cld3 3.4.4 → 3.5.1

data/lib/cld3.rb

@@ -17,39 +17,10 @@
 # limitations under the License.
 # ==============================================================================
 
-require "ffi"
-require "rbconfig"
-require "cld3/unstable"
-
 # Module providing an interface for Compact Language Detector v3 (CLD3)
 module CLD3
   # Class for detecting the language of a document.
   class NNetLanguageIdentifier
-    # Min number of bytes needed to make a prediction if the construcotr is
-    # called without the corresponding parameter.
-    # This is Numeric object.
-    MIN_NUM_BYTES_TO_CONSIDER = 140
-
-    # Max number of bytes needed to make a prediction if the construcotr is
-    # called without the corresponding parameter.
-    # This is Numeric object.
-    MAX_NUM_BYTES_TO_CONSIDER = 700
-
-    # Max number of input bytes to process.
-    # This is Numeric object.
-    MAX_NUM_INPUT_BYTES_TO_CONSIDER = 10000
-
-    # Predictions with probability greater than or equal to this threshold are
-    # marked as reliable. This threshold was optimized on a set of text segments
-    # extracted from wikipedia, and results in an overall precision, recall,
-    # and f1 equal to 0.9760, 0.9624, and 0.9692, respectively.
-    # This is Numeric object.
-    RELIABILITY_THRESHOLD = 0.7
-
-    # Reliability threshold for the languages hr and bs.
-    # This is Numeric object.
-    RELIABILITY_HR_BS_THRESHOLD = 0.5
-
     # Holds probability that Span, specified by start/end indices, is a given
     # language. The langauge is not stored here; it can be found in Result, which
     # holds an Array of SpanInfo.
@@ -76,8 +47,10 @@ module CLD3
 
     # The arguments are two Numeric objects.
     def initialize(min_num_bytes = MIN_NUM_BYTES_TO_CONSIDER, max_num_bytes = MAX_NUM_BYTES_TO_CONSIDER)
-      raise ArgumentError if max_num_bytes <= 0 || min_num_bytes < 0 || min_num_bytes >= max_num_bytes
-      @cc = Unstable::NNetLanguageIdentifier::Pointer.new(Unstable.new_NNetLanguageIdentifier(min_num_bytes, max_num_bytes))
+      min_num_bytes = min_num_bytes.ceil
+      max_num_bytes = max_num_bytes.floor
+      raise ArgumentError if min_num_bytes < 0 || min_num_bytes >= max_num_bytes
+      @cc = Unstable.make(min_num_bytes, max_num_bytes)
     end
 
     # Finds the most likely language for the given text, along with additional
@@ -88,21 +61,7 @@ module CLD3
     # The argument is a String object.
     # The returned value of this function is an instance of Result.
     def find_language(text)
-      text_utf8 = text.encode(Encoding::UTF_8)
-      pointer = FFI::MemoryPointer.new(:char, text_utf8.bytesize)
-
-      begin
-        pointer.put_bytes(0, text_utf8)
-
-        result = Unstable.NNetLanguageIdentifier_find_language(@cc, pointer, text_utf8.bytesize)
-        begin
-          convert_result Unstable::NNetLanguageIdentifier::Result.new(result)
-        ensure
-          Unstable.delete_result result
-        end
-      ensure
-        pointer.free
-      end
+      @cc.find_language(Result, SpanInfo, text.encode(Encoding::UTF_8))
     end
 
     # Splits the input text (up to the first byte, if any, that is not
@@ -119,51 +78,15 @@ module CLD3
     # The second argument is Numeric object.
     # The returned value of this functions is an Array of Result instances.
     def find_top_n_most_freq_langs(text, num_langs)
-      # @type var a: untyped
-
-      text_utf8 = text.encode(Encoding::UTF_8)
-      pointer = FFI::MemoryPointer.new(:char, text_utf8.bytesize)
-
-      begin
-        pointer.put_bytes(0, text_utf8)
-
-        results = Unstable.NNetLanguageIdentifier_find_top_n_most_freq_langs(@cc, pointer, text_utf8.bytesize, num_langs)
-        begin
-          a = num_langs.times
-            .lazy
-            .map { |index| convert_result Unstable.refer_to_nth_result(results, index) }
-            .take_while { |result| !result.nil? }
-            .to_a
-
-          a
-        ensure
-          Unstable.delete_results results
-        end
-      ensure
-        pointer.free
-      end
+      @cc.find_top_n_most_freq_langs(Result, SpanInfo,
+                                     text.encode(Encoding::UTF_8),
+                                     num_langs)
     end
 
-    private
-
-    def convert_result(result)
-      language = result[:language_data].read_bytes(result[:language_size])
-      return nil if language == "und"
-
-      cursor = result[:byte_ranges_data]
-      byte_ranges = result[:byte_ranges_size].times.map do
-        info = Unstable::NNetLanguageIdentifier::SpanInfo.new(cursor)
-        cursor += Unstable::NNetLanguageIdentifier::SpanInfo.size
-        SpanInfo.new(info[:start_index], info[:end_index], info[:probability])
-      end
-
-      Result.new(
-          language.to_sym,
-          result[:probability],
-          result[:reliable?],
-          result[:proportion],
-          byte_ranges)
+    class Unstable
     end
+  
+    private_constant :Unstable
   end
 
   # Encapsulates the TaskContext specifying only the parameters for the model.
@@ -171,17 +94,9 @@ module CLD3
   module TaskContextParams
     # This is an frozen Array object containing symbols.
     # @type const LANGUAGE_NAMES: untyped
-    LANGUAGE_NAMES = [
-      :eo, :co, :eu, :ta, :de, :mt, :ps, :te, :su, :uz, :'zh-Latn', :ne,
-      :nl, :sw, :sq, :hmn, :ja, :no, :mn, :so, :ko, :kk, :sl, :ig,
-      :mr, :th, :zu, :ml, :hr, :bs, :lo, :sd, :cy, :hy, :uk, :pt,
-      :lv, :iw, :cs, :vi, :jv, :be, :km, :mk, :tr, :fy, :am, :zh,
-      :da, :sv, :fi, :ht, :af, :la, :id, :fil, :sm, :ca, :el, :ka,
-      :sr, :it, :sk, :ru, :'ru-Latn', :bg, :ny, :fa, :haw, :gl, :et,
-      :ms, :gd, :'bg-Latn', :ha, :is, :ur, :mi, :hi, :bn, :'hi-Latn', :fr,
-      :yi, :hu, :xh, :my, :tg, :ro, :ar, :lb, :'el-Latn', :st, :ceb,
-      :kn, :az, :si, :ky, :mg, :en, :gu, :es, :pl, :'ja-Latn', :ga, :lt,
-      :sn, :yo, :pa, :ku,
-    ].freeze
+    LANGUAGE_NAMES = []
   end
 end
+
+require "cld3_ext"
+CLD3::TaskContextParams::LANGUAGE_NAMES.freeze

data/sig/cld3.rbs

@@ -36,6 +36,8 @@ module CLD3
       attr_accessor byte_ranges(): Array[SpanInfo]
     end
 
+    @cc: untyped
+
     def initialize: (?Integer, ?Integer) -> void
     def find_language: (String) -> Result?
     def find_top_n_most_freq_langs: (String, Integer) -> Array[Result]

metadata

@@ -1,95 +1,75 @@
 --- !ruby/object:Gem::Specification
 name: cld3
 version: !ruby/object:Gem::Version
-  version: 3.4.4
+  version: 3.5.1
 platform: ruby
 authors:
 - Akihiko Odaki
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-01-20 00:00:00.000000000 Z
+date: 2023-02-21 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: ffi
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.1.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: 1.16.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.1.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: 1.16.0
 - !ruby/object:Gem::Dependency
   name: rbs
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.7.0
+        version: 2.8.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 1.8.0
+        version: 2.9.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.7.0
+        version: 2.8.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 1.8.0
+        version: 2.9.0
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.0
+        version: 3.12.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 3.11.0
+        version: 3.13.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.0
+        version: 3.12.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 3.11.0
+        version: 3.13.0
 - !ruby/object:Gem::Dependency
   name: steep
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.47.0
+        version: 1.3.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 0.48.0
+        version: 1.4.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.47.0
+        version: 1.3.0
     - - "<"
       - !ruby/object:Gem::Version
-        version: 0.48.0
+        version: 1.4.0
 description: Compact Language Detector v3 (CLD3) is a neural network model for language
   identification.
 email: akihiko.odaki@gmail.com
@@ -103,105 +83,71 @@ files:
 - LICENSE_CLD3
 - README.md
 - cld3.gemspec
-- ext/cld3/Makefile
 - ext/cld3/base.cc
 - ext/cld3/base.h
-- ext/cld3/base.o
 - ext/cld3/casts.h
+- ext/cld3/cld_3/protos/feature_extractor.pb.h
+- ext/cld3/cld_3/protos/sentence.pb.h
+- ext/cld3/cld_3/protos/task_spec.pb.h
 - ext/cld3/embedding_feature_extractor.cc
 - ext/cld3/embedding_feature_extractor.h
-- ext/cld3/embedding_feature_extractor.o
 - ext/cld3/embedding_network.cc
 - ext/cld3/embedding_network.h
-- ext/cld3/embedding_network.o
 - ext/cld3/embedding_network_params.h
 - ext/cld3/extconf.rb
 - ext/cld3/feature_extractor.cc
 - ext/cld3/feature_extractor.h
-- ext/cld3/feature_extractor.o
-- ext/cld3/feature_extractor.pb.o
-- ext/cld3/feature_extractor.proto
 - ext/cld3/feature_types.cc
 - ext/cld3/feature_types.h
-- ext/cld3/feature_types.o
 - ext/cld3/fixunicodevalue.cc
 - ext/cld3/fixunicodevalue.h
-- ext/cld3/fixunicodevalue.o
 - ext/cld3/float16.h
 - ext/cld3/fml_parser.cc
 - ext/cld3/fml_parser.h
-- ext/cld3/fml_parser.o
 - ext/cld3/generated_entities.cc
-- ext/cld3/generated_entities.o
 - ext/cld3/generated_ulscript.cc
 - ext/cld3/generated_ulscript.h
-- ext/cld3/generated_ulscript.o
 - ext/cld3/getonescriptspan.cc
 - ext/cld3/getonescriptspan.h
-- ext/cld3/getonescriptspan.o
 - ext/cld3/integral_types.h
 - ext/cld3/lang_id_nn_params.cc
 - ext/cld3/lang_id_nn_params.h
-- ext/cld3/lang_id_nn_params.o
 - ext/cld3/language_identifier_features.cc
 - ext/cld3/language_identifier_features.h
-- ext/cld3/language_identifier_features.o
-- ext/cld3/libcld3.def
-- ext/cld3/libcld3.so
-- ext/cld3/mkmf.log
 - ext/cld3/nnet_language_identifier.cc
 - ext/cld3/nnet_language_identifier.h
-- ext/cld3/nnet_language_identifier.o
 - ext/cld3/nnet_language_identifier_c.cc
-- ext/cld3/nnet_language_identifier_c.o
 - ext/cld3/offsetmap.cc
 - ext/cld3/offsetmap.h
-- ext/cld3/offsetmap.o
 - ext/cld3/port.h
 - ext/cld3/registry.cc
 - ext/cld3/registry.h
-- ext/cld3/registry.o
 - ext/cld3/relevant_script_feature.cc
 - ext/cld3/relevant_script_feature.h
-- ext/cld3/relevant_script_feature.o
 - ext/cld3/script_detector.h
-- ext/cld3/sentence.pb.o
-- ext/cld3/sentence.proto
 - ext/cld3/sentence_features.cc
 - ext/cld3/sentence_features.h
-- ext/cld3/sentence_features.o
 - ext/cld3/simple_adder.h
 - ext/cld3/stringpiece.h
 - ext/cld3/task_context.cc
 - ext/cld3/task_context.h
-- ext/cld3/task_context.o
 - ext/cld3/task_context_params.cc
 - ext/cld3/task_context_params.h
-- ext/cld3/task_context_params.o
-- ext/cld3/task_spec.pb.o
-- ext/cld3/task_spec.proto
 - ext/cld3/text_processing.cc
 - ext/cld3/text_processing.h
-- ext/cld3/text_processing.o
 - ext/cld3/unicodetext.cc
 - ext/cld3/unicodetext.h
-- ext/cld3/unicodetext.o
 - ext/cld3/utf8acceptinterchange.h
 - ext/cld3/utf8prop_lettermarkscriptnum.h
 - ext/cld3/utf8repl_lettermarklower.h
 - ext/cld3/utf8scannot_lettermarkspecial.h
 - ext/cld3/utf8statetable.cc
 - ext/cld3/utf8statetable.h
-- ext/cld3/utf8statetable.o
 - ext/cld3/utils.cc
 - ext/cld3/utils.h
-- ext/cld3/utils.o
 - ext/cld3/workspace.cc
 - ext/cld3/workspace.h
-- ext/cld3/workspace.o
-- lib/a.rb
 - lib/cld3.rb
-- lib/cld3/unstable.rb
 - sig/cld3.rbs
 homepage: https://github.com/akihikodaki/cld3-ruby
 licenses:
@@ -215,17 +161,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.6.0
+      version: 2.7.0
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.2.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubygems_version: 3.3.25
 signing_key:
 specification_version: 4
 summary: Compact Language Detector v3 (CLD3)

data/ext/cld3/Makefile

@@ -1,267 +0,0 @@
-
-SHELL = /bin/sh
-
-# V=0 quiet, V=1 verbose.  other values don't work.
-V = 1
-Q1 = $(V:1=)
-Q = $(Q1:0=@)
-ECHO1 = $(V:1=@ :)
-ECHO = $(ECHO1:0=@ echo)
-NULLCMD = :
-
-#### Start of system configuration section. ####
-
-srcdir = .
-topdir = /usr/include
-hdrdir = $(topdir)
-arch_hdrdir = /usr/include
-PATH_SEPARATOR = :
-VPATH = $(srcdir):$(arch_hdrdir)/ruby:$(hdrdir)/ruby
-prefix = $(DESTDIR)/usr
-rubysitearchprefix = $(sitearchlibdir)/$(RUBY_BASE_NAME)
-rubyarchprefix = $(DESTDIR)/usr/lib64/ruby
-rubylibprefix = $(exec_prefix)/share/ruby
-exec_prefix = $(DESTDIR)/usr
-vendorarchhdrdir = $(vendorhdrdir)/$(arch)
-sitearchhdrdir = $(sitehdrdir)/$(arch)
-rubyarchhdrdir = $(DESTDIR)/usr/include
-vendorhdrdir = $(rubyhdrdir)/vendor_ruby
-sitehdrdir = $(rubyhdrdir)/site_ruby
-rubyhdrdir = $(DESTDIR)/usr/include
-rubygemsdir = $(DESTDIR)/usr/share/rubygems
-vendorarchdir = $(DESTDIR)/usr/lib64/ruby/vendor_ruby
-vendorlibdir = $(vendordir)
-vendordir = $(DESTDIR)/usr/share/ruby/vendor_ruby
-sitearchdir = $(DESTDIR)/usr/local/lib64/ruby/site_ruby
-sitelibdir = $(sitedir)
-sitedir = $(DESTDIR)/usr/local/share/ruby/site_ruby
-rubyarchdir = $(rubyarchprefix)
-rubylibdir = $(rubylibprefix)
-sitearchincludedir = $(includedir)/$(sitearch)
-archincludedir = $(includedir)/$(arch)
-sitearchlibdir = $(libdir)/$(sitearch)
-archlibdir = $(DESTDIR)/usr/lib64
-ridir = $(datarootdir)/$(RI_BASE_NAME)
-mandir = $(DESTDIR)/usr/share/man
-localedir = $(datarootdir)/locale
-libdir = $(exec_prefix)/lib64
-psdir = $(docdir)
-pdfdir = $(docdir)
-dvidir = $(docdir)
-htmldir = $(docdir)
-infodir = $(DESTDIR)/usr/share/info
-docdir = $(datarootdir)/doc/$(PACKAGE)
-oldincludedir = $(DESTDIR)/usr/include
-includedir = $(DESTDIR)/usr/include
-runstatedir = $(localstatedir)/run
-localstatedir = $(DESTDIR)/var
-sharedstatedir = $(DESTDIR)/var/lib
-sysconfdir = $(DESTDIR)/etc
-datadir = $(DESTDIR)/usr/share
-datarootdir = $(prefix)/share
-libexecdir = $(DESTDIR)/usr/libexec
-sbindir = $(DESTDIR)/usr/sbin
-bindir = $(exec_prefix)/bin
-archdir = $(rubyarchdir)
-
-
-CC_WRAPPER = 
-CC = gcc
-CXX = g++
-LIBRUBY = $(LIBRUBY_SO)
-LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
-LIBRUBYARG_SHARED = -l$(RUBY_SO_NAME)
-LIBRUBYARG_STATIC = -l$(RUBY_SO_NAME)-static $(MAINLIBS)
-empty =
-OUTFLAG = -o $(empty)
-COUTFLAG = -o $(empty)
-CSRCFLAG = $(empty)
-
-RUBY_EXTCONF_H = 
-cflags   = $(optflags) $(debugflags) $(warnflags)
-cxxflags = 
-optflags = -O3
-debugflags = -ggdb3
-warnflags = -Wall -Wextra -Wdeprecated-declarations -Wduplicated-cond -Wimplicit-function-declaration -Wimplicit-int -Wmisleading-indentation -Wpointer-arith -Wwrite-strings -Wimplicit-fallthrough=0 -Wmissing-noreturn -Wno-cast-function-type -Wno-constant-logical-operand -Wno-long-long -Wno-missing-field-initializers -Wno-overlength-strings -Wno-packed-bitfield-compat -Wno-parentheses-equality -Wno-self-assign -Wno-tautological-compare -Wno-unused-parameter -Wno-unused-value -Wsuggest-attribute=format -Wsuggest-attribute=noreturn -Wunused-variable
-cppflags = 
-CCDLFLAGS = -fPIC
-CFLAGS   = $(CCDLFLAGS) -O2  -fexceptions -g -grecord-gcc-switches -pipe -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -specs=/usr/lib/rpm/redhat/redhat-hardened-cc1 -fstack-protector-strong -specs=/usr/lib/rpm/redhat/redhat-annobin-cc1  -mbranch-protection=standard -fasynchronous-unwind-tables -fstack-clash-protection -fPIC  $(ARCH_FLAG)
-INCFLAGS = -I. -I$(arch_hdrdir) -I$(hdrdir)/ruby/backward -I$(hdrdir) -I$(srcdir) 
-DEFS     = 
-CPPFLAGS =   $(DEFS) $(cppflags)
-CXXFLAGS = $(CCDLFLAGS) -O2  -fexceptions -g -grecord-gcc-switches -pipe -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -specs=/usr/lib/rpm/redhat/redhat-hardened-cc1 -fstack-protector-strong -specs=/usr/lib/rpm/redhat/redhat-annobin-cc1  -mbranch-protection=standard -fasynchronous-unwind-tables -fstack-clash-protection  -fvisibility=hidden -std=c++11 $(ARCH_FLAG)
-ldflags  = -L. -Wl,-z,relro -Wl,--as-needed  -Wl,-z,now -specs=/usr/lib/rpm/redhat/redhat-hardened-ld  -fstack-protector-strong -rdynamic -Wl,-export-dynamic 
-dldflags = -Wl,-z,relro -Wl,--as-needed  -Wl,-z,now -specs=/usr/lib/rpm/redhat/redhat-hardened-ld  
-ARCH_FLAG = 
-DLDFLAGS = $(ldflags) $(dldflags) $(ARCH_FLAG)
-LDSHARED = $(CC) -shared
-LDSHAREDXX = $(CXX) -shared
-AR = gcc-ar
-EXEEXT = 
-
-RUBY_INSTALL_NAME = $(RUBY_BASE_NAME)
-RUBY_SO_NAME = ruby
-RUBYW_INSTALL_NAME = 
-RUBY_VERSION_NAME = $(RUBY_BASE_NAME)-$(ruby_version_dir_name)
-RUBYW_BASE_NAME = rubyw
-RUBY_BASE_NAME = ruby
-
-arch = aarch64-linux
-sitearch = $(arch)
-ruby_version = 3.0.0
-ruby = $(bindir)/$(RUBY_BASE_NAME)
-RUBY = $(ruby)
-ruby_headers = $(hdrdir)/ruby.h $(hdrdir)/ruby/backward.h $(hdrdir)/ruby/ruby.h $(hdrdir)/ruby/defines.h $(hdrdir)/ruby/missing.h $(hdrdir)/ruby/intern.h $(hdrdir)/ruby/st.h $(hdrdir)/ruby/subst.h $(arch_hdrdir)/ruby/config.h
-
-RM = rm -f
-RM_RF = $(RUBY) -run -e rm -- -rf
-RMDIRS = rmdir --ignore-fail-on-non-empty -p
-MAKEDIRS = /usr/bin/mkdir -p
-INSTALL = /usr/bin/install -c
-INSTALL_PROG = $(INSTALL) -m 0755
-INSTALL_DATA = $(INSTALL) -m 644
-COPY = cp
-TOUCH = exit >
-
-#### End of system configuration section. ####
-
-preload = 
-libpath = . $(archlibdir)
-LIBPATH =  -L. -L$(archlibdir)
-DEFFILE = 
-
-CLEANFILES = mkmf.log
-DISTCLEANFILES = 
-DISTCLEANDIRS = 
-
-extout = 
-extout_prefix = 
-target_prefix = 
-LOCAL_LIBS = 
-LIBS =   -lprotobuf -lpthread -lm   -lc
-ORIG_SRCS = base.cc embedding_feature_extractor.cc embedding_network.cc feature_extractor.cc feature_extractor.pb.cc feature_types.cc fixunicodevalue.cc fml_parser.cc generated_entities.cc generated_ulscript.cc getonescriptspan.cc lang_id_nn_params.cc language_identifier_features.cc nnet_language_identifier.cc nnet_language_identifier_c.cc offsetmap.cc registry.cc relevant_script_feature.cc sentence.pb.cc sentence_features.cc task_context.cc task_context_params.cc task_spec.pb.cc text_processing.cc unicodetext.cc utf8statetable.cc utils.cc workspace.cc
-SRCS = $(ORIG_SRCS) 
-OBJS = base.o embedding_feature_extractor.o embedding_network.o feature_extractor.o feature_extractor.pb.o feature_types.o fixunicodevalue.o fml_parser.o generated_entities.o generated_ulscript.o getonescriptspan.o lang_id_nn_params.o language_identifier_features.o nnet_language_identifier.o nnet_language_identifier_c.o offsetmap.o registry.o relevant_script_feature.o sentence.pb.o sentence_features.o task_context.o task_context_params.o task_spec.pb.o text_processing.o unicodetext.o utf8statetable.o utils.o workspace.o
-HDRS = $(srcdir)/base.h $(srcdir)/casts.h $(srcdir)/embedding_feature_extractor.h $(srcdir)/embedding_network.h $(srcdir)/embedding_network_params.h $(srcdir)/feature_extractor.h $(srcdir)/feature_extractor.pb.h $(srcdir)/feature_types.h $(srcdir)/fixunicodevalue.h $(srcdir)/float16.h $(srcdir)/fml_parser.h $(srcdir)/generated_ulscript.h $(srcdir)/getonescriptspan.h $(srcdir)/integral_types.h $(srcdir)/lang_id_nn_params.h $(srcdir)/language_identifier_features.h $(srcdir)/nnet_language_identifier.h $(srcdir)/offsetmap.h $(srcdir)/port.h $(srcdir)/registry.h $(srcdir)/relevant_script_feature.h $(srcdir)/script_detector.h $(srcdir)/sentence.pb.h $(srcdir)/sentence_features.h $(srcdir)/simple_adder.h $(srcdir)/stringpiece.h $(srcdir)/task_context.h $(srcdir)/task_context_params.h $(srcdir)/task_spec.pb.h $(srcdir)/text_processing.h $(srcdir)/unicodetext.h $(srcdir)/utf8acceptinterchange.h $(srcdir)/utf8prop_lettermarkscriptnum.h $(srcdir)/utf8repl_lettermarklower.h $(srcdir)/utf8scannot_lettermarkspecial.h $(srcdir)/utf8statetable.h $(srcdir)/utils.h $(srcdir)/workspace.h
-LOCAL_HDRS = 
-TARGET = libcld3
-TARGET_NAME = libcld3
-TARGET_ENTRY = Init_$(TARGET_NAME)
-DLLIB = $(TARGET).so
-EXTSTATIC = 
-STATIC_LIB = 
-
-TIMESTAMP_DIR = .
-BINDIR        = $(bindir)
-RUBYCOMMONDIR = $(sitedir)$(target_prefix)
-RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
-RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
-HDRDIR        = $(sitehdrdir)$(target_prefix)
-ARCHHDRDIR    = $(sitearchhdrdir)$(target_prefix)
-TARGET_SO_DIR =
-TARGET_SO     = $(TARGET_SO_DIR)$(DLLIB)
-CLEANLIBS     = $(TARGET_SO) 
-CLEANOBJS     = *.o  *.bak
-
-all:    $(DLLIB)
-static: $(STATIC_LIB)
-.PHONY: all install static install-so install-rb
-.PHONY: clean clean-so clean-static clean-rb
-
-clean-static::
-clean-rb-default::
-clean-rb::
-clean-so::
-clean: clean-so clean-static clean-rb-default clean-rb
-		-$(Q)$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES) .*.time
-
-distclean-rb-default::
-distclean-rb::
-distclean-so::
-distclean-static::
-distclean: clean distclean-so distclean-static distclean-rb-default distclean-rb
-		-$(Q)$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
-		-$(Q)$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
-		-$(Q)$(RMDIRS) $(DISTCLEANDIRS) 2> /dev/null || true
-
-realclean: distclean
-install: install-so install-rb
-
-install-so: $(DLLIB) $(TIMESTAMP_DIR)/.sitearchdir.time
-	$(INSTALL_PROG) $(DLLIB) $(RUBYARCHDIR)
-clean-static::
-	-$(Q)$(RM) $(STATIC_LIB)
-install-rb: pre-install-rb do-install-rb install-rb-default
-install-rb-default: pre-install-rb-default do-install-rb-default
-pre-install-rb: Makefile
-pre-install-rb-default: Makefile
-do-install-rb:
-do-install-rb-default:
-pre-install-rb-default:
-	@$(NULLCMD)
-$(TIMESTAMP_DIR)/.sitearchdir.time:
-	$(Q) $(MAKEDIRS) $(@D) $(RUBYARCHDIR)
-	$(Q) $(TOUCH) $@
-
-site-install: site-install-so site-install-rb
-site-install-so: install-so
-site-install-rb: install-rb
-
-.SUFFIXES: .c .m .cc .mm .cxx .cpp .o .S
-
-.cc.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.cc.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-.mm.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.mm.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-.cxx.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.cxx.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-.cpp.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.cpp.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-.c.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.c.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-.m.o:
-	$(ECHO) compiling $(<)
-	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -c $(CSRCFLAG)$<
-
-.m.S:
-	$(ECHO) translating $(<)
-	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -S $(CSRCFLAG)$<
-
-$(TARGET_SO): $(OBJS) Makefile
-	$(ECHO) linking shared-object $(DLLIB)
-	-$(Q)$(RM) $(@)
-	$(Q) $(LDSHAREDXX) -o $@ $(OBJS) $(LIBPATH) $(DLDFLAGS) $(LOCAL_LIBS) $(LIBS)
-
-
-
-$(OBJS): $(HDRS) $(ruby_headers)