - LZ4 forum froup : https://groups.google.com/forum/#!forum/lz4c
+# ################################################################
+
+# Version numbers
+VERSION ?= 129
+LIBVER_MAJOR=`sed -n '/define LZ4_VERSION_MAJOR/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < lz4.h`
+LIBVER_MINOR=`sed -n '/define LZ4_VERSION_MINOR/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < lz4.h`
+LIBVER_PATCH=`sed -n '/define LZ4_VERSION_RELEASE/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < lz4.h`
+LIBVER=$(LIBVER_MAJOR).$(LIBVER_MINOR).$(LIBVER_PATCH)
+
+DESTDIR?=
+PREFIX ?= /usr/local
+CFLAGS ?= -O3
+CFLAGS += -I. -std=c99 -Wall -Wextra -Wundef -Wshadow -Wcast-align -Wcast-qual -Wstrict-prototypes -pedantic -DXXH_NAMESPACE=LZ4_
+
+LIBDIR?= $(PREFIX)/lib
+INCLUDEDIR=$(PREFIX)/include
+
+
+# OS X linker doesn't support -soname, and use different extension
+# see : https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html
+ifeq ($(shell uname), Darwin)
+ SHARED_EXT = dylib
+ SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT)
+ SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT)
+ SONAME_FLAGS = -install_name $(PREFIX)/lib/liblz4.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER)
+else
+ SONAME_FLAGS = -Wl,-soname=liblz4.$(SHARED_EXT).$(LIBVER_MAJOR)
+ SHARED_EXT = so
+ SHARED_EXT_MAJOR = $(SHARED_EXT).$(LIBVER_MAJOR)
+ SHARED_EXT_VER = $(SHARED_EXT).$(LIBVER)
+endif
+
+default: liblz4
+
+all: liblz4
+
+liblz4: lz4.c lz4hc.c lz4frame.c xxhash.c
+ @echo compiling static library
+ @$(CC) $(CPPFLAGS) $(CFLAGS) -c $^
+ @$(AR) rcs liblz4.a lz4.o lz4hc.o lz4frame.o xxhash.o
+ @echo compiling dynamic library $(LIBVER)
+ @$(CC) $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) -shared $^ -fPIC $(SONAME_FLAGS) -o $@.$(SHARED_EXT_VER)
+ @echo creating versioned links
+ @ln -sf $@.$(SHARED_EXT_VER) $@.$(SHARED_EXT_MAJOR)
+ @ln -sf $@.$(SHARED_EXT_VER) $@.$(SHARED_EXT)
+
+clean:
+ @rm -f core *.o *.a *.$(SHARED_EXT) *.$(SHARED_EXT).* liblz4.pc
+ @echo Cleaning library completed
+
+
+#------------------------------------------------------------------------
+#make install is validated only for Linux, OSX, kFreeBSD and Hurd targets
+ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU))
+
+liblz4.pc: liblz4.pc.in Makefile
+ @echo creating pkgconfig
+ @sed -e 's|@PREFIX@|$(PREFIX)|' \
+ -e 's|@LIBDIR@|$(LIBDIR)|' \
+ -e 's|@INCLUDEDIR@|$(INCLUDEDIR)|' \
+ -e 's|@VERSION@|$(VERSION)|' \
+ $< >$@
+
+install: liblz4 liblz4.pc
+ @install -d -m 755 $(DESTDIR)$(LIBDIR)/pkgconfig/ $(DESTDIR)$(INCLUDEDIR)/
+ @install -m 755 liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_VER)
+ @cp -a liblz4.$(SHARED_EXT_MAJOR) $(DESTDIR)$(LIBDIR)
+ @cp -a liblz4.$(SHARED_EXT) $(DESTDIR)$(LIBDIR)
+ @cp -a liblz4.pc $(DESTDIR)$(LIBDIR)/pkgconfig/
+ @install -m 644 liblz4.a $(DESTDIR)$(LIBDIR)/liblz4.a
+ @install -m 644 lz4.h $(DESTDIR)$(INCLUDEDIR)/lz4.h
+ @install -m 644 lz4hc.h $(DESTDIR)$(INCLUDEDIR)/lz4hc.h
+ @install -m 644 lz4frame.h $(DESTDIR)$(INCLUDEDIR)/lz4frame.h
+ @echo lz4 static and shared library installed
+
+uninstall:
+ @rm -f $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT)
+ @rm -f $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_MAJOR)
+ @rm -f $(DESTDIR)$(LIBDIR)/pkgconfig/liblz4.pc
+ @[ -x $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_VER) ] && rm -f $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_VER)
+ @[ -f $(DESTDIR)$(LIBDIR)/liblz4.a ] && rm -f $(DESTDIR)$(LIBDIR)/liblz4.a
+ @[ -f $(DESTDIR)$(INCLUDEDIR)/lz4.h ] && rm -f $(DESTDIR)$(INCLUDEDIR)/lz4.h
+ @[ -f $(DESTDIR)$(INCLUDEDIR)/lz4hc.h ] && rm -f $(DESTDIR)$(INCLUDEDIR)/lz4hc.h
+ @[ -f $(DESTDIR)$(INCLUDEDIR)/lz4frame.h ] && rm -f $(DESTDIR)$(INCLUDEDIR)/lz4frame.h
+ @echo lz4 libraries successfully uninstalled
+
+endif
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/lib/README.md
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/README.md b/c++/libs/lz4-r131/lib/README.md
new file mode 100644
index 0000000..f6ebf5e
--- /dev/null
+++ b/c++/libs/lz4-r131/lib/README.md
@@ -0,0 +1,21 @@
+LZ4 - Library Files
+================================
+
+The __lib__ directory contains several files, but you don't necessarily need them all.
+
+To integrate fast LZ4 compression/decompression into your program, you basically just need "**lz4.c**" and "**lz4.h**".
+
+For more compression at the cost of compression speed (while preserving decompression speed), use **lz4hc** on top of regular lz4. `lz4hc` only provides compression functions. It also needs `lz4` to compile properly.
+
+If you want to produce files or data streams compatible with `lz4` command line utility, use **lz4frame**. This library encapsulates lz4-compressed blocks into the [official interoperable frame format]. In order to work properly, lz4frame needs lz4 and lz4hc, and also **xxhash**, which provides error detection algorithm.
+(_Advanced stuff_ : It's possible to hide xxhash symbols into a local namespace. This is what `liblz4` does, to avoid symbol duplication in case a user program would link to several libraries containing xxhash symbols.)
+
+A more complex "lz4frame_static.h" is also provided, although its usage is not recommended. It contains definitions which are not guaranteed to remain stable within future versions. Use for static linking ***only***.
+
+The other files are not source code. There are :
+
+ - LICENSE : contains the BSD license text
+ - Makefile : script to compile or install lz4 library (static or dynamic)
+ - liblz4.pc.in : for pkg-config (make install)
+
+[official interoperable frame format]: ../lz4_Frame_format.md
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/lib/liblz4.pc.in
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/liblz4.pc.in b/c++/libs/lz4-r131/lib/liblz4.pc.in
new file mode 100644
index 0000000..0d05152
--- /dev/null
+++ b/c++/libs/lz4-r131/lib/liblz4.pc.in
@@ -0,0 +1,14 @@
+# LZ4 - Fast LZ compression algorithm
+# Copyright (C) 2011-2014, Yann Collet.
+# BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=@INCLUDEDIR@
+
+Name: lz4
+Description: fast lossless compression algorithm library
+URL: http://code.google.com/p/lz4/
+Version: @VERSION@
+Libs: -L@LIBDIR@ -llz4
+Cflags: -I@INCLUDEDIR@
http://git-wip-us.apache.org/repos/asf/orc/blob/9aba074b/c++/libs/lz4-r131/lib/lz4.c
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/lz4.c b/c++/libs/lz4-r131/lib/lz4.c
new file mode 100644
index 0000000..08cf6b5
--- /dev/null
+++ b/c++/libs/lz4-r131/lib/lz4.c
@@ -0,0 +1,1516 @@
+/*
+ LZ4 - Fast LZ compression algorithm
+ Copyright (C) 2011-2015, 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 :
+ - LZ4 source repository : https://github.com/Cyan4973/lz4
+ - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
+*/
+
+
+/**************************************
+* Tuning parameters
+**************************************/
+/*
+ * HEAPMODE :
+ * Select how default compression functions will allocate memory for their hash table,
+ * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
+ */
+#define HEAPMODE 0
+
+/*
+ * ACCELERATION_DEFAULT :
+ * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
+ */
+#define ACCELERATION_DEFAULT 1
+
+
+/**************************************
+* CPU Feature Detection
+**************************************/
+/*
+ * LZ4_FORCE_SW_BITCOUNT
+ * Define this parameter if your target system or compiler does not support hardware bit count
+ */
+#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for Windows CE does not support Hardware bit count */
+# define LZ4_FORCE_SW_BITCOUNT
+#endif
+
+
+/**************************************
+* Includes
+**************************************/
+#include "lz4.h"
+
+
+/**************************************
+* Compiler Options
+**************************************/
+#ifdef _MSC_VER /* Visual Studio */
+# define FORCE_INLINE static __forceinline
+# include <intrin.h>
+# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
+# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */
+#else
+# if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */
+# if defined(__GNUC__) || defined(__clang__)
+# define FORCE_INLINE static inline __attribute__((always_inline))
+# else
+# define FORCE_INLINE static inline
+# endif
+# else
+# define FORCE_INLINE static
+# endif /* __STDC_VERSION__ */
+#endif /* _MSC_VER */
+
+/* LZ4_GCC_VERSION is defined into lz4.h */
+#if (LZ4_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
+# define expect(expr,value) (__builtin_expect ((expr),(value)) )
+#else
+# define expect(expr,value) (expr)
+#endif
+
+#define likely(expr) expect((expr) != 0, 1)
+#define unlikely(expr) expect((expr) != 0, 0)
+
+
+/**************************************
+* Memory routines
+**************************************/
+#include <stdlib.h> /* malloc, calloc, free */
+#define ALLOCATOR(n,s) calloc(n,s)
+#define FREEMEM free
+#include <string.h> /* memset, memcpy */
+#define MEM_INIT memset
+
+
+/**************************************
+* Basic Types
+**************************************/
+#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */
+# include <stdint.h>
+ typedef uint8_t BYTE;
+ typedef uint16_t U16;
+ typedef uint32_t U32;
+ typedef int32_t S32;
+ typedef uint64_t U64;
+#else
+ typedef unsigned char BYTE;
+ typedef unsigned short U16;
+ typedef unsigned int U32;
+ typedef signed int S32;
+ typedef unsigned long long U64;
+#endif
+
+
+/**************************************
+* Reading and writing into memory
+**************************************/
+#define STEPSIZE sizeof(size_t)
+
+static unsigned LZ4_64bits(void) { return sizeof(void*)==8; }
+
+static unsigned LZ4_isLittleEndian(void)
+{
+ const union { U32 i; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */
+ return one.c[0];
+}
+
+
+static U16 LZ4_read16(const void* memPtr)
+{
+ U16 val16;
+ memcpy(&val16, memPtr, 2);
+ return val16;
+}
+
+static U16 LZ4_readLE16(const void* memPtr)
+{
+ if (LZ4_isLittleEndian())
+ {
+ return LZ4_read16(memPtr);
+ }
+ else
+ {
+ const BYTE* p = (const BYTE*)memPtr;
+ return (U16)((U16)p[0] + (p[1]<<8));
+ }
+}
+
+static void LZ4_writeLE16(void* memPtr, U16 value)
+{
+ if (LZ4_isLittleEndian())
+ {
+ memcpy(memPtr, &value, 2);
+ }
+ else
+ {
+ BYTE* p = (BYTE*)memPtr;
+ p[0] = (BYTE) value;
+ p[1] = (BYTE)(value>>8);
+ }
+}
+
+static U32 LZ4_read32(const void* memPtr)
+{
+ U32 val32;
+ memcpy(&val32, memPtr, 4);
+ return val32;
+}
+
+static U64 LZ4_read64(const void* memPtr)
+{
+ U64 val64;
+ memcpy(&val64, memPtr, 8);
+ return val64;
+}
+
+static size_t LZ4_read_ARCH(const void* p)
+{
+ if (LZ4_64bits())
+ return (size_t)LZ4_read64(p);
+ else
+ return (size_t)LZ4_read32(p);
+}
+
+
+static void LZ4_copy4(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 4); }
+
+static void LZ4_copy8(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 8); }
+
+/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */
+static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+ BYTE* d = (BYTE*)dstPtr;
+ const BYTE* s = (const BYTE*)srcPtr;
+ BYTE* e = (BYTE*)dstEnd;
+ do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
+}
+
+
+/**************************************
+* Common Constants
+**************************************/
+#define MINMATCH 4
+
+#define COPYLENGTH 8
+#define LASTLITERALS 5
+#define MFLIMIT (COPYLENGTH+MINMATCH)
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define MAXD_LOG 16
+#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
+
+#define ML_BITS 4
+#define ML_MASK ((1U<<ML_BITS)-1)
+#define RUN_BITS (8-ML_BITS)
+#define RUN_MASK ((1U<<RUN_BITS)-1)
+
+
+/**************************************
+* Common Utils
+**************************************/
+#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */
+
+
+/**************************************
+* Common functions
+**************************************/
+static unsigned LZ4_NbCommonBytes (register size_t val)
+{
+ if (LZ4_isLittleEndian())
+ {
+ if (LZ4_64bits())
+ {
+# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ unsigned long r = 0;
+ _BitScanForward64( &r, (U64)val );
+ return (int)(r>>3);
+# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (__builtin_ctzll((U64)val) >> 3);
+# else
+ static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
+ return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+# endif
+ }
+ else /* 32 bits */
+ {
+# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ unsigned long r;
+ _BitScanForward( &r, (U32)val );
+ return (int)(r>>3);
+# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (__builtin_ctz((U32)val) >> 3);
+# else
+ static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
+ return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+# endif
+ }
+ }
+ else /* Big Endian CPU */
+ {
+ if (LZ4_64bits())
+ {
+# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ unsigned long r = 0;
+ _BitScanReverse64( &r, val );
+ return (unsigned)(r>>3);
+# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (__builtin_clzll((U64)val) >> 3);
+# else
+ unsigned r;
+ if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
+ if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+ r += (!val);
+ return r;
+# endif
+ }
+ else /* 32 bits */
+ {
+# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ unsigned long r = 0;
+ _BitScanReverse( &r, (unsigned long)val );
+ return (unsigned)(r>>3);
+# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (__builtin_clz((U32)val) >> 3);
+# else
+ unsigned r;
+ if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
+ r += (!val);
+ return r;
+# endif
+ }
+ }
+}
+
+static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
+{
+ const BYTE* const pStart = pIn;
+
+ while (likely(pIn<pInLimit-(STEPSIZE-1)))
+ {
+ size_t diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+ if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
+ pIn += LZ4_NbCommonBytes(diff);
+ return (unsigned)(pIn - pStart);
+ }
+
+ if (LZ4_64bits()) if ((pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
+ if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
+ if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
+ return (unsigned)(pIn - pStart);
+}
+
+
+#ifndef LZ4_COMMONDEFS_ONLY
+/**************************************
+* Local Constants
+**************************************/
+#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
+#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */
+
+static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
+static const U32 LZ4_skipTrigger = 6; /* Increase this value ==> compression run slower on incompressible data */
+
+
+/**************************************
+* Local Structures and types
+**************************************/
+typedef struct {
+ U32 hashTable[HASH_SIZE_U32];
+ U32 currentOffset;
+ U32 initCheck;
+ const BYTE* dictionary;
+ BYTE* bufferStart; /* obsolete, used for slideInputBuffer */
+ U32 dictSize;
+} LZ4_stream_t_internal;
+
+typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
+
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+
+
+/**************************************
+* Local Utils
+**************************************/
+int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
+int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); }
+int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
+
+
+
+/********************************
+* Compression functions
+********************************/
+
+static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType)
+{
+ if (tableType == byU16)
+ return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
+ else
+ return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
+}
+
+static const U64 prime5bytes = 889523592379ULL;
+static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType)
+{
+ const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
+ const U32 hashMask = (1<<hashLog) - 1;
+ return ((sequence * prime5bytes) >> (40 - hashLog)) & hashMask;
+}
+
+static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType)
+{
+ if (LZ4_64bits())
+ return LZ4_hashSequence64(sequence, tableType);
+ return LZ4_hashSequence((U32)sequence, tableType);
+}
+
+static U32 LZ4_hashPosition(const void* p, tableType_t tableType) { return LZ4_hashSequenceT(LZ4_read_ARCH(p), tableType); }
+
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
+{
+ switch (tableType)
+ {
+ case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
+ case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
+ case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
+ }
+}
+
+static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ U32 h = LZ4_hashPosition(p, tableType);
+ LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
+}
+
+static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
+ if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
+ { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */
+}
+
+static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ U32 h = LZ4_hashPosition(p, tableType);
+ return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
+}
+
+FORCE_INLINE int LZ4_compress_generic(
+ void* const ctx,
+ const char* const source,
+ char* const dest,
+ const int inputSize,
+ const int maxOutputSize,
+ const limitedOutput_directive outputLimited,
+ const tableType_t tableType,
+ const dict_directive dict,
+ const dictIssue_directive dictIssue,
+ const U32 acceleration)
+{
+ LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx;
+
+ const BYTE* ip = (const BYTE*) source;
+ const BYTE* base;
+ const BYTE* lowLimit;
+ const BYTE* const lowRefLimit = ip - dictPtr->dictSize;
+ const BYTE* const dictionary = dictPtr->dictionary;
+ const BYTE* const dictEnd = dictionary + dictPtr->dictSize;
+ const size_t dictDelta = dictEnd - (const BYTE*)source;
+ const BYTE* anchor = (const BYTE*) source;
+ const BYTE* const iend = ip + inputSize;
+ const BYTE* const mflimit = iend - MFLIMIT;
+ const BYTE* const matchlimit = iend - LASTLITERALS;
+
+ BYTE* op = (BYTE*) dest;
+ BYTE* const olimit = op + maxOutputSize;
+
+ U32 forwardH;
+ size_t refDelta=0;
+
+ /* Init conditions */
+ if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */
+ switch(dict)
+ {
+ case noDict:
+ default:
+ base = (const BYTE*)source;
+ lowLimit = (const BYTE*)source;
+ break;
+ case withPrefix64k:
+ base = (const BYTE*)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE*)source - dictPtr->dictSize;
+ break;
+ case usingExtDict:
+ base = (const BYTE*)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE*)source;
+ break;
+ }
+ if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */
+ if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */
+
+ /* First Byte */
+ LZ4_putPosition(ip, ctx, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+ /* Main Loop */
+ for ( ; ; )
+ {
+ const BYTE* match;
+ BYTE* token;
+ {
+ const BYTE* forwardIp = ip;
+ unsigned step = 1;
+ unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+
+ /* Find a match */
+ do {
+ U32 h = forwardH;
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+ if (unlikely(forwardIp > mflimit)) goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h, ctx, tableType, base);
+ if (dict==usingExtDict)
+ {
+ if (match<(const BYTE*)source)
+ {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ }
+ else
+ {
+ refDelta = 0;
+ lowLimit = (const BYTE*)source;
+ }
+ }
+ forwardH = LZ4_hashPosition(forwardIp, tableType);
+ LZ4_putPositionOnHash(ip, h, ctx, tableType, base);
+
+ } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
+ || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+ }
+
+ /* Catch up */
+ while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+
+ {
+ /* Encode Literal length */
+ unsigned litLength = (unsigned)(ip - anchor);
+ token = op++;
+ if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
+ return 0; /* Check output limit */
+ if (litLength>=RUN_MASK)
+ {
+ int len = (int)litLength-RUN_MASK;
+ *token=(RUN_MASK<<ML_BITS);
+ for(; len >= 255 ; len-=255) *op++ = 255;
+ *op++ = (BYTE)len;
+ }
+ else *token = (BYTE)(litLength<<ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op+litLength);
+ op+=litLength;
+ }
+
+_next_match:
+ /* Encode Offset */
+ LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+
+ /* Encode MatchLength */
+ {
+ unsigned matchLength;
+
+ if ((dict==usingExtDict) && (lowLimit==dictionary))
+ {
+ const BYTE* limit;
+ match += refDelta;
+ limit = ip + (dictEnd-match);
+ if (limit > matchlimit) limit = matchlimit;
+ matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
+ ip += MINMATCH + matchLength;
+ if (ip==limit)
+ {
+ unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+ matchLength += more;
+ ip += more;
+ }
+ }
+ else
+ {
+ matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+ ip += MINMATCH + matchLength;
+ }
+
+ if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit)))
+ return 0; /* Check output limit */
+ if (matchLength>=ML_MASK)
+ {
+ *token += ML_MASK;
+ matchLength -= ML_MASK;
+ for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; }
+ if (matchLength >= 255) { matchLength-=255; *op++ = 255; }
+ *op++ = (BYTE)matchLength;
+ }
+ else *token += (BYTE)(matchLength);
+ }
+
+ anchor = ip;
+
+ /* Test end of chunk */
+ if (ip > mflimit) break;
+
+ /* Fill table */
+ LZ4_putPosition(ip-2, ctx, tableType, base);
+
+ /* Test next position */
+ match = LZ4_getPosition(ip, ctx, tableType, base);
+ if (dict==usingExtDict)
+ {
+ if (match<(const BYTE*)source)
+ {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ }
+ else
+ {
+ refDelta = 0;
+ lowLimit = (const BYTE*)source;
+ }
+ }
+ LZ4_putPosition(ip, ctx, tableType, base);
+ if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
+ && (match+MAX_DISTANCE>=ip)
+ && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
+ { token=op++; *token=0; goto _next_match; }
+
+ /* Prepare next loop */
+ forwardH = LZ4_hashPosition(++ip, tableType);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ {
+ const size_t lastRun = (size_t)(iend - anchor);
+ if ((outputLimited) && ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize))
+ return 0; /* Check output limit */
+ if (lastRun >= RUN_MASK)
+ {
+ size_t accumulator = lastRun - RUN_MASK;
+ *op++ = RUN_MASK << ML_BITS;
+ for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ }
+ else
+ {
+ *op++ = (BYTE)(lastRun<<ML_BITS);
+ }
+ memcpy(op, anchor, lastRun);
+ op += lastRun;
+ }
+
+ /* End */
+ return (int) (((char*)op)-dest);
+}
+
+
+int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+ LZ4_resetStream((LZ4_stream_t*)state);
+ if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+
+ if (maxOutputSize >= LZ4_compressBound(inputSize))
+ {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+ }
+ else
+ {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+ }
+}
+
+
+int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+#if (HEAPMODE)
+ void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+#else
+ LZ4_stream_t ctx;
+ void* ctxPtr = &ctx;
+#endif
+
+ int result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
+
+#if (HEAPMODE)
+ FREEMEM(ctxPtr);
+#endif
+ return result;
+}
+
+
+int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+ return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
+}
+
+
+/* hidden debug function */
+/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
+int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+ LZ4_stream_t ctx;
+
+ LZ4_resetStream(&ctx);
+
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+}
+
+
+/********************************
+* destSize variant
+********************************/
+
+static int LZ4_compress_destSize_generic(
+ void* const ctx,
+ const char* const src,
+ char* const dst,
+ int* const srcSizePtr,
+ const int targetDstSize,
+ const tableType_t tableType)
+{
+ const BYTE* ip = (const BYTE*) src;
+ const BYTE* base = (const BYTE*) src;
+ const BYTE* lowLimit = (const BYTE*) src;
+ const BYTE* anchor = ip;
+ const BYTE* const iend = ip + *srcSizePtr;
+ const BYTE* const mflimit = iend - MFLIMIT;
+ const BYTE* const matchlimit = iend - LASTLITERALS;
+
+ BYTE* op = (BYTE*) dst;
+ BYTE* const oend = op + targetDstSize;
+ BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
+ BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
+ BYTE* const oMaxSeq = oMaxLit - 1 /* token */;
+
+ U32 forwardH;
+
+
+ /* Init conditions */
+ if (targetDstSize < 1) return 0; /* Impossible to store anything */
+ if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */
+ if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */
+ if (*srcSizePtr<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */
+
+ /* First Byte */
+ *srcSizePtr = 0;
+ LZ4_putPosition(ip, ctx, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+ /* Main Loop */
+ for ( ; ; )
+ {
+ const BYTE* match;
+ BYTE* token;
+ {
+ const BYTE* forwardIp = ip;
+ unsigned step = 1;
+ unsigned searchMatchNb = 1 << LZ4_skipTrigger;
+
+ /* Find a match */
+ do {
+ U32 h = forwardH;
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+ if (unlikely(forwardIp > mflimit))
+ goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h, ctx, tableType, base);
+ forwardH = LZ4_hashPosition(forwardIp, tableType);
+ LZ4_putPositionOnHash(ip, h, ctx, tableType, base);
+
+ } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match) != LZ4_read32(ip)) );
+ }
+
+ /* Catch up */
+ while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
+
+ {
+ /* Encode Literal length */
+ unsigned litLength = (unsigned)(ip - anchor);
+ token = op++;
+ if (op + ((litLength+240)/255) + litLength > oMaxLit)
+ {
+ /* Not enough space for a last match */
+ op--;
+ goto _last_literals;
+ }
+ if (litLength>=RUN_MASK)
+ {
+ unsigned len = litLength - RUN_MASK;
+ *token=(RUN_MASK<<ML_BITS);
+ for(; len >= 255 ; len-=255) *op++ = 255;
+ *op++ = (BYTE)len;
+ }
+ else *token = (BYTE)(litLength<<ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op+litLength);
+ op += litLength;
+ }
+
+_next_match:
+ /* Encode Offset */
+ LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+
+ /* Encode MatchLength */
+ {
+ size_t matchLength;
+
+ matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+
+ if (op + ((matchLength+240)/255) > oMaxMatch)
+ {
+ /* Match description too long : reduce it */
+ matchLength = (15-1) + (oMaxMatch-op) * 255;
+ }
+ //printf("offset %5i, matchLength%5i \n", (int)(ip-match), matchLength + MINMATCH);
+ ip += MINMATCH + matchLength;
+
+ if (matchLength>=ML_MASK)
+ {
+ *token += ML_MASK;
+ matchLength -= ML_MASK;
+ while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
+ *op++ = (BYTE)matchLength;
+ }
+ else *token += (BYTE)(matchLength);
+ }
+
+ anchor = ip;
+
+ /* Test end of block */
+ if (ip > mflimit) break;
+ if (op > oMaxSeq) break;
+
+ /* Fill table */
+ LZ4_putPosition(ip-2, ctx, tableType, base);
+
+ /* Test next position */
+ match = LZ4_getPosition(ip, ctx, tableType, base);
+ LZ4_putPosition(ip, ctx, tableType, base);
+ if ( (match+MAX_DISTANCE>=ip)
+ && (LZ4_read32(match)==LZ4_read32(ip)) )
+ { token=op++; *token=0; goto _next_match; }
+
+ /* Prepare next loop */
+ forwardH = LZ4_hashPosition(++ip, tableType);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ {
+ size_t lastRunSize = (size_t)(iend - anchor);
+ if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend)
+ {
+ /* adapt lastRunSize to fill 'dst' */
+ lastRunSize = (oend-op) - 1;
+ lastRunSize -= (lastRunSize+240)/255;
+ }
+ ip = anchor + lastRunSize;
+
+ if (lastRunSize >= RUN_MASK)
+ {
+ size_t accumulator = lastRunSize - RUN_MASK;
+ *op++ = RUN_MASK << ML_BITS;
+ for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ }
+ else
+ {
+ *op++ = (BYTE)(lastRunSize<<ML_BITS);
+ }
+ memcpy(op, anchor, lastRunSize);
+ op += lastRunSize;
+ }
+
+ /* End */
+ *srcSizePtr = (int) (((const char*)ip)-src);
+ return (int) (((char*)op)-dst);
+}
+
+
+static int LZ4_compress_destSize_extState (void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+{
+ LZ4_resetStream((LZ4_stream_t*)state);
+
+ if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) /* compression success is guaranteed */
+ {
+ return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
+ }
+ else
+ {
+ if (*srcSizePtr < LZ4_64Klimit)
+ return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, byU16);
+ else
+ return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr);
+ }
+}
+
+
+int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+{
+#if (HEAPMODE)
+ void* ctx = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+#else
+ LZ4_stream_t ctxBody;
+ void* ctx = &ctxBody;
+#endif
+
+ int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);
+
+#if (HEAPMODE)
+ FREEMEM(ctx);
+#endif
+ return result;
+}
+
+
+
+/********************************
+* Streaming functions
+********************************/
+
+LZ4_stream_t* LZ4_createStream(void)
+{
+ LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+ LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */
+ LZ4_resetStream(lz4s);
+ return lz4s;
+}
+
+void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
+{
+ MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
+int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
+{
+ FREEMEM(LZ4_stream);
+ return (0);
+}
+
+
+#define HASH_UNIT sizeof(size_t)
+int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
+{
+ LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
+ const BYTE* p = (const BYTE*)dictionary;
+ const BYTE* const dictEnd = p + dictSize;
+ const BYTE* base;
+
+ if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */
+ LZ4_resetStream(LZ4_dict);
+
+ if (dictSize < (int)HASH_UNIT)
+ {
+ dict->dictionary = NULL;
+ dict->dictSize = 0;
+ return 0;
+ }
+
+ if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
+ dict->currentOffset += 64 KB;
+ base = p - dict->currentOffset;
+ dict->dictionary = p;
+ dict->dictSize = (U32)(dictEnd - p);
+ dict->currentOffset += dict->dictSize;
+
+ while (p <= dictEnd-HASH_UNIT)
+ {
+ LZ4_putPosition(p, dict->hashTable, byU32, base);
+ p+=3;
+ }
+
+ return dict->dictSize;
+}
+
+
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+{
+ if ((LZ4_dict->currentOffset > 0x80000000) ||
+ ((size_t)LZ4_dict->currentOffset > (size_t)src)) /* address space overflow */
+ {
+ /* rescale hash table */
+ U32 delta = LZ4_dict->currentOffset - 64 KB;
+ const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
+ int i;
+ for (i=0; i<HASH_SIZE_U32; i++)
+ {
+ if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
+ else LZ4_dict->hashTable[i] -= delta;
+ }
+ LZ4_dict->currentOffset = 64 KB;
+ if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
+ LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
+ }
+}
+
+
+int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+ LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream;
+ const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+ const BYTE* smallest = (const BYTE*) source;
+ if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */
+ if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
+ LZ4_renormDictT(streamPtr, smallest);
+ if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+
+ /* Check overlapping input/dictionary space */
+ {
+ const BYTE* sourceEnd = (const BYTE*) source + inputSize;
+ if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd))
+ {
+ streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
+ if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
+ if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
+ streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+ }
+ }
+
+ /* prefix mode : source data follows dictionary */
+ if (dictEnd == (const BYTE*)source)
+ {
+ int result;
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
+ else
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
+ streamPtr->dictSize += (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+
+ /* external dictionary mode */
+ {
+ int result;
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
+ else
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
+ streamPtr->dictionary = (const BYTE*)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+}
+
+
+/* Hidden debug function, to force external dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+{
+ LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict;
+ int result;
+ const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+ const BYTE* smallest = dictEnd;
+ if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
+ LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest);
+
+ result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+
+ streamPtr->dictionary = (const BYTE*)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+
+ return result;
+}
+
+
+int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
+{
+ LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
+ const BYTE* previousDictEnd = dict->dictionary + dict->dictSize;
+
+ if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */
+ if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;
+
+ memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+
+ dict->dictionary = (const BYTE*)safeBuffer;
+ dict->dictSize = (U32)dictSize;
+
+ return dictSize;
+}
+
+
+
+/*******************************
+* Decompression functions
+*******************************/
+/*
+ * This generic decompression function cover all use cases.
+ * It shall be instantiated several times, using different sets of directives
+ * Note that it is essential this generic function is really inlined,
+ * in order to remove useless branches during compilation optimization.
+ */
+FORCE_INLINE int LZ4_decompress_generic(
+ const char* const source,
+ char* const dest,
+ int inputSize,
+ int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
+
+ int endOnInput, /* endOnOutputSize, endOnInputSize */
+ int partialDecoding, /* full, partial */
+ int targetOutputSize, /* only used if partialDecoding==partial */
+ int dict, /* noDict, withPrefix64k, usingExtDict */
+ const BYTE* const lowPrefix, /* == dest if dict == noDict */
+ const BYTE* const dictStart, /* only if dict==usingExtDict */
+ const size_t dictSize /* note : = 0 if noDict */
+ )
+{
+ /* Local Variables */
+ const BYTE* ip = (const BYTE*) source;
+ const BYTE* const iend = ip + inputSize;
+
+ BYTE* op = (BYTE*) dest;
+ BYTE* const oend = op + outputSize;
+ BYTE* cpy;
+ BYTE* oexit = op + targetOutputSize;
+ const BYTE* const lowLimit = lowPrefix - dictSize;
+
+ const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
+ const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4};
+ const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};
+
+ const int safeDecode = (endOnInput==endOnInputSize);
+ const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
+
+
+ /* Special cases */
+ if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */
+ if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */
+ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
+
+
+ /* Main Loop */
+ while (1)
+ {
+ unsigned token;
+ size_t length;
+ const BYTE* match;
+
+ /* get literal length */
+ token = *ip++;
+ if ((length=(token>>ML_BITS)) == RUN_MASK)
+ {
+ unsigned s;
+ do
+ {
+ s = *ip++;
+ length += s;
+ }
+ while (likely((endOnInput)?ip<iend-RUN_MASK:1) && (s==255));
+ if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error; /* overflow detection */
+ if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error; /* overflow detection */
+ }
+
+ /* copy literals */
+ cpy = op+length;
+ if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
+ || ((!endOnInput) && (cpy>oend-COPYLENGTH)))
+ {
+ if (partialDecoding)
+ {
+ if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */
+ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */
+ }
+ else
+ {
+ if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */
+ if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */
+ }
+ memcpy(op, ip, length);
+ ip += length;
+ op += length;
+ break; /* Necessarily EOF, due to parsing restrictions */
+ }
+ LZ4_wildCopy(op, ip, cpy);
+ ip += length; op = cpy;
+
+ /* get offset */
+ match = cpy - LZ4_readLE16(ip); ip+=2;
+ if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside destination buffer */
+
+ /* get matchlength */
+ length = token & ML_MASK;
+ if (length == ML_MASK)
+ {
+ unsigned s;
+ do
+ {
+ if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
+ s = *ip++;
+ length += s;
+ } while (s==255);
+ if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */
+ }
+ length += MINMATCH;
+
+ /* check external dictionary */
+ if ((dict==usingExtDict) && (match < lowPrefix))
+ {
+ if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */
+
+ if (length <= (size_t)(lowPrefix-match))
+ {
+ /* match can be copied as a single segment from external dictionary */
+ match = dictEnd - (lowPrefix-match);
+ memmove(op, match, length); op += length;
+ }
+ else
+ {
+ /* match encompass external dictionary and current segment */
+ size_t copySize = (size_t)(lowPrefix-match);
+ memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+ copySize = length - copySize;
+ if (copySize > (size_t)(op-lowPrefix)) /* overlap within current segment */
+ {
+ BYTE* const endOfMatch = op + copySize;
+ const BYTE* copyFrom = lowPrefix;
+ while (op < endOfMatch) *op++ = *copyFrom++;
+ }
+ else
+ {
+ memcpy(op, lowPrefix, copySize);
+ op += copySize;
+ }
+ }
+ continue;
+ }
+
+ /* copy repeated sequence */
+ cpy = op + length;
+ if (unlikely((op-match)<8))
+ {
+ const size_t dec64 = dec64table[op-match];
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += dec32table[op-match];
+ LZ4_copy4(op+4, match);
+ op += 8; match -= dec64;
+ } else { LZ4_copy8(op, match); op+=8; match+=8; }
+
+ if (unlikely(cpy>oend-12))
+ {
+ if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals */
+ if (op < oend-8)
+ {
+ LZ4_wildCopy(op, match, oend-8);
+ match += (oend-8) - op;
+ op = oend-8;
+ }
+ while (op<cpy) *op++ = *match++;
+ }
+ else
+ LZ4_wildCopy(op, match, cpy);
+ op=cpy; /* correction */
+ }
+
+ /* end of decoding */
+ if (endOnInput)
+ return (int) (((char*)op)-dest); /* Nb of output bytes decoded */
+ else
+ return (int) (((const char*)ip)-source); /* Nb of input bytes read */
+
+ /* Overflow error detected */
+_output_error:
+ return (int) (-(((const char*)ip)-source))-1;
+}
+
+
+int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
+}
+
+int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
+}
+
+int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
+}
+
+
+/* streaming decompression functions */
+
+typedef struct
+{
+ const BYTE* externalDict;
+ size_t extDictSize;
+ const BYTE* prefixEnd;
+ size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+/*
+ * If you prefer dynamic allocation methods,
+ * LZ4_createStreamDecode()
+ * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure.
+ */
+LZ4_streamDecode_t* LZ4_createStreamDecode(void)
+{
+ LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
+ return lz4s;
+}
+
+int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
+{
+ FREEMEM(LZ4_stream);
+ return 0;
+}
+
+/*
+ * LZ4_setStreamDecode
+ * Use this function to instruct where to find the dictionary
+ * This function is not necessary if previous data is still available where it was decoded.
+ * Loading a size of 0 is allowed (same effect as no dictionary).
+ * Return : 1 if OK, 0 if error
+ */
+int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ lz4sd->prefixSize = (size_t) dictSize;
+ lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+ lz4sd->externalDict = NULL;
+ lz4sd->extDictSize = 0;
+ return 1;
+}
+
+/*
+*_continue() :
+ These decoding functions allow decompression of multiple blocks in "streaming" mode.
+ Previously decoded blocks must still be available at the memory position where they were decoded.
+ If it's not possible, save the relevant part of decoded data into a safe buffer,
+ and indicate where it stands using LZ4_setStreamDecode()
+*/
+int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ int result;
+
+ if (lz4sd->prefixEnd == (BYTE*)dest)
+ {
+ result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, full, 0,
+ usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize += result;
+ lz4sd->prefixEnd += result;
+ }
+ else
+ {
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+ result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, full, 0,
+ usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize = result;
+ lz4sd->prefixEnd = (BYTE*)dest + result;
+ }
+
+ return result;
+}
+
+int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ int result;
+
+ if (lz4sd->prefixEnd == (BYTE*)dest)
+ {
+ result = LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, full, 0,
+ usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize += originalSize;
+ lz4sd->prefixEnd += originalSize;
+ }
+ else
+ {
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize;
+ result = LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, full, 0,
+ usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize = originalSize;
+ lz4sd->prefixEnd = (BYTE*)dest + originalSize;
+ }
+
+ return result;
+}
+
+
+/*
+Advanced decoding functions :
+*_usingDict() :
+ These decoding functions work the same as "_continue" ones,
+ the dictionary must be explicitly provided within parameters
+*/
+
+FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
+{
+ if (dictSize==0)
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
+ if (dictStart+dictSize == dest)
+ {
+ if (dictSize >= (int)(64 KB - 1))
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
+ }
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
+{
+ return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
+}
+
+int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
+{
+ return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
+}
+
+/* debug function */
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+
+/***************************************************
+* Obsolete Functions
+***************************************************/
+/* obsolete compression functions */
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
+int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
+int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
+int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }
+
+/*
+These function names are deprecated and should no longer be used.
+They are only provided here for compatibility with older user programs.
+- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
+- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
+*/
+int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
+int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
+
+
+/* Obsolete Streaming functions */
+
+int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
+
+static void LZ4_init(LZ4_stream_t_internal* lz4ds, BYTE* base)
+{
+ MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE);
+ lz4ds->bufferStart = base;
+}
+
+int LZ4_resetStreamState(void* state, char* inputBuffer)
+{
+ if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */
+ LZ4_init((LZ4_stream_t_internal*)state, (BYTE*)inputBuffer);
+ return 0;
+}
+
+void* LZ4_create (char* inputBuffer)
+{
+ void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+ LZ4_init ((LZ4_stream_t_internal*)lz4ds, (BYTE*)inputBuffer);
+ return lz4ds;
+}
+
+char* LZ4_slideInputBuffer (void* LZ4_Data)
+{
+ LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data;
+ int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB);
+ return (char*)(ctx->bufferStart + dictSize);
+}
+
+/* Obsolete streaming decompression functions */
+
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+}
+
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+}
+
+#endif /* LZ4_COMMONDEFS_ONLY */
+