Training in progress, epoch 0

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 wandb/run-20220127_103723-scy0vyln/run-scy0vyln.wandb filter=lfs diff=lfs merge=lfs -text
+text.txt filter=lfs diff=lfs merge=lfs -text

checkpoint-96/config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "KBLab/wav2vec2-large-voxrex",
+  "activation_dropout": 0.15,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.75,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 31,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 34,
+  "xvector_output_dim": 512
+}

checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55e930ed4249341e99a4c46286f740db87be4e84bd738a4c4ef34f432eeabf6
+size 2490337361

checkpoint-96/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-96/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3d7adc84f99873379ee01a5b7bece995841b13eb00f32cc9e0820a51bff003
+size 1262063089

checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3954dc971c4bbccd0f85caf4847af99e2e7855f973ba533949cc40f358a7ad26
+size 14631

checkpoint-96/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85781709d7068a117043a04686e2279506d06f7c98e4956a70cb9d522e7edbb7
+size 559

checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5d8befbb39b76a1e9e1dec9fe376e2b4c979f54b3926eba16675473b185bfc
+size 623

checkpoint-96/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9974025974025974,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 18.22025489807129,
+      "eval_runtime": 188.3513,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 0.839,
+      "eval_wer": 1.0021133629565406,
+      "step": 96
+    }
+  ],
+  "max_steps": 19200,
+  "num_train_epochs": 200,
+  "total_flos": 1.4911839837896755e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36b0de66081b1e60759283ec925cb14218ac8e4b7758178a38fee27a8df110c
+size 3055

config.json

@@ -1,6 +1,6 @@
 {
   "_name_or_path": "KBLab/wav2vec2-large-voxrex",
-  "activation_dropout": 0.1,
+  "activation_dropout": 0.15,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,

kenlm/.github/workflows/mac.yml

@@ -0,0 +1,30 @@
+name: Mac
+
+on:
+  push:
+    branches: master
+  pull_request:
+    branches: master
+
+jobs:
+  build:
+    runs-on: macOS-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Install Boost
+      run: |
+        brew install boost
+        brew install libomp
+        brew install eigen
+    - name: cmake
+      run: |
+        cmake -E make_directory build
+        cd build
+        cmake ..
+    - name: Compile
+      working-directory: build
+      run: cmake --build . -j2
+    - name: Test
+      working-directory: build
+      run: ctest -j2

kenlm/.github/workflows/ubuntu.yml

@@ -0,0 +1,27 @@
+name: Ubuntu
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: dependencies
+      run: sudo apt-get install -y build-essential libboost-all-dev cmake zlib1g-dev libbz2-dev liblzma-dev
+    - name: cmake
+      run: |
+        cmake -E make_directory build
+        cd build
+        cmake -DCOMPILE_TESTS=ON ..
+    - name: Compile
+      working-directory: build
+      run: cmake --build . -j2
+    - name: Test
+      working-directory: build
+      run: ctest -j2

kenlm/.github/workflows/windows.yml

@@ -0,0 +1,25 @@
+name: Windows
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: windows-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: cmake
+      run: |
+        cmake -E make_directory build
+        cd build
+        cmake -DBOOST_ROOT="${env:BOOST_ROOT_1_72_0}" ..
+    - name: Compile
+      working-directory: build
+      run: cmake --build . -j2
+    - name: Test
+      working-directory: build
+      run: ctest -j2

kenlm/.gitignore

@@ -0,0 +1,21 @@
+util/file_piece.cc.gz
+*.swp
+*.o
+doc/
+build/
+/bin
+/lib
+/tests
+._*
+windows/Win32
+windows/x64
+windows/*.user
+windows/*.sdf
+windows/*.opensdf
+windows/*.suo
+CMakeFiles
+cmake_install.cmake
+CMakeCache.txt
+CTestTestfile.cmake
+DartConfiguration.tcl
+Makefile

kenlm/BUILDING

@@ -0,0 +1,21 @@
+KenLM has switched to cmake
+  cmake .
+  make -j 4
+But they recommend building out of tree
+  mkdir -p build && cd build
+  cmake ..
+  make -j 4
+
+If you only want the query code and do not care about compression (.gz, .bz2, and .xz):
+  ./compile_query_only.sh
+
+Windows:
+  The windows directory has visual studio files.  Note that you need to compile
+  the kenlm project before build_binary and ngram_query projects.  
+
+OSX:
+  Missing dependencies can be remedied with brew.
+  brew install cmake boost eigen
+
+Debian/Ubuntu:
+  sudo apt install build-essential cmake libboost-system-dev libboost-thread-dev libboost-program-options-dev libboost-test-dev libeigen3-dev zlib1g-dev libbz2-dev liblzma-dev

kenlm/CMakeLists.txt

@@ -0,0 +1,131 @@
+cmake_minimum_required(VERSION 3.1)
+
+if (WIN32)
+    set(Boost_USE_STATIC_LIBS OFF)
+    # The auto-linking feature has problems with USE_STATIC_LIBS off, so we use
+    # BOOST_ALL_NO_LIB to turn it off.
+    # Several boost libraries headers aren't configured correctly if
+    # USE_STATIC_LIBS is off, so we explicitly say they are dynamic with the
+    # remaining definitions.
+    add_definitions(-DBOOST_ALL_NO_LIB -DBOOST_PROGRAM_OPTIONS_DYN_LINK -DBOOST_IOSTREAMS_DYN_LINK -DBOOST_THREAD_DYN_LINK)
+endif( )
+
+# Define a single cmake project
+project(kenlm)
+
+option(FORCE_STATIC "Build static executables" OFF)
+option(COMPILE_TESTS "Compile tests" OFF)
+option(ENABLE_PYTHON "Build Python bindings" OFF)
+# Eigen3 less than 3.1.0 has a race condition: http://eigen.tuxfamily.org/bz/show_bug.cgi?id=466
+find_package(Eigen3 3.1.0 CONFIG)
+include(CMakeDependentOption)
+cmake_dependent_option(ENABLE_INTERPOLATE "Build interpolation program (depends on Eigen3)" ON "EIGEN3_FOUND AND NOT WIN32" OFF)
+
+if (FORCE_STATIC)
+  #presumably overkill, is there a better way?
+  #http://cmake.3232098.n2.nabble.com/Howto-compile-static-executable-td5580269.html
+  set(Boost_USE_STATIC_LIBS ON)
+  set_property(GLOBAL PROPERTY LINK_SEARCH_START_STATIC ON)
+  set_property(GLOBAL PROPERTY LINK_SEARCH_END_STATIC ON)
+  set(BUILD_SHARED_LIBRARIES OFF)
+  if (MSVC)
+	set(flag_vars
+	  CMAKE_CXX_FLAGS CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE
+	  CMAKE_CXX_FLAGS_MINSIZEREL CMAKE_CXX_FLAGS_RELWITHDEBINFO
+	  CMAKE_C_FLAGS CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE
+	  CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO)
+	  foreach(flag_var ${flag_vars})
+	    if(${flag_var} MATCHES "/MD")
+	      string(REGEX REPLACE "/MD" "/MT" ${flag_var} "${${flag_var}}")
+	    endif(${flag_var} MATCHES "/MD")
+	  endforeach(flag_var)
+  else (MSVC)
+    if (NOT CMAKE_C_COMPILER_ID MATCHES ".*Clang")
+      set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libgcc -static-libstdc++ -static")
+    endif ()
+  set(CMAKE_FIND_LIBRARY_SUFFIXES ".a")
+  endif ()
+  #Annoyingly the exectuables say "File not found" unless these are set
+  set(CMAKE_EXE_LINK_DYNAMIC_C_FLAGS)
+  set(CMAKE_EXE_LINK_DYNAMIC_CXX_FLAGS)
+  set(CMAKE_SHARED_LIBRARY_C_FLAGS)
+  set(CMAKE_SHARED_LIBRARY_CXX_FLAGS)
+  set(CMAKE_SHARED_LIBRARY_LINK_C_FLAGS)
+  set(CMAKE_SHARED_LIBRARY_LINK_CXX_FLAGS)
+endif ()
+
+# Compile all executables into bin/
+set(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR}/bin)
+
+# Compile all libraries into lib/
+set(LIBRARY_OUTPUT_PATH ${PROJECT_BINARY_DIR}/lib)
+
+if (NOT CMAKE_BUILD_TYPE)
+  set(CMAKE_BUILD_TYPE Release)
+endif()
+
+if (COMPILE_TESTS)
+  # Tell cmake that we want unit tests to be compiled
+  include(CTest)
+  enable_testing()
+endif()
+
+# Add our CMake helper functions
+include(cmake/KenLMFunctions.cmake)
+
+if(MSVC)
+  set(CMAKE_C_FLAGS "${CMAKE_CXX_FLAGS} /w34716")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /w34716")
+endif()
+
+# And our helper modules
+list(APPEND CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake/modules)
+
+# We need boost
+find_package(Boost 1.41.0 REQUIRED COMPONENTS
+  program_options
+  system
+  thread
+  unit_test_framework
+)
+
+# Define where include files live
+include_directories(${Boost_INCLUDE_DIRS})
+
+set(THREADS_PREFER_PTHREAD_FLAG ON)
+find_package(Threads REQUIRED)
+
+# Process subdirectories
+add_subdirectory(util)
+add_subdirectory(lm)
+
+if(ENABLE_PYTHON)
+  add_subdirectory(python)
+endif()
+
+# Install targets
+install(EXPORT kenlmTargets
+  FILE kenlmTargets.cmake
+  NAMESPACE kenlm::
+  DESTINATION share/kenlm/cmake
+)
+
+foreach(SUBDIR IN ITEMS util util/double-conversion util/stream lm lm/builder lm/common lm/filter lm/interpolate)
+  file(GLOB HEADERS ${CMAKE_CURRENT_LIST_DIR}/${SUBDIR}/*.h ${CMAKE_CURRENT_LIST_DIR}/${SUBDIR}/*.hh)
+  install(FILES ${HEADERS} DESTINATION include/kenlm/${SUBDIR} COMPONENT headers)
+endforeach(SUBDIR)
+
+# Config
+include(CMakePackageConfigHelpers)
+# generate the config file that is includes the exports
+configure_package_config_file(${PROJECT_SOURCE_DIR}/cmake/kenlmConfig.cmake.in
+  "${CMAKE_CURRENT_BINARY_DIR}/kenlmConfig.cmake"
+  INSTALL_DESTINATION share/kenlm/cmake
+  NO_SET_AND_CHECK_MACRO
+  NO_CHECK_REQUIRED_COMPONENTS_MACRO
+  )
+# install the configuration file
+install(FILES
+  ${CMAKE_CURRENT_BINARY_DIR}/kenlmConfig.cmake
+  DESTINATION share/kenlm/cmake
+  )

kenlm/COPYING

@@ -0,0 +1,502 @@
+                  GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL.  It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it.  You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+  When we speak of free software, we are referring to freedom of use,
+not price.  Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+  To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights.  These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  To protect each distributor, we want to make it very clear that
+there is no warranty for the free library.  Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+  Finally, software patents pose a constant threat to the existence of
+any free program.  We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder.  Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+  Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License.  This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License.  We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+  When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library.  The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom.  The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+  We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License.  It also provides other free software developers Less
+of an advantage over competing non-free programs.  These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries.  However, the Lesser license provides advantages in certain
+special circumstances.
+
+  For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard.  To achieve this, non-free programs must be
+allowed to use the library.  A more frequent case is that a free
+library does the same job as widely used non-free libraries.  In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+  In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software.  For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+  Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+                  GNU LESSER GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Use a suitable shared library mechanism for linking with the
+    Library.  A suitable mechanism is one that (1) uses at run time a
+    copy of the library already present on the user's computer system,
+    rather than copying library functions into the executable, and (2)
+    will operate properly with a modified version of the library, if
+    the user installs one, as long as the modified version is
+    interface-compatible with the version that the work was made with.
+
+    c) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    d) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    e) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+                            NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+           How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public
+    License along with this library; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!

kenlm/COPYING.3

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.

kenlm/COPYING.LESSER.3

@@ -0,0 +1,165 @@
+		   GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+
+  This version of the GNU Lesser General Public License incorporates
+the terms and conditions of version 3 of the GNU General Public
+License, supplemented by the additional permissions listed below.
+
+  0. Additional Definitions.
+
+  As used herein, "this License" refers to version 3 of the GNU Lesser
+General Public License, and the "GNU GPL" refers to version 3 of the GNU
+General Public License.
+
+  "The Library" refers to a covered work governed by this License,
+other than an Application or a Combined Work as defined below.
+
+  An "Application" is any work that makes use of an interface provided
+by the Library, but which is not otherwise based on the Library.
+Defining a subclass of a class defined by the Library is deemed a mode
+of using an interface provided by the Library.
+
+  A "Combined Work" is a work produced by combining or linking an
+Application with the Library.  The particular version of the Library
+with which the Combined Work was made is also called the "Linked
+Version".
+
+  The "Minimal Corresponding Source" for a Combined Work means the
+Corresponding Source for the Combined Work, excluding any source code
+for portions of the Combined Work that, considered in isolation, are
+based on the Application, and not on the Linked Version.
+
+  The "Corresponding Application Code" for a Combined Work means the
+object code and/or source code for the Application, including any data
+and utility programs needed for reproducing the Combined Work from the
+Application, but excluding the System Libraries of the Combined Work.
+
+  1. Exception to Section 3 of the GNU GPL.
+
+  You may convey a covered work under sections 3 and 4 of this License
+without being bound by section 3 of the GNU GPL.
+
+  2. Conveying Modified Versions.
+
+  If you modify a copy of the Library, and, in your modifications, a
+facility refers to a function or data to be supplied by an Application
+that uses the facility (other than as an argument passed when the
+facility is invoked), then you may convey a copy of the modified
+version:
+
+   a) under this License, provided that you make a good faith effort to
+   ensure that, in the event an Application does not supply the
+   function or data, the facility still operates, and performs
+   whatever part of its purpose remains meaningful, or
+
+   b) under the GNU GPL, with none of the additional permissions of
+   this License applicable to that copy.
+
+  3. Object Code Incorporating Material from Library Header Files.
+
+  The object code form of an Application may incorporate material from
+a header file that is part of the Library.  You may convey such object
+code under terms of your choice, provided that, if the incorporated
+material is not limited to numerical parameters, data structure
+layouts and accessors, or small macros, inline functions and templates
+(ten or fewer lines in length), you do both of the following:
+
+   a) Give prominent notice with each copy of the object code that the
+   Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the object code with a copy of the GNU GPL and this license
+   document.
+
+  4. Combined Works.
+
+  You may convey a Combined Work under terms of your choice that,
+taken together, effectively do not restrict modification of the
+portions of the Library contained in the Combined Work and reverse
+engineering for debugging such modifications, if you also do each of
+the following:
+
+   a) Give prominent notice with each copy of the Combined Work that
+   the Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the Combined Work with a copy of the GNU GPL and this license
+   document.
+
+   c) For a Combined Work that displays copyright notices during
+   execution, include the copyright notice for the Library among
+   these notices, as well as a reference directing the user to the
+   copies of the GNU GPL and this license document.
+
+   d) Do one of the following:
+
+       0) Convey the Minimal Corresponding Source under the terms of this
+       License, and the Corresponding Application Code in a form
+       suitable for, and under terms that permit, the user to
+       recombine or relink the Application with a modified version of
+       the Linked Version to produce a modified Combined Work, in the
+       manner specified by section 6 of the GNU GPL for conveying
+       Corresponding Source.
+
+       1) Use a suitable shared library mechanism for linking with the
+       Library.  A suitable mechanism is one that (a) uses at run time
+       a copy of the Library already present on the user's computer
+       system, and (b) will operate properly with a modified version
+       of the Library that is interface-compatible with the Linked
+       Version.
+
+   e) Provide Installation Information, but only if you would otherwise
+   be required to provide such information under section 6 of the
+   GNU GPL, and only to the extent that such information is
+   necessary to install and execute a modified version of the
+   Combined Work produced by recombining or relinking the
+   Application with a modified version of the Linked Version. (If
+   you use option 4d0, the Installation Information must accompany
+   the Minimal Corresponding Source and Corresponding Application
+   Code. If you use option 4d1, you must provide the Installation
+   Information in the manner specified by section 6 of the GNU GPL
+   for conveying Corresponding Source.)
+
+  5. Combined Libraries.
+
+  You may place library facilities that are a work based on the
+Library side by side in a single library together with other library
+facilities that are not Applications and are not covered by this
+License, and convey such a combined library under terms of your
+choice, if you do both of the following:
+
+   a) Accompany the combined library with a copy of the same work based
+   on the Library, uncombined with any other library facilities,
+   conveyed under the terms of this License.
+
+   b) Give prominent notice with the combined library that part of it
+   is a work based on the Library, and explaining where to find the
+   accompanying uncombined form of the same work.
+
+  6. Revised Versions of the GNU Lesser General Public License.
+
+  The Free Software Foundation may publish revised and/or new versions
+of the GNU Lesser General Public License from time to time. Such new
+versions will be similar in spirit to the present version, but may
+differ in detail to address new problems or concerns.
+
+  Each version is given a distinguishing version number. If the
+Library as you received it specifies that a certain numbered version
+of the GNU Lesser General Public License "or any later version"
+applies to it, you have the option of following the terms and
+conditions either of that published version or of any later version
+published by the Free Software Foundation. If the Library as you
+received it does not specify a version number of the GNU Lesser
+General Public License, you may choose any version of the GNU Lesser
+General Public License ever published by the Free Software Foundation.
+
+  If the Library as you received it specifies that a proxy can decide
+whether future versions of the GNU Lesser General Public License shall
+apply, that proxy's public statement of acceptance of any version is
+permanent authorization for you to choose that version for the
+Library.

kenlm/Doxyfile

@@ -0,0 +1,1519 @@
+# Doxyfile 1.6.1
+
+# This file describes the settings to be used by the documentation system
+# doxygen (www.doxygen.org) for a project
+#
+# All text after a hash (#) is considered a comment and will be ignored
+# The format is:
+#       TAG = value [value, ...]
+# For lists items can also be appended using:
+#       TAG += value [value, ...]
+# Values that contain spaces should be placed between quotes (" ")
+
+#---------------------------------------------------------------------------
+# Project related configuration options
+#---------------------------------------------------------------------------
+
+# This tag specifies the encoding used for all characters in the config file
+# that follow. The default is UTF-8 which is also the encoding used for all
+# text before the first occurrence of this tag. Doxygen uses libiconv (or the
+# iconv built into libc) for the transcoding. See
+# http://www.gnu.org/software/libiconv for the list of possible encodings.
+
+DOXYFILE_ENCODING      = UTF-8
+
+# The PROJECT_NAME tag is a single word (or a sequence of words surrounded
+# by quotes) that should identify the project.
+
+PROJECT_NAME           = KenLM
+
+# The PROJECT_NUMBER tag can be used to enter a project or revision number.
+# This could be handy for archiving the generated documentation or
+# if some version control system is used.
+
+PROJECT_NUMBER         =
+
+# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
+# base path where the generated documentation will be put.
+# If a relative path is entered, it will be relative to the location
+# where doxygen was started. If left blank the current directory will be used.
+
+OUTPUT_DIRECTORY       = doc
+
+# If the CREATE_SUBDIRS tag is set to YES, then doxygen will create
+# 4096 sub-directories (in 2 levels) under the output directory of each output
+# format and will distribute the generated files over these directories.
+# Enabling this option can be useful when feeding doxygen a huge amount of
+# source files, where putting all generated files in the same directory would
+# otherwise cause performance problems for the file system.
+
+CREATE_SUBDIRS         = NO
+
+# The OUTPUT_LANGUAGE tag is used to specify the language in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all constant output in the proper language.
+# The default language is English, other supported languages are:
+# Afrikaans, Arabic, Brazilian, Catalan, Chinese, Chinese-Traditional,
+# Croatian, Czech, Danish, Dutch, Esperanto, Farsi, Finnish, French, German,
+# Greek, Hungarian, Italian, Japanese, Japanese-en (Japanese with English
+# messages), Korean, Korean-en, Lithuanian, Norwegian, Macedonian, Persian,
+# Polish, Portuguese, Romanian, Russian, Serbian, Serbian-Cyrilic, Slovak,
+# Slovene, Spanish, Swedish, Ukrainian, and Vietnamese.
+
+OUTPUT_LANGUAGE        = English
+
+# If the BRIEF_MEMBER_DESC tag is set to YES (the default) Doxygen will
+# include brief member descriptions after the members that are listed in
+# the file and class documentation (similar to JavaDoc).
+# Set to NO to disable this.
+
+BRIEF_MEMBER_DESC      = YES
+
+# If the REPEAT_BRIEF tag is set to YES (the default) Doxygen will prepend
+# the brief description of a member or function before the detailed description.
+# Note: if both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the
+# brief descriptions will be completely suppressed.
+
+REPEAT_BRIEF           = YES
+
+# This tag implements a quasi-intelligent brief description abbreviator
+# that is used to form the text in various listings. Each string
+# in this list, if found as the leading text of the brief description, will be
+# stripped from the text and the result after processing the whole list, is
+# used as the annotated text. Otherwise, the brief description is used as-is.
+# If left blank, the following values are used ("$name" is automatically
+# replaced with the name of the entity): "The $name class" "The $name widget"
+# "The $name file" "is" "provides" "specifies" "contains"
+# "represents" "a" "an" "the"
+
+ABBREVIATE_BRIEF       =
+
+# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then
+# Doxygen will generate a detailed section even if there is only a brief
+# description.
+
+ALWAYS_DETAILED_SEC    = YES
+
+# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all
+# inherited members of a class in the documentation of that class as if those
+# members were ordinary class members. Constructors, destructors and assignment
+# operators of the base classes will not be shown.
+
+INLINE_INHERITED_MEMB  = NO
+
+# If the FULL_PATH_NAMES tag is set to YES then Doxygen will prepend the full
+# path before files name in the file list and in the header files. If set
+# to NO the shortest path that makes the file name unique will be used.
+
+FULL_PATH_NAMES        = YES
+
+# If the FULL_PATH_NAMES tag is set to YES then the STRIP_FROM_PATH tag
+# can be used to strip a user-defined part of the path. Stripping is
+# only done if one of the specified strings matches the left-hand part of
+# the path. The tag can be used to show relative paths in the file list.
+# If left blank the directory from which doxygen is run is used as the
+# path to strip.
+
+STRIP_FROM_PATH        =
+
+# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of
+# the path mentioned in the documentation of a class, which tells
+# the reader which header file to include in order to use a class.
+# If left blank only the name of the header file containing the class
+# definition is used. Otherwise one should specify the include paths that
+# are normally passed to the compiler using the -I flag.
+
+STRIP_FROM_INC_PATH    =
+
+# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter
+# (but less readable) file names. This can be useful is your file systems
+# doesn't support long names like on DOS, Mac, or CD-ROM.
+
+SHORT_NAMES            = NO
+
+# If the JAVADOC_AUTOBRIEF tag is set to YES then Doxygen
+# will interpret the first line (until the first dot) of a JavaDoc-style
+# comment as the brief description. If set to NO, the JavaDoc
+# comments will behave just like regular Qt-style comments
+# (thus requiring an explicit @brief command for a brief description.)
+
+JAVADOC_AUTOBRIEF      = YES
+
+# If the QT_AUTOBRIEF tag is set to YES then Doxygen will
+# interpret the first line (until the first dot) of a Qt-style
+# comment as the brief description. If set to NO, the comments
+# will behave just like regular Qt-style comments (thus requiring
+# an explicit \brief command for a brief description.)
+
+QT_AUTOBRIEF           = NO
+
+# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen
+# treat a multi-line C++ special comment block (i.e. a block of //! or ///
+# comments) as a brief description. This used to be the default behaviour.
+# The new default is to treat a multi-line C++ comment block as a detailed
+# description. Set this tag to YES if you prefer the old behaviour instead.
+
+MULTILINE_CPP_IS_BRIEF = NO
+
+# If the INHERIT_DOCS tag is set to YES (the default) then an undocumented
+# member inherits the documentation from any documented member that it
+# re-implements.
+
+INHERIT_DOCS           = YES
+
+# If the SEPARATE_MEMBER_PAGES tag is set to YES, then doxygen will produce
+# a new page for each member. If set to NO, the documentation of a member will
+# be part of the file/class/namespace that contains it.
+
+SEPARATE_MEMBER_PAGES  = NO
+
+# The TAB_SIZE tag can be used to set the number of spaces in a tab.
+# Doxygen uses this value to replace tabs by spaces in code fragments.
+
+TAB_SIZE               = 8
+
+# This tag can be used to specify a number of aliases that acts
+# as commands in the documentation. An alias has the form "name=value".
+# For example adding "sideeffect=\par Side Effects:\n" will allow you to
+# put the command \sideeffect (or @sideeffect) in the documentation, which
+# will result in a user-defined paragraph with heading "Side Effects:".
+# You can put \n's in the value part of an alias to insert newlines.
+
+ALIASES                =
+
+# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C
+# sources only. Doxygen will then generate output that is more tailored for C.
+# For instance, some of the names that are used will be different. The list
+# of all members will be omitted, etc.
+
+OPTIMIZE_OUTPUT_FOR_C  = NO
+
+# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java
+# sources only. Doxygen will then generate output that is more tailored for
+# Java. For instance, namespaces will be presented as packages, qualified
+# scopes will look different, etc.
+
+OPTIMIZE_OUTPUT_JAVA   = NO
+
+# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran
+# sources only. Doxygen will then generate output that is more tailored for
+# Fortran.
+
+OPTIMIZE_FOR_FORTRAN   = NO
+
+# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL
+# sources. Doxygen will then generate output that is tailored for
+# VHDL.
+
+OPTIMIZE_OUTPUT_VHDL   = NO
+
+# Doxygen selects the parser to use depending on the extension of the files it parses.
+# With this tag you can assign which parser to use for a given extension.
+# Doxygen has a built-in mapping, but you can override or extend it using this tag.
+# The format is ext=language, where ext is a file extension, and language is one of
+# the parsers supported by doxygen: IDL, Java, Javascript, C#, C, C++, D, PHP,
+# Objective-C, Python, Fortran, VHDL, C, C++. For instance to make doxygen treat
+# .inc files as Fortran files (default is PHP), and .f files as C (default is Fortran),
+# use: inc=Fortran f=C. Note that for custom extensions you also need to set FILE_PATTERNS otherwise the files are not read by doxygen.
+
+EXTENSION_MAPPING      =
+
+# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want
+# to include (a tag file for) the STL sources as input, then you should
+# set this tag to YES in order to let doxygen match functions declarations and
+# definitions whose arguments contain STL classes (e.g. func(std::string); v.s.
+# func(std::string) {}). This also make the inheritance and collaboration
+# diagrams that involve STL classes more complete and accurate.
+
+BUILTIN_STL_SUPPORT    = NO
+
+# If you use Microsoft's C++/CLI language, you should set this option to YES to
+# enable parsing support.
+
+CPP_CLI_SUPPORT        = NO
+
+# Set the SIP_SUPPORT tag to YES if your project consists of sip sources only.
+# Doxygen will parse them like normal C++ but will assume all classes use public
+# instead of private inheritance when no explicit protection keyword is present.
+
+SIP_SUPPORT            = NO
+
+# For Microsoft's IDL there are propget and propput attributes to indicate getter
+# and setter methods for a property. Setting this option to YES (the default)
+# will make doxygen to replace the get and set methods by a property in the
+# documentation. This will only work if the methods are indeed getting or
+# setting a simple type. If this is not the case, or you want to show the
+# methods anyway, you should set this option to NO.
+
+IDL_PROPERTY_SUPPORT   = YES
+
+# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC
+# tag is set to YES, then doxygen will reuse the documentation of the first
+# member in the group (if any) for the other members of the group. By default
+# all members of a group must be documented explicitly.
+
+DISTRIBUTE_GROUP_DOC   = NO
+
+# Set the SUBGROUPING tag to YES (the default) to allow class member groups of
+# the same type (for instance a group of public functions) to be put as a
+# subgroup of that type (e.g. under the Public Functions section). Set it to
+# NO to prevent subgrouping. Alternatively, this can be done per class using
+# the \nosubgrouping command.
+
+SUBGROUPING            = YES
+
+# When TYPEDEF_HIDES_STRUCT is enabled, a typedef of a struct, union, or enum
+# is documented as struct, union, or enum with the name of the typedef. So
+# typedef struct TypeS {} TypeT, will appear in the documentation as a struct
+# with name TypeT. When disabled the typedef will appear as a member of a file,
+# namespace, or class. And the struct will be named TypeS. This can typically
+# be useful for C code in case the coding convention dictates that all compound
+# types are typedef'ed and only the typedef is referenced, never the tag name.
+
+TYPEDEF_HIDES_STRUCT   = NO
+
+# The SYMBOL_CACHE_SIZE determines the size of the internal cache use to
+# determine which symbols to keep in memory and which to flush to disk.
+# When the cache is full, less often used symbols will be written to disk.
+# For small to medium size projects (<1000 input files) the default value is
+# probably good enough. For larger projects a too small cache size can cause
+# doxygen to be busy swapping symbols to and from disk most of the time
+# causing a significant performance penality.
+# If the system has enough physical memory increasing the cache will improve the
+# performance by keeping more symbols in memory. Note that the value works on
+# a logarithmic scale so increasing the size by one will rougly double the
+# memory usage. The cache size is given by this formula:
+# 2^(16+SYMBOL_CACHE_SIZE). The valid range is 0..9, the default is 0,
+# corresponding to a cache size of 2^16 = 65536 symbols
+
+SYMBOL_CACHE_SIZE      = 0
+
+#---------------------------------------------------------------------------
+# Build related configuration options
+#---------------------------------------------------------------------------
+
+# If the EXTRACT_ALL tag is set to YES doxygen will assume all entities in
+# documentation are documented, even if no documentation was available.
+# Private class members and static file members will be hidden unless
+# the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES
+
+EXTRACT_ALL            = NO
+
+# If the EXTRACT_PRIVATE tag is set to YES all private members of a class
+# will be included in the documentation.
+
+EXTRACT_PRIVATE        = YES
+
+# If the EXTRACT_STATIC tag is set to YES all static members of a file
+# will be included in the documentation.
+
+EXTRACT_STATIC         = NO
+
+# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs)
+# defined locally in source files will be included in the documentation.
+# If set to NO only classes defined in header files are included.
+
+EXTRACT_LOCAL_CLASSES  = YES
+
+# This flag is only useful for Objective-C code. When set to YES local
+# methods, which are defined in the implementation section but not in
+# the interface are included in the documentation.
+# If set to NO (the default) only methods in the interface are included.
+
+EXTRACT_LOCAL_METHODS  = NO
+
+# If this flag is set to YES, the members of anonymous namespaces will be
+# extracted and appear in the documentation as a namespace called
+# 'anonymous_namespace{file}', where file will be replaced with the base
+# name of the file that contains the anonymous namespace. By default
+# anonymous namespace are hidden.
+
+EXTRACT_ANON_NSPACES   = NO
+
+# If the HIDE_UNDOC_MEMBERS tag is set to YES, Doxygen will hide all
+# undocumented members of documented classes, files or namespaces.
+# If set to NO (the default) these members will be included in the
+# various overviews, but no documentation section is generated.
+# This option has no effect if EXTRACT_ALL is enabled.
+
+HIDE_UNDOC_MEMBERS     = YES
+
+# If the HIDE_UNDOC_CLASSES tag is set to YES, Doxygen will hide all
+# undocumented classes that are normally visible in the class hierarchy.
+# If set to NO (the default) these classes will be included in the various
+# overviews. This option has no effect if EXTRACT_ALL is enabled.
+
+HIDE_UNDOC_CLASSES     = YES
+
+# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, Doxygen will hide all
+# friend (class|struct|union) declarations.
+# If set to NO (the default) these declarations will be included in the
+# documentation.
+
+HIDE_FRIEND_COMPOUNDS  = NO
+
+# If the HIDE_IN_BODY_DOCS tag is set to YES, Doxygen will hide any
+# documentation blocks found inside the body of a function.
+# If set to NO (the default) these blocks will be appended to the
+# function's detailed documentation block.
+
+HIDE_IN_BODY_DOCS      = NO
+
+# The INTERNAL_DOCS tag determines if documentation
+# that is typed after a \internal command is included. If the tag is set
+# to NO (the default) then the documentation will be excluded.
+# Set it to YES to include the internal documentation.
+
+INTERNAL_DOCS          = NO
+
+# If the CASE_SENSE_NAMES tag is set to NO then Doxygen will only generate
+# file names in lower-case letters. If set to YES upper-case letters are also
+# allowed. This is useful if you have classes or files whose names only differ
+# in case and if your file system supports case sensitive file names. Windows
+# and Mac users are advised to set this option to NO.
+
+CASE_SENSE_NAMES       = YES
+
+# If the HIDE_SCOPE_NAMES tag is set to NO (the default) then Doxygen
+# will show members with their full class and namespace scopes in the
+# documentation. If set to YES the scope will be hidden.
+
+HIDE_SCOPE_NAMES       = NO
+
+# If the SHOW_INCLUDE_FILES tag is set to YES (the default) then Doxygen
+# will put a list of the files that are included by a file in the documentation
+# of that file.
+
+SHOW_INCLUDE_FILES     = YES
+
+# If the INLINE_INFO tag is set to YES (the default) then a tag [inline]
+# is inserted in the documentation for inline members.
+
+INLINE_INFO            = YES
+
+# If the SORT_MEMBER_DOCS tag is set to YES (the default) then doxygen
+# will sort the (detailed) documentation of file and class members
+# alphabetically by member name. If set to NO the members will appear in
+# declaration order.
+
+SORT_MEMBER_DOCS       = YES
+
+# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the
+# brief documentation of file, namespace and class members alphabetically
+# by member name. If set to NO (the default) the members will appear in
+# declaration order.
+
+SORT_BRIEF_DOCS        = NO
+
+# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the (brief and detailed) documentation of class members so that constructors and destructors are listed first. If set to NO (the default) the constructors will appear in the respective orders defined by SORT_MEMBER_DOCS and SORT_BRIEF_DOCS. This tag will be ignored for brief docs if SORT_BRIEF_DOCS is set to NO and ignored for detailed docs if SORT_MEMBER_DOCS is set to NO.
+
+SORT_MEMBERS_CTORS_1ST = YES
+
+# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the
+# hierarchy of group names into alphabetical order. If set to NO (the default)
+# the group names will appear in their defined order.
+
+SORT_GROUP_NAMES       = NO
+
+# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be
+# sorted by fully-qualified names, including namespaces. If set to
+# NO (the default), the class list will be sorted only by class name,
+# not including the namespace part.
+# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.
+# Note: This option applies only to the class list, not to the
+# alphabetical list.
+
+SORT_BY_SCOPE_NAME     = YES
+
+# The GENERATE_TODOLIST tag can be used to enable (YES) or
+# disable (NO) the todo list. This list is created by putting \todo
+# commands in the documentation.
+
+GENERATE_TODOLIST      = YES
+
+# The GENERATE_TESTLIST tag can be used to enable (YES) or
+# disable (NO) the test list. This list is created by putting \test
+# commands in the documentation.
+
+GENERATE_TESTLIST      = YES
+
+# The GENERATE_BUGLIST tag can be used to enable (YES) or
+# disable (NO) the bug list. This list is created by putting \bug
+# commands in the documentation.
+
+GENERATE_BUGLIST       = YES
+
+# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or
+# disable (NO) the deprecated list. This list is created by putting
+# \deprecated commands in the documentation.
+
+GENERATE_DEPRECATEDLIST= YES
+
+# The ENABLED_SECTIONS tag can be used to enable conditional
+# documentation sections, marked by \if sectionname ... \endif.
+
+ENABLED_SECTIONS       =
+
+# The MAX_INITIALIZER_LINES tag determines the maximum number of lines
+# the initial value of a variable or define consists of for it to appear in
+# the documentation. If the initializer consists of more lines than specified
+# here it will be hidden. Use a value of 0 to hide initializers completely.
+# The appearance of the initializer of individual variables and defines in the
+# documentation can be controlled using \showinitializer or \hideinitializer
+# command in the documentation regardless of this setting.
+
+MAX_INITIALIZER_LINES  = 30
+
+# Set the SHOW_USED_FILES tag to NO to disable the list of files generated
+# at the bottom of the documentation of classes and structs. If set to YES the
+# list will mention the files that were used to generate the documentation.
+
+SHOW_USED_FILES        = YES
+
+# If the sources in your project are distributed over multiple directories
+# then setting the SHOW_DIRECTORIES tag to YES will show the directory hierarchy
+# in the documentation. The default is NO.
+
+SHOW_DIRECTORIES       = NO
+
+# Set the SHOW_FILES tag to NO to disable the generation of the Files page.
+# This will remove the Files entry from the Quick Index and from the
+# Folder Tree View (if specified). The default is YES.
+
+SHOW_FILES             = YES
+
+# Set the SHOW_NAMESPACES tag to NO to disable the generation of the
+# Namespaces page.
+# This will remove the Namespaces entry from the Quick Index
+# and from the Folder Tree View (if specified). The default is YES.
+
+SHOW_NAMESPACES        = YES
+
+# The FILE_VERSION_FILTER tag can be used to specify a program or script that
+# doxygen should invoke to get the current version for each file (typically from
+# the version control system). Doxygen will invoke the program by executing (via
+# popen()) the command <command> <input-file>, where <command> is the value of
+# the FILE_VERSION_FILTER tag, and <input-file> is the name of an input file
+# provided by doxygen. Whatever the program writes to standard output
+# is used as the file version. See the manual for examples.
+
+FILE_VERSION_FILTER    =
+
+# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed by
+# doxygen. The layout file controls the global structure of the generated output files
+# in an output format independent way. The create the layout file that represents
+# doxygen's defaults, run doxygen with the -l option. You can optionally specify a
+# file name after the option, if omitted DoxygenLayout.xml will be used as the name
+# of the layout file.
+
+LAYOUT_FILE            =
+
+#---------------------------------------------------------------------------
+# configuration options related to warning and progress messages
+#---------------------------------------------------------------------------
+
+# The QUIET tag can be used to turn on/off the messages that are generated
+# by doxygen. Possible values are YES and NO. If left blank NO is used.
+
+QUIET                  = NO
+
+# The WARNINGS tag can be used to turn on/off the warning messages that are
+# generated by doxygen. Possible values are YES and NO. If left blank
+# NO is used.
+
+WARNINGS               = YES
+
+# If WARN_IF_UNDOCUMENTED is set to YES, then doxygen will generate warnings
+# for undocumented members. If EXTRACT_ALL is set to YES then this flag will
+# automatically be disabled.
+
+WARN_IF_UNDOCUMENTED   = YES
+
+# If WARN_IF_DOC_ERROR is set to YES, doxygen will generate warnings for
+# potential errors in the documentation, such as not documenting some
+# parameters in a documented function, or documenting parameters that
+# don't exist or using markup commands wrongly.
+
+WARN_IF_DOC_ERROR      = YES
+
+# This WARN_NO_PARAMDOC option can be abled to get warnings for
+# functions that are documented, but have no documentation for their parameters
+# or return value. If set to NO (the default) doxygen will only warn about
+# wrong or incomplete parameter documentation, but not about the absence of
+# documentation.
+
+WARN_NO_PARAMDOC       = NO
+
+# The WARN_FORMAT tag determines the format of the warning messages that
+# doxygen can produce. The string should contain the $file, $line, and $text
+# tags, which will be replaced by the file and line number from which the
+# warning originated and the warning text. Optionally the format may contain
+# $version, which will be replaced by the version of the file (if it could
+# be obtained via FILE_VERSION_FILTER)
+
+WARN_FORMAT            = "$file:$line: $text"
+
+# The WARN_LOGFILE tag can be used to specify a file to which warning
+# and error messages should be written. If left blank the output is written
+# to stderr.
+
+WARN_LOGFILE           =
+
+#---------------------------------------------------------------------------
+# configuration options related to the input files
+#---------------------------------------------------------------------------
+
+# The INPUT tag can be used to specify the files and/or directories that contain
+# documented source files. You may enter file names like "myfile.cpp" or
+# directories like "/usr/src/myproject". Separate the files or directories
+# with spaces.
+
+INPUT                  = lm lm/builder lm/filter lm/interpolate lm/wrappers util util/double-conversion util/stream
+
+# This tag can be used to specify the character encoding of the source files
+# that doxygen parses. Internally doxygen uses the UTF-8 encoding, which is
+# also the default input encoding. Doxygen uses libiconv (or the iconv built
+# into libc) for the transcoding. See http://www.gnu.org/software/libiconv for
+# the list of possible encodings.
+
+INPUT_ENCODING         = UTF-8
+
+# If the value of the INPUT tag contains directories, you can use the
+# FILE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp
+# and *.h) to filter out the source-files in the directories. If left
+# blank the following patterns are tested:
+# *.c *.cc *.cxx *.cpp *.c++ *.java *.ii *.ixx *.ipp *.i++ *.inl *.h *.hh *.hxx
+# *.hpp *.h++ *.idl *.odl *.cs *.php *.php3 *.inc *.m *.mm *.py *.f90
+
+FILE_PATTERNS          =
+
+# The RECURSIVE tag can be used to turn specify whether or not subdirectories
+# should be searched for input files as well. Possible values are YES and NO.
+# If left blank NO is used.
+
+RECURSIVE              = NO
+
+# The EXCLUDE tag can be used to specify files and/or directories that should
+# excluded from the INPUT source files. This way you can easily exclude a
+# subdirectory from a directory tree whose root is specified with the INPUT tag.
+
+EXCLUDE                =
+
+# The EXCLUDE_SYMLINKS tag can be used select whether or not files or
+# directories that are symbolic links (a Unix filesystem feature) are excluded
+# from the input.
+
+EXCLUDE_SYMLINKS       = NO
+
+# If the value of the INPUT tag contains directories, you can use the
+# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude
+# certain files from those directories. Note that the wildcards are matched
+# against the file with absolute path, so to exclude all test directories
+# for example use the pattern */test/*
+
+EXCLUDE_PATTERNS       =
+
+# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
+# (namespaces, classes, functions, etc.) that should be excluded from the
+# output. The symbol name can be a fully qualified name, a word, or if the
+# wildcard * is used, a substring. Examples: ANamespace, AClass,
+# AClass::ANamespace, ANamespace::*Test
+
+EXCLUDE_SYMBOLS        =
+
+# The EXAMPLE_PATH tag can be used to specify one or more files or
+# directories that contain example code fragments that are included (see
+# the \include command).
+
+EXAMPLE_PATH           =
+
+# If the value of the EXAMPLE_PATH tag contains directories, you can use the
+# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp
+# and *.h) to filter out the source-files in the directories. If left
+# blank all files are included.
+
+EXAMPLE_PATTERNS       =
+
+# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be
+# searched for input files to be used with the \include or \dontinclude
+# commands irrespective of the value of the RECURSIVE tag.
+# Possible values are YES and NO. If left blank NO is used.
+
+EXAMPLE_RECURSIVE      = NO
+
+# The IMAGE_PATH tag can be used to specify one or more files or
+# directories that contain image that are included in the documentation (see
+# the \image command).
+
+IMAGE_PATH             =
+
+# The INPUT_FILTER tag can be used to specify a program that doxygen should
+# invoke to filter for each input file. Doxygen will invoke the filter program
+# by executing (via popen()) the command <filter> <input-file>, where <filter>
+# is the value of the INPUT_FILTER tag, and <input-file> is the name of an
+# input file. Doxygen will then use the output that the filter program writes
+# to standard output.
+# If FILTER_PATTERNS is specified, this tag will be
+# ignored.
+
+INPUT_FILTER           =
+
+# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern
+# basis.
+# Doxygen will compare the file name with each pattern and apply the
+# filter if there is a match.
+# The filters are a list of the form:
+# pattern=filter (like *.cpp=my_cpp_filter). See INPUT_FILTER for further
+# info on how filters are used. If FILTER_PATTERNS is empty, INPUT_FILTER
+# is applied to all files.
+
+FILTER_PATTERNS        =
+
+# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using
+# INPUT_FILTER) will be used to filter the input files when producing source
+# files to browse (i.e. when SOURCE_BROWSER is set to YES).
+
+FILTER_SOURCE_FILES    = NO
+
+#---------------------------------------------------------------------------
+# configuration options related to source browsing
+#---------------------------------------------------------------------------
+
+# If the SOURCE_BROWSER tag is set to YES then a list of source files will
+# be generated. Documented entities will be cross-referenced with these sources.
+# Note: To get rid of all source code in the generated output, make sure also
+# VERBATIM_HEADERS is set to NO.
+
+SOURCE_BROWSER         = NO
+
+# Setting the INLINE_SOURCES tag to YES will include the body
+# of functions and classes directly in the documentation.
+
+INLINE_SOURCES         = NO
+
+# Setting the STRIP_CODE_COMMENTS tag to YES (the default) will instruct
+# doxygen to hide any special comment blocks from generated source code
+# fragments. Normal C and C++ comments will always remain visible.
+
+STRIP_CODE_COMMENTS    = YES
+
+# If the REFERENCED_BY_RELATION tag is set to YES
+# then for each documented function all documented
+# functions referencing it will be listed.
+
+REFERENCED_BY_RELATION = NO
+
+# If the REFERENCES_RELATION tag is set to YES
+# then for each documented function all documented entities
+# called/used by that function will be listed.
+
+REFERENCES_RELATION    = NO
+
+# If the REFERENCES_LINK_SOURCE tag is set to YES (the default)
+# and SOURCE_BROWSER tag is set to YES, then the hyperlinks from
+# functions in REFERENCES_RELATION and REFERENCED_BY_RELATION lists will
+# link to the source code.
+# Otherwise they will link to the documentation.
+
+REFERENCES_LINK_SOURCE = YES
+
+# If the USE_HTAGS tag is set to YES then the references to source code
+# will point to the HTML generated by the htags(1) tool instead of doxygen
+# built-in source browser. The htags tool is part of GNU's global source
+# tagging system (see http://www.gnu.org/software/global/global.html). You
+# will need version 4.8.6 or higher.
+
+USE_HTAGS              = NO
+
+# If the VERBATIM_HEADERS tag is set to YES (the default) then Doxygen
+# will generate a verbatim copy of the header file for each class for
+# which an include is specified. Set to NO to disable this.
+
+VERBATIM_HEADERS       = YES
+
+#---------------------------------------------------------------------------
+# configuration options related to the alphabetical class index
+#---------------------------------------------------------------------------
+
+# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index
+# of all compounds will be generated. Enable this if the project
+# contains a lot of classes, structs, unions or interfaces.
+
+ALPHABETICAL_INDEX     = NO
+
+# If the alphabetical index is enabled (see ALPHABETICAL_INDEX) then
+# the COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns
+# in which this list will be split (can be a number in the range [1..20])
+
+COLS_IN_ALPHA_INDEX    = 5
+
+# In case all classes in a project start with a common prefix, all
+# classes will be put under the same header in the alphabetical index.
+# The IGNORE_PREFIX tag can be used to specify one or more prefixes that
+# should be ignored while generating the index headers.
+
+IGNORE_PREFIX          =
+
+#---------------------------------------------------------------------------
+# configuration options related to the HTML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_HTML tag is set to YES (the default) Doxygen will
+# generate HTML output.
+
+GENERATE_HTML          = YES
+
+# The HTML_OUTPUT tag is used to specify where the HTML docs will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be
+# put in front of it. If left blank `html' will be used as the default path.
+
+HTML_OUTPUT            = html
+
+# The HTML_FILE_EXTENSION tag can be used to specify the file extension for
+# each generated HTML page (for example: .htm,.php,.asp). If it is left blank
+# doxygen will generate files with .html extension.
+
+HTML_FILE_EXTENSION    = .html
+
+# The HTML_HEADER tag can be used to specify a personal HTML header for
+# each generated HTML page. If it is left blank doxygen will generate a
+# standard header.
+
+HTML_HEADER            =
+
+# The HTML_FOOTER tag can be used to specify a personal HTML footer for
+# each generated HTML page. If it is left blank doxygen will generate a
+# standard footer.
+
+HTML_FOOTER            =
+
+# If the HTML_TIMESTAMP tag is set to YES then the generated HTML
+# documentation will contain the timesstamp.
+
+HTML_TIMESTAMP         = NO
+
+# The HTML_STYLESHEET tag can be used to specify a user-defined cascading
+# style sheet that is used by each HTML page. It can be used to
+# fine-tune the look of the HTML output. If the tag is left blank doxygen
+# will generate a default style sheet. Note that doxygen will try to copy
+# the style sheet file to the HTML output directory, so don't put your own
+# stylesheet in the HTML output directory as well, or it will be erased!
+
+HTML_STYLESHEET        =
+
+# If the HTML_ALIGN_MEMBERS tag is set to YES, the members of classes,
+# files or namespaces will be aligned in HTML using tables. If set to
+# NO a bullet list will be used.
+
+HTML_ALIGN_MEMBERS     = YES
+
+# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
+# documentation will contain sections that can be hidden and shown after the
+# page has loaded. For this to work a browser that supports
+# JavaScript and DHTML is required (for instance Mozilla 1.0+, Firefox
+# Netscape 6.0+, Internet explorer 5.0+, Konqueror, or Safari).
+
+HTML_DYNAMIC_SECTIONS  = NO
+
+# If the GENERATE_DOCSET tag is set to YES, additional index files
+# will be generated that can be used as input for Apple's Xcode 3
+# integrated development environment, introduced with OSX 10.5 (Leopard).
+# To create a documentation set, doxygen will generate a Makefile in the
+# HTML output directory. Running make will produce the docset in that
+# directory and running "make install" will install the docset in
+# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find
+# it at startup.
+# See http://developer.apple.com/tools/creatingdocsetswithdoxygen.html for more information.
+
+GENERATE_DOCSET        = NO
+
+# When GENERATE_DOCSET tag is set to YES, this tag determines the name of the
+# feed. A documentation feed provides an umbrella under which multiple
+# documentation sets from a single provider (such as a company or product suite)
+# can be grouped.
+
+DOCSET_FEEDNAME        = "Doxygen generated docs"
+
+# When GENERATE_DOCSET tag is set to YES, this tag specifies a string that
+# should uniquely identify the documentation set bundle. This should be a
+# reverse domain-name style string, e.g. com.mycompany.MyDocSet. Doxygen
+# will append .docset to the name.
+
+DOCSET_BUNDLE_ID       = org.doxygen.Project
+
+# If the GENERATE_HTMLHELP tag is set to YES, additional index files
+# will be generated that can be used as input for tools like the
+# Microsoft HTML help workshop to generate a compiled HTML help file (.chm)
+# of the generated HTML documentation.
+
+GENERATE_HTMLHELP      = NO
+
+# If the GENERATE_HTMLHELP tag is set to YES, the CHM_FILE tag can
+# be used to specify the file name of the resulting .chm file. You
+# can add a path in front of the file if the result should not be
+# written to the html output directory.
+
+CHM_FILE               =
+
+# If the GENERATE_HTMLHELP tag is set to YES, the HHC_LOCATION tag can
+# be used to specify the location (absolute path including file name) of
+# the HTML help compiler (hhc.exe). If non-empty doxygen will try to run
+# the HTML help compiler on the generated index.hhp.
+
+HHC_LOCATION           =
+
+# If the GENERATE_HTMLHELP tag is set to YES, the GENERATE_CHI flag
+# controls if a separate .chi index file is generated (YES) or that
+# it should be included in the master .chm file (NO).
+
+GENERATE_CHI           = NO
+
+# If the GENERATE_HTMLHELP tag is set to YES, the CHM_INDEX_ENCODING
+# is used to encode HtmlHelp index (hhk), content (hhc) and project file
+# content.
+
+CHM_INDEX_ENCODING     =
+
+# If the GENERATE_HTMLHELP tag is set to YES, the BINARY_TOC flag
+# controls whether a binary table of contents is generated (YES) or a
+# normal table of contents (NO) in the .chm file.
+
+BINARY_TOC             = NO
+
+# The TOC_EXPAND flag can be set to YES to add extra items for group members
+# to the contents of the HTML help documentation and to the tree view.
+
+TOC_EXPAND             = NO
+
+# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and QHP_VIRTUAL_FOLDER
+# are set, an additional index file will be generated that can be used as input for
+# Qt's qhelpgenerator to generate a Qt Compressed Help (.qch) of the generated
+# HTML documentation.
+
+GENERATE_QHP           = NO
+
+# If the QHG_LOCATION tag is specified, the QCH_FILE tag can
+# be used to specify the file name of the resulting .qch file.
+# The path specified is relative to the HTML output folder.
+
+QCH_FILE               =
+
+# The QHP_NAMESPACE tag specifies the namespace to use when generating
+# Qt Help Project output. For more information please see
+# http://doc.trolltech.com/qthelpproject.html#namespace
+
+QHP_NAMESPACE          =
+
+# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating
+# Qt Help Project output. For more information please see
+# http://doc.trolltech.com/qthelpproject.html#virtual-folders
+
+QHP_VIRTUAL_FOLDER     = doc
+
+# If QHP_CUST_FILTER_NAME is set, it specifies the name of a custom filter to add.
+# For more information please see
+# http://doc.trolltech.com/qthelpproject.html#custom-filters
+
+QHP_CUST_FILTER_NAME   =
+
+# The QHP_CUST_FILT_ATTRS tag specifies the list of the attributes of the custom filter to add.For more information please see
+# <a href="http://doc.trolltech.com/qthelpproject.html#custom-filters">Qt Help Project / Custom Filters</a>.
+
+QHP_CUST_FILTER_ATTRS  =
+
+# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this project's
+# filter section matches.
+# <a href="http://doc.trolltech.com/qthelpproject.html#filter-attributes">Qt Help Project / Filter Attributes</a>.
+
+QHP_SECT_FILTER_ATTRS  =
+
+# If the GENERATE_QHP tag is set to YES, the QHG_LOCATION tag can
+# be used to specify the location of Qt's qhelpgenerator.
+# If non-empty doxygen will try to run qhelpgenerator on the generated
+# .qhp file.
+
+QHG_LOCATION           =
+
+# The DISABLE_INDEX tag can be used to turn on/off the condensed index at
+# top of each HTML page. The value NO (the default) enables the index and
+# the value YES disables it.
+
+DISABLE_INDEX          = NO
+
+# This tag can be used to set the number of enum values (range [1..20])
+# that doxygen will group on one line in the generated HTML documentation.
+
+ENUM_VALUES_PER_LINE   = 4
+
+# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index
+# structure should be generated to display hierarchical information.
+# If the tag value is set to YES, a side panel will be generated
+# containing a tree-like index structure (just like the one that
+# is generated for HTML Help). For this to work a browser that supports
+# JavaScript, DHTML, CSS and frames is required (i.e. any modern browser).
+# Windows users are probably better off using the HTML help feature.
+
+GENERATE_TREEVIEW      = NO
+
+# By enabling USE_INLINE_TREES, doxygen will generate the Groups, Directories,
+# and Class Hierarchy pages using a tree view instead of an ordered list.
+
+USE_INLINE_TREES       = NO
+
+# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be
+# used to set the initial width (in pixels) of the frame in which the tree
+# is shown.
+
+TREEVIEW_WIDTH         = 250
+
+# Use this tag to change the font size of Latex formulas included
+# as images in the HTML documentation. The default is 10. Note that
+# when you change the font size after a successful doxygen run you need
+# to manually remove any form_*.png images from the HTML output directory
+# to force them to be regenerated.
+
+FORMULA_FONTSIZE       = 10
+
+# When the SEARCHENGINE tag is enable doxygen will generate a search box for the HTML output. The underlying search engine uses javascript
+# and DHTML and should work on any modern browser. Note that when using HTML help (GENERATE_HTMLHELP) or Qt help (GENERATE_QHP)
+# there is already a search function so this one should typically
+# be disabled.
+
+SEARCHENGINE           = YES
+
+#---------------------------------------------------------------------------
+# configuration options related to the LaTeX output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_LATEX tag is set to YES (the default) Doxygen will
+# generate Latex output.
+
+GENERATE_LATEX         = YES
+
+# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be
+# put in front of it. If left blank `latex' will be used as the default path.
+
+LATEX_OUTPUT           = latex
+
+# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
+# invoked. If left blank `latex' will be used as the default command name.
+
+LATEX_CMD_NAME         = latex
+
+# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to
+# generate index for LaTeX. If left blank `makeindex' will be used as the
+# default command name.
+
+MAKEINDEX_CMD_NAME     = makeindex
+
+# If the COMPACT_LATEX tag is set to YES Doxygen generates more compact
+# LaTeX documents. This may be useful for small projects and may help to
+# save some trees in general.
+
+COMPACT_LATEX          = NO
+
+# The PAPER_TYPE tag can be used to set the paper type that is used
+# by the printer. Possible values are: a4, a4wide, letter, legal and
+# executive. If left blank a4wide will be used.
+
+PAPER_TYPE             = a4wide
+
+# The EXTRA_PACKAGES tag can be to specify one or more names of LaTeX
+# packages that should be included in the LaTeX output.
+
+EXTRA_PACKAGES         =
+
+# The LATEX_HEADER tag can be used to specify a personal LaTeX header for
+# the generated latex document. The header should contain everything until
+# the first chapter. If it is left blank doxygen will generate a
+# standard header. Notice: only use this tag if you know what you are doing!
+
+LATEX_HEADER           =
+
+# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated
+# is prepared for conversion to pdf (using ps2pdf). The pdf file will
+# contain links (just like the HTML output) instead of page references
+# This makes the output suitable for online browsing using a pdf viewer.
+
+PDF_HYPERLINKS         = YES
+
+# If the USE_PDFLATEX tag is set to YES, pdflatex will be used instead of
+# plain latex in the generated Makefile. Set this option to YES to get a
+# higher quality PDF documentation.
+
+USE_PDFLATEX           = YES
+
+# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \\batchmode.
+# command to the generated LaTeX files. This will instruct LaTeX to keep
+# running if errors occur, instead of asking the user for help.
+# This option is also used when generating formulas in HTML.
+
+LATEX_BATCHMODE        = NO
+
+# If LATEX_HIDE_INDICES is set to YES then doxygen will not
+# include the index chapters (such as File Index, Compound Index, etc.)
+# in the output.
+
+LATEX_HIDE_INDICES     = NO
+
+# If LATEX_SOURCE_CODE is set to YES then doxygen will include source code with syntax highlighting in the LaTeX output. Note that which sources are shown also depends on other settings such as SOURCE_BROWSER.
+
+LATEX_SOURCE_CODE      = NO
+
+#---------------------------------------------------------------------------
+# configuration options related to the RTF output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_RTF tag is set to YES Doxygen will generate RTF output
+# The RTF output is optimized for Word 97 and may not look very pretty with
+# other RTF readers or editors.
+
+GENERATE_RTF           = NO
+
+# The RTF_OUTPUT tag is used to specify where the RTF docs will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be
+# put in front of it. If left blank `rtf' will be used as the default path.
+
+RTF_OUTPUT             = rtf
+
+# If the COMPACT_RTF tag is set to YES Doxygen generates more compact
+# RTF documents. This may be useful for small projects and may help to
+# save some trees in general.
+
+COMPACT_RTF            = NO
+
+# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated
+# will contain hyperlink fields. The RTF file will
+# contain links (just like the HTML output) instead of page references.
+# This makes the output suitable for online browsing using WORD or other
+# programs which support those fields.
+# Note: wordpad (write) and others do not support links.
+
+RTF_HYPERLINKS         = NO
+
+# Load stylesheet definitions from file. Syntax is similar to doxygen's
+# config file, i.e. a series of assignments. You only have to provide
+# replacements, missing definitions are set to their default value.
+
+RTF_STYLESHEET_FILE    =
+
+# Set optional variables used in the generation of an rtf document.
+# Syntax is similar to doxygen's config file.
+
+RTF_EXTENSIONS_FILE    =
+
+#---------------------------------------------------------------------------
+# configuration options related to the man page output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_MAN tag is set to YES (the default) Doxygen will
+# generate man pages
+
+GENERATE_MAN           = NO
+
+# The MAN_OUTPUT tag is used to specify where the man pages will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be
+# put in front of it. If left blank `man' will be used as the default path.
+
+MAN_OUTPUT             = man
+
+# The MAN_EXTENSION tag determines the extension that is added to
+# the generated man pages (default is the subroutine's section .3)
+
+MAN_EXTENSION          = .3
+
+# If the MAN_LINKS tag is set to YES and Doxygen generates man output,
+# then it will generate one additional man file for each entity
+# documented in the real man page(s). These additional files
+# only source the real man page, but without them the man command
+# would be unable to find the correct page. The default is NO.
+
+MAN_LINKS              = NO
+
+#---------------------------------------------------------------------------
+# configuration options related to the XML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_XML tag is set to YES Doxygen will
+# generate an XML file that captures the structure of
+# the code including all documentation.
+
+GENERATE_XML           = NO
+
+# The XML_OUTPUT tag is used to specify where the XML pages will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be
+# put in front of it. If left blank `xml' will be used as the default path.
+
+XML_OUTPUT             = xml
+
+# The XML_SCHEMA tag can be used to specify an XML schema,
+# which can be used by a validating XML parser to check the
+# syntax of the XML files.
+
+XML_SCHEMA             =
+
+# The XML_DTD tag can be used to specify an XML DTD,
+# which can be used by a validating XML parser to check the
+# syntax of the XML files.
+
+XML_DTD                =
+
+# If the XML_PROGRAMLISTING tag is set to YES Doxygen will
+# dump the program listings (including syntax highlighting
+# and cross-referencing information) to the XML output. Note that
+# enabling this will significantly increase the size of the XML output.
+
+XML_PROGRAMLISTING     = YES
+
+#---------------------------------------------------------------------------
+# configuration options for the AutoGen Definitions output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_AUTOGEN_DEF tag is set to YES Doxygen will
+# generate an AutoGen Definitions (see autogen.sf.net) file
+# that captures the structure of the code including all
+# documentation. Note that this feature is still experimental
+# and incomplete at the moment.
+
+GENERATE_AUTOGEN_DEF   = NO
+
+#---------------------------------------------------------------------------
+# configuration options related to the Perl module output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_PERLMOD tag is set to YES Doxygen will
+# generate a Perl module file that captures the structure of
+# the code including all documentation. Note that this
+# feature is still experimental and incomplete at the
+# moment.
+
+GENERATE_PERLMOD       = NO
+
+# If the PERLMOD_LATEX tag is set to YES Doxygen will generate
+# the necessary Makefile rules, Perl scripts and LaTeX code to be able
+# to generate PDF and DVI output from the Perl module output.
+
+PERLMOD_LATEX          = NO
+
+# If the PERLMOD_PRETTY tag is set to YES the Perl module output will be
+# nicely formatted so it can be parsed by a human reader.
+# This is useful
+# if you want to understand what is going on.
+# On the other hand, if this
+# tag is set to NO the size of the Perl module output will be much smaller
+# and Perl will parse it just the same.
+
+PERLMOD_PRETTY         = YES
+
+# The names of the make variables in the generated doxyrules.make file
+# are prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX.
+# This is useful so different doxyrules.make files included by the same
+# Makefile don't overwrite each other's variables.
+
+PERLMOD_MAKEVAR_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the preprocessor
+#---------------------------------------------------------------------------
+
+# If the ENABLE_PREPROCESSING tag is set to YES (the default) Doxygen will
+# evaluate all C-preprocessor directives found in the sources and include
+# files.
+
+ENABLE_PREPROCESSING   = YES
+
+# If the MACRO_EXPANSION tag is set to YES Doxygen will expand all macro
+# names in the source code. If set to NO (the default) only conditional
+# compilation will be performed. Macro expansion can be done in a controlled
+# way by setting EXPAND_ONLY_PREDEF to YES.
+
+MACRO_EXPANSION        = NO
+
+# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES
+# then the macro expansion is limited to the macros specified with the
+# PREDEFINED and EXPAND_AS_DEFINED tags.
+
+EXPAND_ONLY_PREDEF     = NO
+
+# If the SEARCH_INCLUDES tag is set to YES (the default) the includes files
+# in the INCLUDE_PATH (see below) will be search if a #include is found.
+
+SEARCH_INCLUDES        = YES
+
+# The INCLUDE_PATH tag can be used to specify one or more directories that
+# contain include files that are not input files but should be processed by
+# the preprocessor.
+
+INCLUDE_PATH           =
+
+# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
+# patterns (like *.h and *.hpp) to filter out the header-files in the
+# directories. If left blank, the patterns specified with FILE_PATTERNS will
+# be used.
+
+INCLUDE_FILE_PATTERNS  =
+
+# The PREDEFINED tag can be used to specify one or more macro names that
+# are defined before the preprocessor is started (similar to the -D option of
+# gcc). The argument of the tag is a list of macros of the form: name
+# or name=definition (no spaces). If the definition and the = are
+# omitted =1 is assumed. To prevent a macro definition from being
+# undefined via #undef or recursively expanded use the := operator
+# instead of the = operator.
+
+PREDEFINED             =
+
+# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then
+# this tag can be used to specify a list of macro names that should be expanded.
+# The macro definition that is found in the sources will be used.
+# Use the PREDEFINED tag if you want to use a different macro definition.
+
+EXPAND_AS_DEFINED      =
+
+# If the SKIP_FUNCTION_MACROS tag is set to YES (the default) then
+# doxygen's preprocessor will remove all function-like macros that are alone
+# on a line, have an all uppercase name, and do not end with a semicolon. Such
+# function macros are typically used for boiler-plate code, and will confuse
+# the parser if not removed.
+
+SKIP_FUNCTION_MACROS   = YES
+
+#---------------------------------------------------------------------------
+# Configuration::additions related to external references
+#---------------------------------------------------------------------------
+
+# The TAGFILES option can be used to specify one or more tagfiles.
+# Optionally an initial location of the external documentation
+# can be added for each tagfile. The format of a tag file without
+# this location is as follows:
+#
+# TAGFILES = file1 file2 ...
+# Adding location for the tag files is done as follows:
+#
+# TAGFILES = file1=loc1 "file2 = loc2" ...
+# where "loc1" and "loc2" can be relative or absolute paths or
+# URLs. If a location is present for each tag, the installdox tool
+# does not have to be run to correct the links.
+# Note that each tag file must have a unique name
+# (where the name does NOT include the path)
+# If a tag file is not located in the directory in which doxygen
+# is run, you must also specify the path to the tagfile here.
+
+TAGFILES               =
+
+# When a file name is specified after GENERATE_TAGFILE, doxygen will create
+# a tag file that is based on the input files it reads.
+
+GENERATE_TAGFILE       =
+
+# If the ALLEXTERNALS tag is set to YES all external classes will be listed
+# in the class index. If set to NO only the inherited external classes
+# will be listed.
+
+ALLEXTERNALS           = NO
+
+# If the EXTERNAL_GROUPS tag is set to YES all external groups will be listed
+# in the modules index. If set to NO, only the current project's groups will
+# be listed.
+
+EXTERNAL_GROUPS        = YES
+
+# The PERL_PATH should be the absolute path and name of the perl script
+# interpreter (i.e. the result of `which perl').
+
+PERL_PATH              = /usr/bin/perl
+
+#---------------------------------------------------------------------------
+# Configuration options related to the dot tool
+#---------------------------------------------------------------------------
+
+# If the CLASS_DIAGRAMS tag is set to YES (the default) Doxygen will
+# generate a inheritance diagram (in HTML, RTF and LaTeX) for classes with base
+# or super classes. Setting the tag to NO turns the diagrams off. Note that
+# this option is superseded by the HAVE_DOT option below. This is only a
+# fallback. It is recommended to install and use dot, since it yields more
+# powerful graphs.
+
+CLASS_DIAGRAMS         = YES
+
+# You can define message sequence charts within doxygen comments using the \msc
+# command. Doxygen will then run the mscgen tool (see
+# http://www.mcternan.me.uk/mscgen/) to produce the chart and insert it in the
+# documentation. The MSCGEN_PATH tag allows you to specify the directory where
+# the mscgen tool resides. If left empty the tool is assumed to be found in the
+# default search path.
+
+MSCGEN_PATH            =
+
+# If set to YES, the inheritance and collaboration graphs will hide
+# inheritance and usage relations if the target is undocumented
+# or is not a class.
+
+HIDE_UNDOC_RELATIONS   = YES
+
+# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is
+# available from the path. This tool is part of Graphviz, a graph visualization
+# toolkit from AT&T and Lucent Bell Labs. The other options in this section
+# have no effect if this option is set to NO (the default)
+
+HAVE_DOT               = NO
+
+# By default doxygen will write a font called FreeSans.ttf to the output
+# directory and reference it in all dot files that doxygen generates. This
+# font does not include all possible unicode characters however, so when you need
+# these (or just want a differently looking font) you can specify the font name
+# using DOT_FONTNAME. You need need to make sure dot is able to find the font,
+# which can be done by putting it in a standard location or by setting the
+# DOTFONTPATH environment variable or by setting DOT_FONTPATH to the directory
+# containing the font.
+
+DOT_FONTNAME           = FreeSans
+
+# The DOT_FONTSIZE tag can be used to set the size of the font of dot graphs.
+# The default size is 10pt.
+
+DOT_FONTSIZE           = 10
+
+# By default doxygen will tell dot to use the output directory to look for the
+# FreeSans.ttf font (which doxygen will put there itself). If you specify a
+# different font using DOT_FONTNAME you can set the path where dot
+# can find it using this tag.
+
+DOT_FONTPATH           =
+
+# If the CLASS_GRAPH and HAVE_DOT tags are set to YES then doxygen
+# will generate a graph for each documented class showing the direct and
+# indirect inheritance relations. Setting this tag to YES will force the
+# the CLASS_DIAGRAMS tag to NO.
+
+CLASS_GRAPH            = YES
+
+# If the COLLABORATION_GRAPH and HAVE_DOT tags are set to YES then doxygen
+# will generate a graph for each documented class showing the direct and
+# indirect implementation dependencies (inheritance, containment, and
+# class references variables) of the class with other documented classes.
+
+COLLABORATION_GRAPH    = YES
+
+# If the GROUP_GRAPHS and HAVE_DOT tags are set to YES then doxygen
+# will generate a graph for groups, showing the direct groups dependencies
+
+GROUP_GRAPHS           = YES
+
+# If the UML_LOOK tag is set to YES doxygen will generate inheritance and
+# collaboration diagrams in a style similar to the OMG's Unified Modeling
+# Language.
+
+UML_LOOK               = NO
+
+# If set to YES, the inheritance and collaboration graphs will show the
+# relations between templates and their instances.
+
+TEMPLATE_RELATIONS     = NO
+
+# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDE_GRAPH, and HAVE_DOT
+# tags are set to YES then doxygen will generate a graph for each documented
+# file showing the direct and indirect include dependencies of the file with
+# other documented files.
+
+INCLUDE_GRAPH          = YES
+
+# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDED_BY_GRAPH, and
+# HAVE_DOT tags are set to YES then doxygen will generate a graph for each
+# documented header file showing the documented files that directly or
+# indirectly include this file.
+
+INCLUDED_BY_GRAPH      = YES
+
+# If the CALL_GRAPH and HAVE_DOT options are set to YES then
+# doxygen will generate a call dependency graph for every global function
+# or class method. Note that enabling this option will significantly increase
+# the time of a run. So in most cases it will be better to enable call graphs
+# for selected functions only using the \callgraph command.
+
+CALL_GRAPH             = NO
+
+# If the CALLER_GRAPH and HAVE_DOT tags are set to YES then
+# doxygen will generate a caller dependency graph for every global function
+# or class method. Note that enabling this option will significantly increase
+# the time of a run. So in most cases it will be better to enable caller
+# graphs for selected functions only using the \callergraph command.
+
+CALLER_GRAPH           = NO
+
+# If the GRAPHICAL_HIERARCHY and HAVE_DOT tags are set to YES then doxygen
+# will graphical hierarchy of all classes instead of a textual one.
+
+GRAPHICAL_HIERARCHY    = YES
+
+# If the DIRECTORY_GRAPH, SHOW_DIRECTORIES and HAVE_DOT tags are set to YES
+# then doxygen will show the dependencies a directory has on other directories
+# in a graphical way. The dependency relations are determined by the #include
+# relations between the files in the directories.
+
+DIRECTORY_GRAPH        = YES
+
+# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images
+# generated by dot. Possible values are png, jpg, or gif
+# If left blank png will be used.
+
+DOT_IMAGE_FORMAT       = png
+
+# The tag DOT_PATH can be used to specify the path where the dot tool can be
+# found. If left blank, it is assumed the dot tool can be found in the path.
+
+DOT_PATH               =
+
+# The DOTFILE_DIRS tag can be used to specify one or more directories that
+# contain dot files that are included in the documentation (see the
+# \dotfile command).
+
+DOTFILE_DIRS           =
+
+# The DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of
+# nodes that will be shown in the graph. If the number of nodes in a graph
+# becomes larger than this value, doxygen will truncate the graph, which is
+# visualized by representing a node as a red box. Note that doxygen if the
+# number of direct children of the root node in a graph is already larger than
+# DOT_GRAPH_MAX_NODES then the graph will not be shown at all. Also note
+# that the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH.
+
+DOT_GRAPH_MAX_NODES    = 50
+
+# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the
+# graphs generated by dot. A depth value of 3 means that only nodes reachable
+# from the root by following a path via at most 3 edges will be shown. Nodes
+# that lay further from the root node will be omitted. Note that setting this
+# option to 1 or 2 may greatly reduce the computation time needed for large
+# code bases. Also note that the size of a graph can be further restricted by
+# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction.
+
+MAX_DOT_GRAPH_DEPTH    = 0
+
+# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent
+# background. This is disabled by default, because dot on Windows does not
+# seem to support this out of the box. Warning: Depending on the platform used,
+# enabling this option may lead to badly anti-aliased labels on the edges of
+# a graph (i.e. they become hard to read).
+
+DOT_TRANSPARENT        = NO
+
+# Set the DOT_MULTI_TARGETS tag to YES allow dot to generate multiple output
+# files in one run (i.e. multiple -o and -T options on the command line). This
+# makes dot run faster, but since only newer versions of dot (>1.8.10)
+# support this, this feature is disabled by default.
+
+DOT_MULTI_TARGETS      = NO
+
+# If the GENERATE_LEGEND tag is set to YES (the default) Doxygen will
+# generate a legend page explaining the meaning of the various boxes and
+# arrows in the dot generated graphs.
+
+GENERATE_LEGEND        = YES
+
+# If the DOT_CLEANUP tag is set to YES (the default) Doxygen will
+# remove the intermediate dot files that are used to generate
+# the various graphs.
+
+DOT_CLEANUP            = YES

kenlm/GIT_REVISION

@@ -0,0 +1 @@
+b32c19389737a5def8bbc4623de809ced3091187

kenlm/LICENSE

@@ -0,0 +1,25 @@
+Most of the code here is licensed under the LGPL.  There are exceptions that
+have their own licenses, listed below.  See comments in those files for more
+details.  
+
+util/getopt.* is getopt for Windows
+util/murmur_hash.cc
+util/string_piece.hh and util/string_piece.cc
+util/double-conversion/LICENSE covers util/double-conversion except the build files
+util/file.cc contains a modified implementation of mkstemp under the LGPL
+util/integer_to_string.* is BSD
+
+For the rest:
+
+    KenLM is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Lesser General Public License as published
+    by the Free Software Foundation, either version 2.1 of the License, or
+    (at your option) any later version.
+
+    KenLM is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public License 2.1
+    along with KenLM code.  If not, see <http://www.gnu.org/licenses/lgpl-2.1.html>.

kenlm/MANIFEST.in

@@ -0,0 +1,9 @@
+# file GENERATED by distutils, do NOT edit
+include setup.py
+include lm/*.cc
+include lm/*.hh
+include python/*.cpp
+include util/*.cc
+include util/*.hh
+include util/double-conversion/*.cc
+include util/double-conversion/*.h

kenlm/README.md

@@ -0,0 +1,102 @@
+# kenlm
+
+Language model inference code by Kenneth Heafield (kenlm at kheafield.com)
+
+The website https://kheafield.com/code/kenlm/ has more documentation.  If you're a decoder developer, please download the latest version from there instead of copying from another decoder.
+
+## Compiling
+Use cmake, see [BUILDING](BUILDING) for build dependencies and more detail.
+```bash
+mkdir -p build
+cd build
+cmake ..
+make -j 4
+```
+
+## Compiling with your own build system
+If you want to compile with your own build system (Makefile etc) or to use as a library, there are a number of macros you can set on the g++ command line or in util/have.hh .  
+
+* `KENLM_MAX_ORDER` is the maximum order that can be loaded.  This is done to make state an efficient POD rather than a vector.  
+* `HAVE_ICU` If your code links against ICU, define this to disable the internal StringPiece and replace it with ICU's copy of StringPiece, avoiding naming conflicts.  
+
+ARPA files can be read in compressed format with these options:
+* `HAVE_ZLIB` Supports gzip.  Link with -lz.
+* `HAVE_BZLIB` Supports bzip2.  Link with -lbz2.
+* `HAVE_XZLIB` Supports xz.  Link with -llzma.
+
+Note that these macros impact only `read_compressed.cc` and `read_compressed_test.cc`.  The bjam build system will auto-detect bzip2 and xz support.  
+
+## Estimation
+lmplz estimates unpruned language models with modified Kneser-Ney smoothing.  After compiling with bjam, run
+```bash
+bin/lmplz -o 5 <text >text.arpa
+```
+The algorithm is on-disk, using an amount of memory that you specify.  See https://kheafield.com/code/kenlm/estimation/ for more.
+
+MT Marathon 2012 team members Ivan Pouzyrevsky and Mohammed Mediani contributed to the computation design and early implementation. Jon Clark contributed to the design, clarified points about smoothing, and added logging. 
+
+## Filtering
+
+filter takes an ARPA or count file and removes entries that will never be queried.  The filter criterion can be corpus-level vocabulary, sentence-level vocabulary, or sentence-level phrases.  Run
+```bash
+bin/filter
+```
+and see https://kheafield.com/code/kenlm/filter/ for more documentation.
+
+## Querying
+
+Two data structures are supported: probing and trie.  Probing is a probing hash table with keys that are 64-bit hashes of n-grams and floats as values.  Trie is a fairly standard trie but with bit-level packing so it uses the minimum number of bits to store word indices and pointers.  The trie node entries are sorted by word index.  Probing is the fastest and uses the most memory.  Trie uses the least memory and is a bit slower.
+
+As is the custom in language modeling, all probabilities are log base 10.
+
+With trie, resident memory is 58% of IRST's smallest version and 21% of SRI's compact version.  Simultaneously, trie CPU's use is 81% of IRST's fastest version and 84% of SRI's fast version.  KenLM's probing hash table implementation goes even faster at the expense of using more memory.  See https://kheafield.com/code/kenlm/benchmark/.
+
+Binary format via mmap is supported.  Run `./build_binary` to make one then pass the binary file name to the appropriate Model constructor.   
+
+## Platforms
+`murmur_hash.cc` and `bit_packing.hh` perform unaligned reads and writes that make the code architecture-dependent.  
+It has been sucessfully tested on x86\_64, x86, and PPC64.  
+ARM support is reportedly working, at least on the iphone.   
+
+Runs on Linux, OS X, Cygwin, and MinGW.  
+
+Hideo Okuma and Tomoyuki Yoshimura from NICT contributed ports to ARM and MinGW.  
+
+## Decoder developers
+- I recommend copying the code and distributing it with your decoder.  However, please send improvements upstream.  
+
+- It's possible to compile the query-only code without Boost, but useful things like estimating models require Boost.
+
+- Select the macros you want, listed in the previous section.  
+
+- There are two build systems: compile.sh and cmake.  They're pretty simple and are intended to be reimplemented in your build system.  
+
+- Use either the interface in `lm/model.hh` or `lm/virtual_interface.hh`.  Interface documentation is in comments of `lm/virtual_interface.hh` and `lm/model.hh`.  
+
+- There are several possible data structures in `model.hh`.  Use `RecognizeBinary` in `binary_format.hh` to determine which one a user has provided.  You probably already implement feature functions as an abstract virtual base class with several children.  I suggest you co-opt this existing virtual dispatch by templatizing the language model feature implementation on the KenLM model identified by `RecognizeBinary`.  This is the strategy used in Moses and cdec.
+
+- See `lm/config.hh` for run-time tuning options.
+
+## Contributors
+Contributions to KenLM are welcome.  Please base your contributions on https://github.com/kpu/kenlm and send pull requests (or I might give you commit access).  Downstream copies in Moses and cdec are maintained by overwriting them so do not make changes there.  
+
+## Python module
+Contributed by Victor Chahuneau.
+
+### Installation
+
+```bash
+pip install https://github.com/kpu/kenlm/archive/master.zip
+```
+
+### Basic Usage
+```python
+import kenlm
+model = kenlm.Model('lm/test.arpa')
+print(model.score('this is a sentence .', bos = True, eos = True))
+```
+See [python/example.py](python/example.py) and [python/kenlm.pyx](python/kenlm.pyx) for more, including stateful APIs.  
+
+---
+
+The name was Hieu Hoang's idea, not mine.

kenlm/clean_query_only.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+rm -rf {lm,util,util/double-conversion}/*.o bin/{query,build_binary}

kenlm/cmake/KenLMFunctions.cmake

@@ -0,0 +1,81 @@
+# Helper functions used across the CMake build system
+
+include(CMakeParseArguments)
+
+# Adds a bunch of executables to the build, each depending on the specified
+# dependent object files and linking against the specified libraries
+function(AddExes)
+  set(multiValueArgs EXES DEPENDS LIBRARIES)
+  cmake_parse_arguments(AddExes "" "" "${multiValueArgs}" ${ARGN})
+
+  # Iterate through the executable list
+  foreach(exe ${AddExes_EXES})
+
+    # Compile the executable, linking against the requisite dependent object files
+    add_executable(${exe} ${exe}_main.cc ${AddExes_DEPENDS})
+
+    # Link the executable against the supplied libraries
+    target_link_libraries(${exe} ${AddExes_LIBRARIES})
+
+    # Group executables together
+    set_target_properties(${exe} PROPERTIES FOLDER executables)
+
+  # End for loop
+  endforeach(exe)
+
+  # Install the executable files
+  install(TARGETS ${AddExes_EXES} DESTINATION bin)
+endfunction()
+
+# Adds a single test to the build, depending on the specified dependent
+# object files, linking against the specified libraries, and with the
+# specified command line arguments
+function(KenLMAddTest)
+  cmake_parse_arguments(KenLMAddTest "" "TEST"
+                        "DEPENDS;LIBRARIES;TEST_ARGS" ${ARGN})
+
+  # Compile the executable, linking against the requisite dependent object files
+  add_executable(${KenLMAddTest_TEST}
+                 ${KenLMAddTest_TEST}.cc
+                 ${KenLMAddTest_DEPENDS})
+
+  if (Boost_USE_STATIC_LIBS)
+    set(DYNLINK_FLAGS)
+  else()
+    set(DYNLINK_FLAGS COMPILE_FLAGS -DBOOST_TEST_DYN_LINK)
+  endif()
+
+  # Require the following compile flag
+  set_target_properties(${KenLMAddTest_TEST} PROPERTIES
+                        ${DYNLINK_FLAGS}
+                        RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/tests)
+
+  target_link_libraries(${KenLMAddTest_TEST} ${KenLMAddTest_LIBRARIES} ${TIMER_LINK})
+
+  set(test_params "")
+  if(KenLMAddTest_TEST_ARGS)
+    set(test_params ${KenLMAddTest_TEST_ARGS})
+  endif()
+
+  # Specify command arguments for how to run each unit test
+  add_test(NAME ${KenLMAddTest_TEST}
+           COMMAND ${KenLMAddTest_TEST} ${test_params})
+
+  # Group unit tests together
+  set_target_properties(${KenLMAddTest_TEST} PROPERTIES FOLDER "unit_tests")
+endfunction()
+
+# Adds a bunch of tests to the build, each depending on the specified
+# dependent object files and linking against the specified libraries
+function(AddTests)
+  set(multiValueArgs TESTS DEPENDS LIBRARIES TEST_ARGS)
+  cmake_parse_arguments(AddTests "" "" "${multiValueArgs}" ${ARGN})
+
+  # Iterate through the Boost tests list
+  foreach(test ${AddTests_TESTS})
+    KenLMAddTest(TEST ${test}
+                 DEPENDS ${AddTests_DEPENDS}
+                 LIBRARIES ${AddTests_LIBRARIES}
+                 TEST_ARGS ${AddTests_TEST_ARGS})
+  endforeach(test)
+endfunction()

kenlm/cmake/kenlmConfig.cmake.in

@@ -0,0 +1,19 @@
+@PACKAGE_INIT@
+
+include(CMakeFindDependencyMacro)
+
+find_dependency(Boost)
+find_dependency(Threads)
+
+# Compression libs
+if (@ZLIB_FOUND@)
+  find_dependency(ZLIB)
+endif()
+if (@BZIP2_FOUND@)
+  find_dependency(BZip2)
+endif()
+if (@LIBLZMA_FOUND@)
+  find_dependency(LibLZMA)
+endif()
+
+include("${CMAKE_CURRENT_LIST_DIR}/kenlmTargets.cmake")

kenlm/cmake/modules/FindEigen3.cmake

@@ -0,0 +1,90 @@
+# - Try to find Eigen3 lib
+#
+# This module supports requiring a minimum version, e.g. you can do
+#   find_package(Eigen3 3.1.2)
+# to require version 3.1.2 or newer of Eigen3.
+#
+# Once done this will define
+#
+#  EIGEN3_FOUND - system has eigen lib with correct version
+#  EIGEN3_INCLUDE_DIR - the eigen include directory
+#  EIGEN3_VERSION - eigen version
+#
+# This module reads hints about search locations from 
+# the following enviroment variables:
+#
+# EIGEN3_ROOT
+# EIGEN3_ROOT_DIR
+
+# Copyright (c) 2006, 2007 Montel Laurent, <montel@kde.org>
+# Copyright (c) 2008, 2009 Gael Guennebaud, <g.gael@free.fr>
+# Copyright (c) 2009 Benoit Jacob <jacob.benoit.1@gmail.com>
+# Redistribution and use is allowed according to the terms of the 2-clause BSD license.
+
+if(NOT Eigen3_FIND_VERSION)
+  if(NOT Eigen3_FIND_VERSION_MAJOR)
+    set(Eigen3_FIND_VERSION_MAJOR 2)
+  endif(NOT Eigen3_FIND_VERSION_MAJOR)
+  if(NOT Eigen3_FIND_VERSION_MINOR)
+    set(Eigen3_FIND_VERSION_MINOR 91)
+  endif(NOT Eigen3_FIND_VERSION_MINOR)
+  if(NOT Eigen3_FIND_VERSION_PATCH)
+    set(Eigen3_FIND_VERSION_PATCH 0)
+  endif(NOT Eigen3_FIND_VERSION_PATCH)
+
+  set(Eigen3_FIND_VERSION "${Eigen3_FIND_VERSION_MAJOR}.${Eigen3_FIND_VERSION_MINOR}.${Eigen3_FIND_VERSION_PATCH}")
+endif(NOT Eigen3_FIND_VERSION)
+
+macro(_eigen3_check_version)
+  file(READ "${EIGEN3_INCLUDE_DIR}/Eigen/src/Core/util/Macros.h" _eigen3_version_header)
+
+  string(REGEX MATCH "define[ \t]+EIGEN_WORLD_VERSION[ \t]+([0-9]+)" _eigen3_world_version_match "${_eigen3_version_header}")
+  set(EIGEN3_WORLD_VERSION "${CMAKE_MATCH_1}")
+  string(REGEX MATCH "define[ \t]+EIGEN_MAJOR_VERSION[ \t]+([0-9]+)" _eigen3_major_version_match "${_eigen3_version_header}")
+  set(EIGEN3_MAJOR_VERSION "${CMAKE_MATCH_1}")
+  string(REGEX MATCH "define[ \t]+EIGEN_MINOR_VERSION[ \t]+([0-9]+)" _eigen3_minor_version_match "${_eigen3_version_header}")
+  set(EIGEN3_MINOR_VERSION "${CMAKE_MATCH_1}")
+
+  set(EIGEN3_VERSION ${EIGEN3_WORLD_VERSION}.${EIGEN3_MAJOR_VERSION}.${EIGEN3_MINOR_VERSION})
+  if(${EIGEN3_VERSION} VERSION_LESS ${Eigen3_FIND_VERSION})
+    set(EIGEN3_VERSION_OK FALSE)
+  else(${EIGEN3_VERSION} VERSION_LESS ${Eigen3_FIND_VERSION})
+    set(EIGEN3_VERSION_OK TRUE)
+  endif(${EIGEN3_VERSION} VERSION_LESS ${Eigen3_FIND_VERSION})
+
+  if(NOT EIGEN3_VERSION_OK)
+
+    message(STATUS "Eigen3 version ${EIGEN3_VERSION} found in ${EIGEN3_INCLUDE_DIR}, "
+                   "but at least version ${Eigen3_FIND_VERSION} is required")
+  endif(NOT EIGEN3_VERSION_OK)
+endmacro(_eigen3_check_version)
+
+if (EIGEN3_INCLUDE_DIR)
+
+  # in cache already
+  _eigen3_check_version()
+  set(EIGEN3_FOUND ${EIGEN3_VERSION_OK})
+
+else (EIGEN3_INCLUDE_DIR)
+
+  find_path(EIGEN3_INCLUDE_DIR NAMES signature_of_eigen3_matrix_library
+      HINTS
+      ENV EIGEN3_ROOT 
+      ENV EIGEN3_ROOT_DIR
+      PATHS
+      ${CMAKE_INSTALL_PREFIX}/include
+      ${KDE4_INCLUDE_DIR}
+      PATH_SUFFIXES eigen3 eigen
+    )
+
+  if(EIGEN3_INCLUDE_DIR)
+    _eigen3_check_version()
+  endif(EIGEN3_INCLUDE_DIR)
+
+  include(FindPackageHandleStandardArgs)
+  find_package_handle_standard_args(Eigen3 DEFAULT_MSG EIGEN3_INCLUDE_DIR EIGEN3_VERSION_OK)
+
+  mark_as_advanced(EIGEN3_INCLUDE_DIR)
+
+endif(EIGEN3_INCLUDE_DIR)
+

kenlm/compile_query_only.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+#This is just an example compilation.  You should integrate these files into your build system.  Boost jam is provided and preferred.
+
+echo You must use ./bjam if you want language model estimation, filtering, or support for compressed files \(.gz, .bz2, .xz\) 1>&2
+
+rm {lm,util}/*.o 2>/dev/null
+set -e
+
+CXX=${CXX:-g++}
+
+CXXFLAGS+=" -I. -O3 -DNDEBUG -DKENLM_MAX_ORDER=6"
+
+#If this fails for you, consider using bjam.
+if [ ${#NPLM} != 0 ]; then
+  CXXFLAGS+=" -DHAVE_NPLM -lneuralLM -L$NPLM/src -I$NPLM/src -lboost_thread-mt -fopenmp"
+  ADDED_PATHS="lm/wrappers/*.cc"
+fi
+echo 'Compiling with '$CXX $CXXFLAGS
+
+#Grab all cc files in these directories except those ending in test.cc or main.cc
+objects=""
+for i in util/double-conversion/*.cc util/*.cc lm/*.cc $ADDED_PATHS; do
+  if [ "${i%test.cc}" == "$i" ] && [ "${i%main.cc}" == "$i" ]; then
+    $CXX $CXXFLAGS -c $i -o ${i%.cc}.o
+    objects="$objects ${i%.cc}.o"
+  fi
+done
+
+mkdir -p bin
+if [ "$(uname)" != Darwin ]; then
+  CXXFLAGS="$CXXFLAGS -lrt"
+fi
+$CXX lm/build_binary_main.cc $objects -o bin/build_binary $CXXFLAGS $LDFLAGS
+$CXX lm/query_main.cc $objects -o bin/query $CXXFLAGS $LDFLAGS

kenlm/include/lm/bhiksha.hh

@@ -0,0 +1,123 @@
+/* Simple implementation of
+ * @inproceedings{bhikshacompression,
+ *  author={Bhiksha Raj and Ed Whittaker},
+ *  year={2003},
+ *  title={Lossless Compression of Language Model Structure and Word Identifiers},
+ *  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing},
+ *  pages={388--391},
+ *  }
+ *
+ *  Currently only used for next pointers.  
+ */
+
+#ifndef LM_BHIKSHA_H
+#define LM_BHIKSHA_H
+
+#include "lm/model_type.hh"
+#include "lm/trie.hh"
+#include "util/bit_packing.hh"
+#include "util/sorted_uniform.hh"
+
+#include <algorithm>
+
+#include <stdint.h>
+#include <assert.h>
+
+namespace lm {
+namespace ngram {
+struct Config;
+class BinaryFormat;
+
+namespace trie {
+
+class DontBhiksha {
+  public:
+    static const ModelType kModelTypeAdd = static_cast<ModelType>(0);
+
+    static void UpdateConfigFromBinary(const BinaryFormat &, uint64_t, Config &/*config*/) {}
+
+    static uint64_t Size(uint64_t /*max_offset*/, uint64_t /*max_next*/, const Config &/*config*/) { return 0; }
+
+    static uint8_t InlineBits(uint64_t /*max_offset*/, uint64_t max_next, const Config &/*config*/) {
+      return util::RequiredBits(max_next);
+    }
+
+    DontBhiksha(const void *base, uint64_t max_offset, uint64_t max_next, const Config &config);
+
+    void ReadNext(const void *base, uint64_t bit_offset, uint64_t /*index*/, uint8_t total_bits, NodeRange &out) const {
+      out.begin = util::ReadInt57(base, bit_offset, next_.bits, next_.mask);
+      out.end = util::ReadInt57(base, bit_offset + total_bits, next_.bits, next_.mask);
+      //assert(out.end >= out.begin);
+    }
+
+    void WriteNext(void *base, uint64_t bit_offset, uint64_t /*index*/, uint64_t value) {
+      util::WriteInt57(base, bit_offset, next_.bits, value);
+    }
+
+    void FinishedLoading(const Config &/*config*/) {}
+
+    uint8_t InlineBits() const { return next_.bits; }
+
+  private:
+    util::BitsMask next_;
+};
+
+class ArrayBhiksha {
+  public:
+    static const ModelType kModelTypeAdd = kArrayAdd;
+
+    static void UpdateConfigFromBinary(const BinaryFormat &file, uint64_t offset, Config &config);
+
+    static uint64_t Size(uint64_t max_offset, uint64_t max_next, const Config &config);
+
+    static uint8_t InlineBits(uint64_t max_offset, uint64_t max_next, const Config &config);
+
+    ArrayBhiksha(void *base, uint64_t max_offset, uint64_t max_value, const Config &config);
+
+    void ReadNext(const void *base, uint64_t bit_offset, uint64_t index, uint8_t total_bits, NodeRange &out) const {
+      // Some assertions are commented out because they are expensive.
+      // assert(*offset_begin_ == 0);
+      // std::upper_bound returns the first element that is greater.  Want the
+      // last element that is <= to the index.
+      const uint64_t *begin_it = std::upper_bound(offset_begin_, offset_end_, index) - 1;
+      // Since *offset_begin_ == 0, the position should be in range.
+      // assert(begin_it >= offset_begin_);
+      const uint64_t *end_it;
+      for (end_it = begin_it + 1; (end_it < offset_end_) && (*end_it <= index + 1); ++end_it) {}
+      // assert(end_it == std::upper_bound(offset_begin_, offset_end_, index + 1));
+      --end_it;
+      // assert(end_it >= begin_it);
+      out.begin = ((begin_it - offset_begin_) << next_inline_.bits) | 
+        util::ReadInt57(base, bit_offset, next_inline_.bits, next_inline_.mask);
+      out.end = ((end_it - offset_begin_) << next_inline_.bits) | 
+        util::ReadInt57(base, bit_offset + total_bits, next_inline_.bits, next_inline_.mask);
+      // If this fails, consider rebuilding your model using KenLM after 1e333d786b748555e8f368d2bbba29a016c98052
+      assert(out.end >= out.begin);
+    }
+
+    void WriteNext(void *base, uint64_t bit_offset, uint64_t index, uint64_t value) {
+      uint64_t encode = value >> next_inline_.bits;
+      for (; write_to_ <= offset_begin_ + encode; ++write_to_) *write_to_ = index;
+      util::WriteInt57(base, bit_offset, next_inline_.bits, value & next_inline_.mask);
+    }
+
+    void FinishedLoading(const Config &config);
+
+    uint8_t InlineBits() const { return next_inline_.bits; }
+
+  private:
+    const util::BitsMask next_inline_;
+
+    const uint64_t *const offset_begin_;
+    const uint64_t *const offset_end_;
+
+    uint64_t *write_to_;
+
+    void *original_base_;
+};
+
+} // namespace trie
+} // namespace ngram
+} // namespace lm
+
+#endif // LM_BHIKSHA_H

kenlm/include/lm/binary_format.hh

@@ -0,0 +1,106 @@
+#ifndef LM_BINARY_FORMAT_H
+#define LM_BINARY_FORMAT_H
+
+#include "lm/config.hh"
+#include "lm/model_type.hh"
+#include "lm/read_arpa.hh"
+
+#include "util/file_piece.hh"
+#include "util/mmap.hh"
+#include "util/scoped.hh"
+
+#include <cstddef>
+#include <vector>
+
+#include <stdint.h>
+
+namespace lm {
+namespace ngram {
+
+extern const char *kModelNames[6];
+
+/*Inspect a file to determine if it is a binary lm.  If not, return false.  
+ * If so, return true and set recognized to the type.  This is the only API in
+ * this header designed for use by decoder authors.  
+ */
+bool RecognizeBinary(const char *file, ModelType &recognized);
+
+struct FixedWidthParameters {
+  unsigned char order;
+  float probing_multiplier;
+  // What type of model is this?  
+  ModelType model_type;
+  // Does the end of the file have the actual strings in the vocabulary?   
+  bool has_vocabulary;
+  unsigned int search_version;
+};
+
+// This is a macro instead of an inline function so constants can be assigned using it.
+#define ALIGN8(a) ((std::ptrdiff_t(((a)-1)/8)+1)*8)
+
+// Parameters stored in the header of a binary file.  
+struct Parameters {
+  FixedWidthParameters fixed;
+  std::vector<uint64_t> counts;
+};
+
+class BinaryFormat {
+  public:
+    explicit BinaryFormat(const Config &config);
+
+    // Reading a binary file:
+    // Takes ownership of fd
+    void InitializeBinary(int fd, ModelType model_type, unsigned int search_version, Parameters &params);
+    // Used to read parts of the file to update the config object before figuring out full size.
+    void ReadForConfig(void *to, std::size_t amount, uint64_t offset_excluding_header) const;
+    // Actually load the binary file and return a pointer to the beginning of the search area.
+    void *LoadBinary(std::size_t size);
+
+    uint64_t VocabStringReadingOffset() const {
+      assert(vocab_string_offset_ != kInvalidOffset);
+      return vocab_string_offset_;
+    }
+
+    // Writing a binary file or initializing in RAM from ARPA:
+    // Size for vocabulary.
+    void *SetupJustVocab(std::size_t memory_size, uint8_t order);
+    // Warning: can change the vocaulary base pointer.
+    void *GrowForSearch(std::size_t memory_size, std::size_t vocab_pad, void *&vocab_base);
+    // Warning: can change vocabulary and search base addresses.
+    void WriteVocabWords(const std::string &buffer, void *&vocab_base, void *&search_base);
+    // Write the header at the beginning of the file.
+    void FinishFile(const Config &config, ModelType model_type, unsigned int search_version, const std::vector<uint64_t> &counts);
+
+  private:
+    void MapFile(void *&vocab_base, void *&search_base);
+
+    // Copied from configuration.
+    const Config::WriteMethod write_method_;
+    const char *write_mmap_;
+    util::LoadMethod load_method_;
+
+    // File behind memory, if any.  
+    util::scoped_fd file_;
+
+    // If there is a file involved, a single mapping.
+    util::scoped_memory mapping_;
+
+    // If the data is only in memory, separately allocate each because the trie
+    // knows vocab's size before it knows search's size (because SRILM might
+    // have pruned).
+    util::scoped_memory memory_vocab_, memory_search_;
+
+    // Memory ranges.  Note that these may not be contiguous and may not all
+    // exist.
+    std::size_t header_size_, vocab_size_, vocab_pad_;
+    // aka end of search.
+    uint64_t vocab_string_offset_;
+
+    static const uint64_t kInvalidOffset = (uint64_t)-1;
+};
+
+bool IsBinaryFormat(int fd);
+
+} // namespace ngram
+} // namespace lm
+#endif // LM_BINARY_FORMAT_H

kenlm/include/lm/blank.hh

@@ -0,0 +1,43 @@
+#ifndef LM_BLANK_H
+#define LM_BLANK_H
+
+#include <limits>
+
+#include <stdint.h>
+#include <math.h>
+
+namespace lm {
+namespace ngram {
+
+/* Suppose "foo bar" appears with zero backoff but there is no trigram
+ * beginning with these words.  Then, when scoring "foo bar", the model could
+ * return out_state containing "bar" or even null context if "bar" also has no
+ * backoff and is never followed by another word.  Then the backoff is set to
+ * kNoExtensionBackoff.  If the n-gram might be extended, then out_state must
+ * contain the full n-gram, in which case kExtensionBackoff is set.  In any
+ * case, if an n-gram has non-zero backoff, the full state is returned so
+ * backoff can be properly charged.  
+ * These differ only in sign bit because the backoff is in fact zero in either
+ * case.   
+ */
+const float kNoExtensionBackoff = -0.0;
+const float kExtensionBackoff = 0.0;
+const uint64_t kNoExtensionQuant = 0;
+const uint64_t kExtensionQuant = 1;
+
+inline void SetExtension(float &backoff) {
+  if (backoff == kNoExtensionBackoff) backoff = kExtensionBackoff;
+}
+
+// This compiles down nicely.  
+inline bool HasExtension(const float &backoff) {
+  typedef union { float f; uint32_t i; } UnionValue;
+  UnionValue compare, interpret;
+  compare.f = kNoExtensionBackoff;
+  interpret.f = backoff;
+  return compare.i != interpret.i;
+}
+
+} // namespace ngram
+} // namespace lm
+#endif // LM_BLANK_H

kenlm/include/lm/builder/adjust_counts.hh

@@ -0,0 +1,72 @@
+#ifndef LM_BUILDER_ADJUST_COUNTS_H
+#define LM_BUILDER_ADJUST_COUNTS_H
+
+#include "lm/builder/discount.hh"
+#include "lm/lm_exception.hh"
+#include "util/exception.hh"
+
+#include <vector>
+
+#include <stdint.h>
+
+namespace util { namespace stream { class ChainPositions; } }
+
+namespace lm {
+namespace builder {
+
+class BadDiscountException : public util::Exception {
+  public:
+    BadDiscountException() throw();
+    ~BadDiscountException() throw();
+};
+
+struct DiscountConfig {
+  // Overrides discounts for orders [1,discount_override.size()].
+  std::vector<Discount> overwrite;
+  // If discounting fails for an order, copy them from here.
+  Discount fallback;
+  // What to do when discounts are out of range or would trigger divison by
+  // zero.  It it does something other than THROW_UP, use fallback_discount.
+  WarningAction bad_action;
+};
+
+/* Compute adjusted counts.  
+ * Input: unique suffix sorted N-grams (and just the N-grams) with raw counts.
+ * Output: [1,N]-grams with adjusted counts.  
+ * [1,N)-grams are in suffix order
+ * N-grams are in undefined order (they're going to be sorted anyway).
+ */
+class AdjustCounts {
+  public:
+    // counts: output
+    // counts_pruned: output
+    // discounts: mostly output.  If the input already has entries, they will be kept.
+    // prune_thresholds: input.  n-grams with normal (not adjusted) count below this will be pruned.
+    AdjustCounts(
+        const std::vector<uint64_t> &prune_thresholds,
+        std::vector<uint64_t> &counts,
+        std::vector<uint64_t> &counts_pruned,
+        const std::vector<bool> &prune_words,
+        const DiscountConfig &discount_config,
+        std::vector<Discount> &discounts)
+      : prune_thresholds_(prune_thresholds), counts_(counts), counts_pruned_(counts_pruned),
+        prune_words_(prune_words), discount_config_(discount_config), discounts_(discounts) 
+    {}
+
+    void Run(const util::stream::ChainPositions &positions);
+
+  private:
+    const std::vector<uint64_t> &prune_thresholds_; 
+    std::vector<uint64_t> &counts_;
+    std::vector<uint64_t> &counts_pruned_;
+    const std::vector<bool> &prune_words_;
+
+    DiscountConfig discount_config_;
+    std::vector<Discount> &discounts_;
+};
+
+} // namespace builder
+} // namespace lm
+
+#endif // LM_BUILDER_ADJUST_COUNTS_H
+

kenlm/include/lm/builder/corpus_count.hh

@@ -0,0 +1,53 @@
+#ifndef LM_BUILDER_CORPUS_COUNT_H
+#define LM_BUILDER_CORPUS_COUNT_H
+
+#include "lm/lm_exception.hh"
+#include "lm/word_index.hh"
+#include "util/scoped.hh"
+
+#include <cstddef>
+#include <string>
+#include <stdint.h>
+#include <vector>
+
+namespace util {
+class FilePiece;
+namespace stream {
+class ChainPosition;
+} // namespace stream
+} // namespace util
+
+namespace lm {
+namespace builder {
+
+class CorpusCount {
+  public:
+    // Memory usage will be DedupeMultipler(order) * block_size + total_chain_size + unknown vocab_hash_size
+    static float DedupeMultiplier(std::size_t order);
+
+    // How much memory vocabulary will use based on estimated size of the vocab.
+    static std::size_t VocabUsage(std::size_t vocab_estimate);
+
+    // token_count: out.
+    // type_count aka vocabulary size.  Initialize to an estimate.  It is set to the exact value.
+    CorpusCount(util::FilePiece &from, int vocab_write, uint64_t &token_count, WordIndex &type_count, std::vector<bool> &prune_words, const std::string& prune_vocab_filename, std::size_t entries_per_block, WarningAction disallowed_symbol);
+
+    void Run(const util::stream::ChainPosition &position);
+
+  private:
+    util::FilePiece &from_;
+    int vocab_write_;
+    uint64_t &token_count_;
+    WordIndex &type_count_;
+    std::vector<bool>& prune_words_;
+    const std::string& prune_vocab_filename_; 
+
+    std::size_t dedupe_mem_size_;
+    util::scoped_malloc dedupe_mem_;
+
+    WarningAction disallowed_symbol_action_;
+};
+
+} // namespace builder
+} // namespace lm
+#endif // LM_BUILDER_CORPUS_COUNT_H

kenlm/include/lm/builder/discount.hh

@@ -0,0 +1,26 @@
+#ifndef LM_BUILDER_DISCOUNT_H
+#define LM_BUILDER_DISCOUNT_H
+
+#include <algorithm>
+
+#include <stdint.h>
+
+namespace lm {
+namespace builder {
+
+struct Discount {
+  float amount[4];
+
+  float Get(uint64_t count) const {
+    return amount[std::min<uint64_t>(count, 3)];
+  }
+
+  float Apply(uint64_t count) const {
+    return static_cast<float>(count) - Get(count);
+  }
+};
+
+} // namespace builder
+} // namespace lm
+
+#endif // LM_BUILDER_DISCOUNT_H

kenlm/include/lm/builder/hash_gamma.hh

@@ -0,0 +1,19 @@
+#ifndef LM_BUILDER_HASH_GAMMA__
+#define LM_BUILDER_HASH_GAMMA__
+
+#include <stdint.h>
+
+namespace lm { namespace builder {
+
+#pragma pack(push)
+#pragma pack(4)
+
+struct HashGamma {
+    uint64_t hash_value;
+    float gamma;
+};
+
+#pragma pack(pop)
+
+}} // namespaces
+#endif // LM_BUILDER_HASH_GAMMA__

kenlm/include/lm/builder/header_info.hh

@@ -0,0 +1,24 @@
+#ifndef LM_BUILDER_HEADER_INFO_H
+#define LM_BUILDER_HEADER_INFO_H
+
+#include <string>
+#include <vector>
+#include <stdint.h>
+
+// Some configuration info that is used to add
+// comments to the beginning of an ARPA file
+struct HeaderInfo {
+  std::string input_file;
+  uint64_t token_count;
+  std::vector<uint64_t> counts_pruned;
+
+  HeaderInfo() {}
+
+  HeaderInfo(const std::string& input_file_in, uint64_t token_count_in, const std::vector<uint64_t> &counts_pruned_in)
+    : input_file(input_file_in), token_count(token_count_in), counts_pruned(counts_pruned_in) {}
+
+  // TODO: Add smoothing type
+  // TODO: More info if multiple models were interpolated
+};
+
+#endif

kenlm/include/lm/builder/initial_probabilities.hh

@@ -0,0 +1,42 @@
+#ifndef LM_BUILDER_INITIAL_PROBABILITIES_H
+#define LM_BUILDER_INITIAL_PROBABILITIES_H
+
+#include "lm/builder/discount.hh"
+#include "util/stream/config.hh"
+
+#include <vector>
+
+namespace util { namespace stream { class Chains; } }
+
+namespace lm {
+namespace builder {
+
+struct InitialProbabilitiesConfig {
+  // These should be small buffers to keep the adder from getting too far ahead
+  util::stream::ChainConfig adder_in;
+  util::stream::ChainConfig adder_out;
+  // SRILM doesn't normally interpolate unigrams.  
+  bool interpolate_unigrams;
+};
+
+/* Compute initial (uninterpolated) probabilities
+ * primary: the normal chain of n-grams.  Incoming is context sorted adjusted
+ *   counts.  Outgoing has uninterpolated probabilities for use by Interpolate.
+ * second_in: a second copy of the primary input.  Discard the output.  
+ * gamma_out: Computed gamma values are output on these chains in suffix order.
+ *   The values are bare floats and should be buffered for interpolation to
+ *   use.  
+ */
+void InitialProbabilities(
+    const InitialProbabilitiesConfig &config,
+    const std::vector<Discount> &discounts,
+    util::stream::Chains &primary,
+    util::stream::Chains &second_in,
+    util::stream::Chains &gamma_out,
+    const std::vector<uint64_t> &prune_thresholds,
+    bool prune_vocab);
+
+} // namespace builder
+} // namespace lm
+
+#endif // LM_BUILDER_INITIAL_PROBABILITIES_H

kenlm/include/lm/builder/interpolate.hh

@@ -0,0 +1,34 @@
+#ifndef LM_BUILDER_INTERPOLATE_H
+#define LM_BUILDER_INTERPOLATE_H
+
+#include "util/stream/multi_stream.hh"
+
+#include <vector>
+
+#include <stdint.h>
+
+namespace lm { namespace builder {
+ 
+/* Interpolate step.  
+ * Input: suffix sorted n-grams with (p_uninterpolated, gamma) from
+ * InitialProbabilities.
+ * Output: suffix sorted n-grams with complete probability
+ */
+class Interpolate {
+  public:
+    // Normally vocab_size is the unigram count-1 (since p(<s>) = 0) but might
+    // be larger when the user specifies a consistent vocabulary size.
+    explicit Interpolate(uint64_t vocab_size, const util::stream::ChainPositions &backoffs, const std::vector<uint64_t> &prune_thresholds, bool prune_vocab, bool output_q_);
+
+    void Run(const util::stream::ChainPositions &positions);
+
+  private:
+    float uniform_prob_;
+    util::stream::ChainPositions backoffs_;
+    const std::vector<uint64_t> prune_thresholds_;
+    bool prune_vocab_;
+    bool output_q_;
+};
+
+}} // namespaces
+#endif // LM_BUILDER_INTERPOLATE_H

kenlm/include/lm/builder/joint_order.hh

@@ -0,0 +1,67 @@
+#ifndef LM_BUILDER_JOINT_ORDER_H
+#define LM_BUILDER_JOINT_ORDER_H
+
+#include "lm/builder/ngram_stream.hh"
+#include "lm/lm_exception.hh"
+
+#ifdef DEBUG
+#include "util/fixed_array.hh"
+#include <iostream>
+#endif
+
+#include <string.h>
+
+namespace lm { namespace builder {
+
+template <class Callback, class Compare> void JointOrder(const util::stream::ChainPositions &positions, Callback &callback) {
+  // Allow matching to reference streams[-1].
+  NGramStreams streams_with_dummy;
+  streams_with_dummy.InitWithDummy(positions);
+  NGramStream *streams = streams_with_dummy.begin() + 1;
+
+  unsigned int order;
+  for (order = 0; order < positions.size() && streams[order]; ++order) {}
+  assert(order); // should always have <unk>.
+
+  // Debugging only: call comparison function to sanity check order.
+#ifdef DEBUG
+  util::FixedArray<Compare> less_compare(order);
+  for (unsigned i = 0; i < order; ++i)
+    less_compare.push_back(i + 1);
+#endif // DEBUG
+
+  unsigned int current = 0;
+  while (true) {
+    // Does the context match the lower one?
+    if (!memcmp(streams[static_cast<int>(current) - 1]->begin(), streams[current]->begin() + Compare::kMatchOffset, sizeof(WordIndex) * current)) {
+      callback.Enter(current, *streams[current]);
+      // Transition to looking for extensions.  
+      if (++current < order) continue;
+    }
+#ifdef DEBUG
+    // match_check[current - 1] matches current-grams
+    // The lower-order stream (which skips fewer current-grams) should always be <= the higher order-stream (which can skip current-grams).
+    else if (!less_compare[current - 1](streams[static_cast<int>(current) - 1]->begin(), streams[current]->begin() + Compare::kMatchOffset)) {
+      std::cerr << "Stream out of order detected" << std::endl;
+      abort();
+    }
+#endif // DEBUG
+    // No extension left.  
+    while(true) {
+      assert(current > 0);
+      --current;
+      callback.Exit(current, *streams[current]);
+      
+      if (++streams[current]) break;
+      
+      UTIL_THROW_IF(order != current + 1, FormatLoadException, "Detected n-gram without matching suffix");
+      
+      order = current;
+      if (!order) return;
+    }
+  }
+}
+
+}} // namespaces
+
+#endif // LM_BUILDER_JOINT_ORDER_H

kenlm/include/lm/builder/ngram.hh

@@ -0,0 +1,109 @@
+#ifndef LM_BUILDER_NGRAM_H
+#define LM_BUILDER_NGRAM_H
+
+#include "lm/weights.hh"
+#include "lm/word_index.hh"
+
+#include <cstddef>
+
+#include <assert.h>
+#include <stdint.h>
+#include <string.h>
+
+namespace lm {
+namespace builder {
+
+struct Uninterpolated {
+  float prob;  // Uninterpolated probability.
+  float gamma; // Interpolation weight for lower order.
+};
+
+union Payload {
+  uint64_t count;
+  Uninterpolated uninterp;
+  ProbBackoff complete;
+};
+
+class NGram {
+  public:
+    NGram(void *begin, std::size_t order)
+      : begin_(static_cast<WordIndex*>(begin)), end_(begin_ + order) {}
+
+    const uint8_t *Base() const { return reinterpret_cast<const uint8_t*>(begin_); }
+    uint8_t *Base() { return reinterpret_cast<uint8_t*>(begin_); }
+
+    void ReBase(void *to) {
+      std::size_t difference = end_ - begin_;
+      begin_ = reinterpret_cast<WordIndex*>(to);
+      end_ = begin_ + difference;
+    }
+
+    // Would do operator++ but that can get confusing for a stream.
+    void NextInMemory() {
+      ReBase(&Value() + 1);
+    }
+
+    // Lower-case in deference to STL.
+    const WordIndex *begin() const { return begin_; }
+    WordIndex *begin() { return begin_; }
+    const WordIndex *end() const { return end_; }
+    WordIndex *end() { return end_; }
+
+    const Payload &Value() const { return *reinterpret_cast<const Payload *>(end_); }
+    Payload &Value() { return *reinterpret_cast<Payload *>(end_); }
+
+    uint64_t &Count() { return Value().count; }
+    uint64_t Count() const { return Value().count; }
+
+    std::size_t Order() const { return end_ - begin_; }
+
+    static std::size_t TotalSize(std::size_t order) {
+      return order * sizeof(WordIndex) + sizeof(Payload);
+    }
+    std::size_t TotalSize() const {
+      // Compiler should optimize this.
+      return TotalSize(Order());
+    }
+    static std::size_t OrderFromSize(std::size_t size) {
+      std::size_t ret = (size - sizeof(Payload)) / sizeof(WordIndex);
+      assert(size == TotalSize(ret));
+      return ret;
+    }
+    
+    // manipulate msb to signal that ngram can be pruned
+    /*mjd**********************************************************************/
+
+    bool IsMarked() const {
+      return Value().count >> (sizeof(Value().count) * 8 - 1);
+    }
+    
+    void Mark() {
+      Value().count |= (1ul << (sizeof(Value().count) * 8 - 1));
+    }
+    
+    void Unmark() {
+      Value().count &= ~(1ul << (sizeof(Value().count) * 8 - 1));
+    }
+    
+    uint64_t UnmarkedCount() const {
+      return Value().count & ~(1ul << (sizeof(Value().count) * 8 - 1));
+    }
+    
+    uint64_t CutoffCount() const {
+      return IsMarked() ? 0 : UnmarkedCount();
+    }
+
+    /*mjd**********************************************************************/
+
+  private:
+    WordIndex *begin_, *end_;
+};
+
+const WordIndex kUNK = 0;
+const WordIndex kBOS = 1;
+const WordIndex kEOS = 2;
+
+} // namespace builder
+} // namespace lm
+
+#endif // LM_BUILDER_NGRAM_H

kenlm/include/lm/builder/ngram_stream.hh

@@ -0,0 +1,58 @@
+#ifndef LM_BUILDER_NGRAM_STREAM_H
+#define LM_BUILDER_NGRAM_STREAM_H
+
+#include "lm/builder/ngram.hh"
+#include "util/stream/chain.hh"
+#include "util/stream/multi_stream.hh"
+#include "util/stream/stream.hh"
+
+#include <cstddef>
+
+namespace lm { namespace builder {
+
+class NGramStream {
+  public:
+    NGramStream() : gram_(NULL, 0) {}
+
+    NGramStream(const util::stream::ChainPosition &position) : gram_(NULL, 0) {
+      Init(position);
+    }
+
+    void Init(const util::stream::ChainPosition &position) {
+      stream_.Init(position);
+      gram_ = NGram(stream_.Get(), NGram::OrderFromSize(position.GetChain().EntrySize()));
+    }
+
+    NGram &operator*() { return gram_; }
+    const NGram &operator*() const { return gram_; }
+
+    NGram *operator->() { return &gram_; }
+    const NGram *operator->() const { return &gram_; }
+
+    void *Get() { return stream_.Get(); }
+    const void *Get() const { return stream_.Get(); }
+
+    operator bool() const { return stream_; }
+    bool operator!() const { return !stream_; }
+    void Poison() { stream_.Poison(); }
+
+    NGramStream &operator++() {
+      ++stream_;
+      gram_.ReBase(stream_.Get());
+      return *this;
+    }
+
+  private:
+    NGram gram_;
+    util::stream::Stream stream_;
+};
+
+inline util::stream::Chain &operator>>(util::stream::Chain &chain, NGramStream &str) {
+  str.Init(chain.Add());
+  return chain;
+}
+
+typedef util::stream::GenericStreams<NGramStream> NGramStreams;
+
+}} // namespaces
+#endif // LM_BUILDER_NGRAM_STREAM_H

kenlm/include/lm/builder/output.hh

@@ -0,0 +1,89 @@
+#ifndef LM_BUILDER_OUTPUT_H
+#define LM_BUILDER_OUTPUT_H
+
+#include "lm/builder/header_info.hh"
+#include "util/file.hh"
+
+#include <boost/ptr_container/ptr_vector.hpp>
+#include <boost/utility.hpp>
+
+#include <map>
+
+namespace util { namespace stream { class Chains; class ChainPositions; } }
+
+/* Outputs from lmplz: ARPA< sharded files, etc */
+namespace lm { namespace builder {
+
+// These are different types of hooks.  Values should be consecutive to enable a vector lookup.
+enum HookType {
+  COUNT_HOOK, // Raw N-gram counts, highest order only.
+  PROB_PARALLEL_HOOK, // Probability and backoff (or just q).  Output must process the orders in parallel or there will be a deadlock.
+  PROB_SEQUENTIAL_HOOK, // Probability and backoff (or just q).  Output can process orders any way it likes.  This requires writing the data to disk then reading.  Useful for ARPA files, which put unigrams first etc.
+  NUMBER_OF_HOOKS // Keep this last so we know how many values there are.
+};
+
+class Output;
+
+class OutputHook {
+  public:
+    explicit OutputHook(HookType hook_type) : type_(hook_type), master_(NULL) {}
+
+    virtual ~OutputHook();
+
+    virtual void Apply(util::stream::Chains &chains);
+
+    virtual void Run(const util::stream::ChainPositions &positions) = 0;
+
+  protected:
+    const HeaderInfo &GetHeader() const;
+    int GetVocabFD() const;
+
+  private:
+    friend class Output;
+    const HookType type_;
+    const Output *master_;
+};
+
+class Output : boost::noncopyable {
+  public:
+    Output() {}
+
+    // Takes ownership.
+    void Add(OutputHook *hook) {
+      hook->master_ = this;
+      outputs_[hook->type_].push_back(hook);
+    }
+
+    bool Have(HookType hook_type) const {
+      return !outputs_[hook_type].empty();
+    }
+
+    void SetVocabFD(int to) { vocab_fd_ = to; }
+    int GetVocabFD() const { return vocab_fd_; }
+
+    void SetHeader(const HeaderInfo &header) { header_ = header; }
+    const HeaderInfo &GetHeader() const { return header_; }
+
+    void Apply(HookType hook_type, util::stream::Chains &chains) {
+      for (boost::ptr_vector<OutputHook>::iterator entry = outputs_[hook_type].begin(); entry != outputs_[hook_type].end(); ++entry) {
+        entry->Apply(chains);
+      }
+    }
+
+  private:
+    boost::ptr_vector<OutputHook> outputs_[NUMBER_OF_HOOKS];
+    int vocab_fd_;
+    HeaderInfo header_;
+};
+
+inline const HeaderInfo &OutputHook::GetHeader() const {
+  return master_->GetHeader();
+}
+
+inline int OutputHook::GetVocabFD() const {
+  return master_->GetVocabFD();
+}
+
+}} // namespaces
+
+#endif // LM_BUILDER_OUTPUT_H

kenlm/include/lm/builder/pipeline.hh

@@ -0,0 +1,74 @@
+#ifndef LM_BUILDER_PIPELINE_H
+#define LM_BUILDER_PIPELINE_H
+
+#include "lm/builder/adjust_counts.hh"
+#include "lm/builder/initial_probabilities.hh"
+#include "lm/builder/header_info.hh"
+#include "lm/lm_exception.hh"
+#include "lm/word_index.hh"
+#include "util/stream/config.hh"
+#include "util/file_piece.hh"
+
+#include <string>
+#include <cstddef>
+
+namespace lm { namespace builder {
+
+class Output;
+
+struct PipelineConfig {
+  std::size_t order;
+  std::string vocab_file;
+  util::stream::SortConfig sort;
+  InitialProbabilitiesConfig initial_probs;
+  util::stream::ChainConfig read_backoffs;
+
+  // Estimated vocabulary size.  Used for sizing CorpusCount memory and
+  // initial probing hash table sizing, also in CorpusCount.
+  lm::WordIndex vocab_estimate;
+
+  // Minimum block size to tolerate.
+  std::size_t minimum_block;
+
+  // Number of blocks to use.  This will be overridden to 1 if everything fits.
+  std::size_t block_count;
+
+  // n-gram count thresholds for pruning. 0 values means no pruning for
+  // corresponding n-gram order
+  std::vector<uint64_t> prune_thresholds; //mjd
+  bool prune_vocab;
+  std::string prune_vocab_file;
+
+  // What to do with discount failures.
+  DiscountConfig discount;
+
+  // Compute collapsed q values instead of probability and backoff
+  bool output_q;
+  
+  /* Computing the perplexity of LMs with different vocabularies is hard.  For
+   * example, the lowest perplexity is attained by a unigram model that
+   * predicts p(<unk>) = 1 and has no other vocabulary.  Also, linearly
+   * interpolated models will sum to more than 1 because <unk> is duplicated
+   * (SRI just pretends p(<unk>) = 0 for these purposes, which makes it sum to
+   * 1 but comes with its own problems).  This option will make the vocabulary
+   * a particular size by replicating <unk> multiple times for purposes of
+   * computing vocabulary size.  It has no effect if the actual vocabulary is
+   * larger.  This parameter serves the same purpose as IRSTLM's "dub".
+   */
+  uint64_t vocab_size_for_unk;
+
+  /* What to do the first time <s>, </s>, or <unk> appears in the input.  If
+   * this is anything but THROW_UP, then the symbol will always be treated as
+   * whitespace.
+   */
+  WarningAction disallowed_symbol_action;
+
+  const std::string &TempPrefix() const { return sort.temp_prefix; }
+  std::size_t TotalMemory() const { return sort.total_memory; }
+};
+
+// Takes ownership of text_file and out_arpa.
+void Pipeline(PipelineConfig &config, int text_file, Output &output);
+
+}} // namespaces
+#endif // LM_BUILDER_PIPELINE_H

kenlm/include/lm/builder/print.hh

@@ -0,0 +1,115 @@
+#ifndef LM_BUILDER_PRINT_H
+#define LM_BUILDER_PRINT_H
+
+#include "lm/builder/ngram.hh"
+#include "lm/builder/ngram_stream.hh"
+#include "lm/builder/output.hh"
+#include "util/fake_ofstream.hh"
+#include "util/file.hh"
+#include "util/mmap.hh"
+#include "util/string_piece.hh"
+
+#include <ostream>
+
+#include <assert.h>
+
+// Warning: print routines read all unigrams before all bigrams before all
+// trigrams etc.  So if other parts of the chain move jointly, you'll have to
+// buffer.  
+
+namespace lm { namespace builder {
+
+class VocabReconstitute {
+  public:
+    // fd must be alive for life of this object; does not take ownership.
+    explicit VocabReconstitute(int fd);
+
+    const char *Lookup(WordIndex index) const {
+      assert(index < map_.size() - 1);
+      return map_[index];
+    }
+
+    StringPiece LookupPiece(WordIndex index) const {
+      return StringPiece(map_[index], map_[index + 1] - 1 - map_[index]);
+    }
+
+    std::size_t Size() const {
+      // There's an extra entry to support StringPiece lengths.
+      return map_.size() - 1;
+    }
+
+  private:
+    util::scoped_memory memory_;
+    std::vector<const char*> map_;
+};
+
+// Not defined, only specialized.  
+template <class T> void PrintPayload(util::FakeOFStream &to, const Payload &payload);
+template <> inline void PrintPayload<uint64_t>(util::FakeOFStream &to, const Payload &payload) {
+  // TODO slow
+  to << boost::lexical_cast<std::string>(payload.count);
+}
+template <> inline void PrintPayload<Uninterpolated>(util::FakeOFStream &to, const Payload &payload) {
+  to << log10(payload.uninterp.prob) << ' ' << log10(payload.uninterp.gamma);
+}
+template <> inline void PrintPayload<ProbBackoff>(util::FakeOFStream &to, const Payload &payload) {
+  to << payload.complete.prob << ' ' << payload.complete.backoff;
+}
+
+// template parameter is the type stored.  
+template <class V> class Print {
+  public:
+    static void DumpSeparateFiles(const VocabReconstitute &vocab, const std::string &file_base, util::stream::Chains &chains) {
+      for (unsigned int i = 0; i < chains.size(); ++i) {
+        std::string file(file_base + boost::lexical_cast<std::string>(i));
+        chains[i] >> Print(vocab, util::CreateOrThrow(file.c_str()));
+      }
+    }
+
+    explicit Print(const VocabReconstitute &vocab, int fd) : vocab_(vocab), to_(fd) {}
+
+    void Run(const util::stream::ChainPositions &chains) {
+      util::scoped_fd fd(to_);
+      util::FakeOFStream out(to_);
+      NGramStreams streams(chains);
+      for (NGramStream *s = streams.begin(); s != streams.end(); ++s) {
+        DumpStream(*s, out);
+      }
+    }
+
+    void Run(const util::stream::ChainPosition &position) {
+      util::scoped_fd fd(to_);
+      util::FakeOFStream out(to_);
+      NGramStream stream(position);
+      DumpStream(stream, out);
+    }
+
+  private:
+    void DumpStream(NGramStream &stream, util::FakeOFStream &to) {
+      for (; stream; ++stream) {
+        PrintPayload<V>(to, stream->Value());
+        for (const WordIndex *w = stream->begin(); w != stream->end(); ++w) {
+          to << ' ' << vocab_.Lookup(*w) << '=' << *w;
+        }
+        to << '\n';
+      }
+    }
+
+    const VocabReconstitute &vocab_;
+    int to_;
+};
+
+class PrintARPA : public OutputHook {
+  public:
+    explicit PrintARPA(int fd, bool verbose_header)
+      : OutputHook(PROB_SEQUENTIAL_HOOK), out_fd_(fd), verbose_header_(verbose_header) {}
+
+    void Run(const util::stream::ChainPositions &positions);
+
+  private:
+    util::scoped_fd out_fd_;
+    bool verbose_header_;
+};
+
+}} // namespaces
+#endif // LM_BUILDER_PRINT_H

kenlm/include/lm/builder/sort.hh

@@ -0,0 +1,244 @@
+#ifndef LM_BUILDER_SORT_H
+#define LM_BUILDER_SORT_H
+
+#include "lm/builder/ngram_stream.hh"
+#include "lm/builder/ngram.hh"
+#include "lm/word_index.hh"
+#include "util/stream/sort.hh"
+
+#include "util/stream/timer.hh"
+
+#include <functional>
+#include <string>
+
+namespace lm {
+namespace builder {
+
+/**
+ * Abstract parent class for defining custom n-gram comparators.
+ */
+template <class Child> class Comparator : public std::binary_function<const void *, const void *, bool> {
+  public:
+  
+    /**
+     * Constructs a comparator capable of comparing two n-grams.
+     *
+     * @param order Number of words in each n-gram
+     */
+    explicit Comparator(std::size_t order) : order_(order) {}
+
+    /**
+     * Applies the comparator using the Compare method that must be defined in any class that inherits from this class.
+     *
+     * @param lhs A pointer to the n-gram on the left-hand side of the comparison
+     * @param rhs A pointer to the n-gram on the right-hand side of the comparison
+     *
+     * @see ContextOrder::Compare
+     * @see PrefixOrder::Compare
+     * @see SuffixOrder::Compare
+     */
+    inline bool operator()(const void *lhs, const void *rhs) const {
+      return static_cast<const Child*>(this)->Compare(static_cast<const WordIndex*>(lhs), static_cast<const WordIndex*>(rhs));
+    }
+
+    /** Gets the n-gram order defined for this comparator. */
+    std::size_t Order() const { return order_; }
+
+  protected:
+    std::size_t order_;
+};
+
+/**
+ * N-gram comparator that compares n-grams according to their reverse (suffix) order.
+ *
+ * This comparator compares n-grams lexicographically, one word at a time, 
+ * beginning with the last word of each n-gram and ending with the first word of each n-gram. 
+ *
+ * Some examples of n-gram comparisons as defined by this comparator:
+ * - a b c == a b c
+ * - a b c < a b d
+ * - a b c > a d b
+ * - a b c > a b b
+ * - a b c > x a c
+ * - a b c < x y z
+ */
+class SuffixOrder : public Comparator<SuffixOrder> {
+  public:
+  
+    /** 
+     * Constructs a comparator capable of comparing two n-grams.
+     *
+     * @param order Number of words in each n-gram
+     */
+    explicit SuffixOrder(std::size_t order) : Comparator<SuffixOrder>(order) {}
+
+    /**
+     * Compares two n-grams lexicographically, one word at a time, 
+     * beginning with the last word of each n-gram and ending with the first word of each n-gram.
+     *
+     * @param lhs A pointer to the n-gram on the left-hand side of the comparison
+     * @param rhs A pointer to the n-gram on the right-hand side of the comparison
+     */
+    inline bool Compare(const WordIndex *lhs, const WordIndex *rhs) const {
+      for (std::size_t i = order_ - 1; i != 0; --i) {
+        if (lhs[i] != rhs[i])
+          return lhs[i] < rhs[i];
+      }
+      return lhs[0] < rhs[0];
+    }
+
+    static const unsigned kMatchOffset = 1;
+};
+
+  
+/**
+  * N-gram comparator that compares n-grams according to the reverse (suffix) order of the n-gram context.
+  *
+  * This comparator compares n-grams lexicographically, one word at a time, 
+  * beginning with the penultimate word of each n-gram and ending with the first word of each n-gram;
+  * finally, this comparator compares the last word of each n-gram.
+  *
+  * Some examples of n-gram comparisons as defined by this comparator:
+  * - a b c == a b c
+  * - a b c < a b d
+  * - a b c < a d b
+  * - a b c > a b b
+  * - a b c > x a c
+  * - a b c < x y z
+  */
+class ContextOrder : public Comparator<ContextOrder> {
+  public:
+  
+    /** 
+     * Constructs a comparator capable of comparing two n-grams.
+     *
+     * @param order Number of words in each n-gram
+     */
+    explicit ContextOrder(std::size_t order) : Comparator<ContextOrder>(order) {}
+
+    /**
+     * Compares two n-grams lexicographically, one word at a time, 
+     * beginning with the penultimate word of each n-gram and ending with the first word of each n-gram;
+     * finally, this comparator compares the last word of each n-gram.
+     *
+     * @param lhs A pointer to the n-gram on the left-hand side of the comparison
+     * @param rhs A pointer to the n-gram on the right-hand side of the comparison
+     */
+    inline bool Compare(const WordIndex *lhs, const WordIndex *rhs) const {
+      for (int i = order_ - 2; i >= 0; --i) {
+        if (lhs[i] != rhs[i])
+          return lhs[i] < rhs[i];
+      }
+      return lhs[order_ - 1] < rhs[order_ - 1];
+    }
+};
+
+/**
+ * N-gram comparator that compares n-grams according to their natural (prefix) order.
+ *
+ * This comparator compares n-grams lexicographically, one word at a time, 
+ * beginning with the first word of each n-gram and ending with the last word of each n-gram.
+ *
+ * Some examples of n-gram comparisons as defined by this comparator:
+ * - a b c == a b c
+ * - a b c < a b d
+ * - a b c < a d b
+ * - a b c > a b b
+ * - a b c < x a c
+ * - a b c < x y z
+ */
+class PrefixOrder : public Comparator<PrefixOrder> {
+  public:
+  
+    /** 
+     * Constructs a comparator capable of comparing two n-grams.
+     *
+     * @param order Number of words in each n-gram
+     */
+    explicit PrefixOrder(std::size_t order) : Comparator<PrefixOrder>(order) {}
+
+    /**
+     * Compares two n-grams lexicographically, one word at a time, 
+     * beginning with the first word of each n-gram and ending with the last word of each n-gram.
+     *
+     * @param lhs A pointer to the n-gram on the left-hand side of the comparison
+     * @param rhs A pointer to the n-gram on the right-hand side of the comparison
+     */
+    inline bool Compare(const WordIndex *lhs, const WordIndex *rhs) const {
+      for (std::size_t i = 0; i < order_; ++i) {
+        if (lhs[i] != rhs[i])
+          return lhs[i] < rhs[i];
+      }
+      return false;
+    }
+    
+    static const unsigned kMatchOffset = 0;
+};
+
+// Sum counts for the same n-gram.
+struct AddCombiner {
+  bool operator()(void *first_void, const void *second_void, const SuffixOrder &compare) const {
+    NGram first(first_void, compare.Order());
+    // There isn't a const version of NGram.  
+    NGram second(const_cast<void*>(second_void), compare.Order());
+    if (memcmp(first.begin(), second.begin(), sizeof(WordIndex) * compare.Order())) return false;
+    first.Count() += second.Count();
+    return true;
+  }
+};
+
+// The combiner is only used on a single chain, so I didn't bother to allow
+// that template.
+/**
+ * Represents an @ref util::FixedArray "array" capable of storing @ref util::stream::Sort "Sort" objects.
+ *
+ * In the anticipated use case, an instance of this class will maintain one @ref util::stream::Sort "Sort" object
+ * for each n-gram order (ranging from 1 up to the maximum n-gram order being processed).
+ * Use in this manner would enable the n-grams each n-gram order to be sorted, in parallel.
+ *
+ * @tparam Compare An @ref Comparator "ngram comparator" to use during sorting.
+ */
+template <class Compare> class Sorts : public util::FixedArray<util::stream::Sort<Compare> > {
+  private:
+    typedef util::stream::Sort<Compare> S;
+    typedef util::FixedArray<S> P;
+
+  public:
+  
+    /**
+     * Constructs, but does not initialize.
+     * 
+     * @ref util::FixedArray::Init() "Init" must be called before use.
+     *
+     * @see util::FixedArray::Init()
+     */
+    Sorts() {}
+
+    /**
+     * Constructs an @ref util::FixedArray "array" capable of storing a fixed number of @ref util::stream::Sort "Sort" objects.
+     *
+     * @param number The maximum number of @ref util::stream::Sort "sorters" that can be held by this @ref util::FixedArray "array"
+     * @see util::FixedArray::FixedArray()
+     */
+    explicit Sorts(std::size_t number) : util::FixedArray<util::stream::Sort<Compare> >(number) {}
+
+    /** 
+     * Constructs a new @ref util::stream::Sort "Sort" object which is stored in this @ref util::FixedArray "array".
+     *
+     * The new @ref util::stream::Sort "Sort" object is constructed using the provided @ref util::stream::SortConfig "SortConfig" and @ref Comparator "ngram comparator";
+     * once constructed, a new worker @ref util::stream::Thread "thread" (owned by the @ref util::stream::Chain "chain") will sort the n-gram data stored
+     * in the @ref util::stream::Block "blocks" of the provided @ref util::stream::Chain "chain".
+     *
+     * @see util::stream::Sort::Sort()
+     * @see util::stream::Chain::operator>>()
+     */
+    void push_back(util::stream::Chain &chain, const util::stream::SortConfig &config, const Compare &compare) {
+      new (P::end()) S(chain, config, compare); // use "placement new" syntax to initalize S in an already-allocated memory location
+      P::Constructed();
+    }
+};
+
+} // namespace builder
+} // namespace lm
+
+#endif // LM_BUILDER_SORT_H

kenlm/include/lm/config.hh

@@ -0,0 +1,124 @@
+#ifndef LM_CONFIG_H
+#define LM_CONFIG_H
+
+#include "lm/lm_exception.hh"
+#include "util/mmap.hh"
+
+#include <iosfwd>
+#include <string>
+#include <vector>
+
+/* Configuration for ngram model.  Separate header to reduce pollution. */
+
+namespace lm {
+
+class EnumerateVocab;
+
+namespace ngram {
+
+struct Config {
+  // EFFECTIVE FOR BOTH ARPA AND BINARY READS
+
+  // (default true) print progress bar to messages
+  bool show_progress;
+
+  // Where to log messages including the progress bar.  Set to NULL for
+  // silence.
+  std::ostream *messages;
+
+  std::ostream *ProgressMessages() const {
+    return show_progress ? messages : 0;
+  }
+
+  // This will be called with every string in the vocabulary by the
+  // constructor; it need only exist for the lifetime of the constructor.
+  // See enumerate_vocab.hh for more detail.  Config does not take ownership;
+  // just delete/let it go out of scope after the constructor exits.
+  EnumerateVocab *enumerate_vocab;
+
+
+  // ONLY EFFECTIVE WHEN READING ARPA
+
+  // What to do when <unk> isn't in the provided model.
+  WarningAction unknown_missing;
+  // What to do when <s> or </s> is missing from the model.
+  // If THROW_UP, the exception will be of type util::SpecialWordMissingException.
+  WarningAction sentence_marker_missing;
+
+  // What to do with a positive log probability.  For COMPLAIN and SILENT, map
+  // to 0.
+  WarningAction positive_log_probability;
+
+  // The probability to substitute for <unk> if it's missing from the model.
+  // No effect if the model has <unk> or unknown_missing == THROW_UP.
+  float unknown_missing_logprob;
+
+  // Size multiplier for probing hash table.  Must be > 1.  Space is linear in
+  // this.  Time is probing_multiplier / (probing_multiplier - 1).  No effect
+  // for sorted variant.
+  // If you find yourself setting this to a low number, consider using the
+  // TrieModel which has lower memory consumption.
+  float probing_multiplier;
+
+  // Amount of memory to use for building.  The actual memory usage will be
+  // higher since this just sets sort buffer size.  Only applies to trie
+  // models.
+  std::size_t building_memory;
+
+  // Template for temporary directory appropriate for passing to mkdtemp.
+  // The characters XXXXXX are appended before passing to mkdtemp.  Only
+  // applies to trie.  If empty, defaults to write_mmap.  If that's NULL,
+  // defaults to input file name.
+  std::string temporary_directory_prefix;
+
+  // Level of complaining to do when loading from ARPA instead of binary format.
+  enum ARPALoadComplain {ALL, EXPENSIVE, NONE};
+  ARPALoadComplain arpa_complain;
+
+  // While loading an ARPA file, also write out this binary format file.  Set
+  // to NULL to disable.
+  const char *write_mmap;
+
+  enum WriteMethod {
+    WRITE_MMAP, // Map the file directly.
+    WRITE_AFTER // Write after we're done.
+  };
+  WriteMethod write_method;
+
+  // Include the vocab in the binary file?  Only effective if write_mmap != NULL.
+  bool include_vocab;
+
+
+  // Left rest options.  Only used when the model includes rest costs.
+  enum RestFunction {
+    REST_MAX,   // Maximum of any score to the left
+    REST_LOWER, // Use lower-order files given below.
+  };
+  RestFunction rest_function;
+  // Only used for REST_LOWER.
+  std::vector<std::string> rest_lower_files;
+
+
+  // Quantization options.  Only effective for QuantTrieModel.  One value is
+  // reserved for each of prob and backoff, so 2^bits - 1 buckets will be used
+  // to quantize (and one of the remaining backoffs will be 0).
+  uint8_t prob_bits, backoff_bits;
+
+  // Bhiksha compression (simple form).  Only works with trie.
+  uint8_t pointer_bhiksha_bits;
+
+
+  // ONLY EFFECTIVE WHEN READING BINARY
+
+  // How to get the giant array into memory: lazy mmap, populate, read etc.
+  // See util/mmap.hh for details of MapMethod.
+  util::LoadMethod load_method;
+
+
+  // Set defaults.
+  Config();
+};
+
+} /* namespace ngram */ } /* namespace lm */
+
+#endif // LM_CONFIG_H