cld 0.5.0 → 0.10.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,14 @@
1
+ AC_INIT(cld, 0.6.0)
2
+ AC_CONFIG_AUX_DIR(build_aux)
3
+ AM_INIT_AUTOMAKE(cld, 0.6.0)
4
+
5
+ LT_INIT
6
+
7
+ # Checks for a C++ compiler.
8
+ AC_PROG_CXX
9
+
10
+ # Check for stdc headers.
11
+ AC_HEADER_STDC
12
+
13
+ AC_CONFIG_FILES(Makefile)
14
+ AC_OUTPUT
data/ext/cld/extconf.rb CHANGED
@@ -1,2 +1,7 @@
1
1
  #require 'mkmf'
2
2
  #create_makefile('cld/cld')
3
+
4
+ ENV['CFLAGS'] = ENV['CFLAGS'].to_s + ' -Wno-narrowing'
5
+ ENV['CXXFLAGS'] = ENV['CXXFLAGS'].to_s + ' -Wno-narrowing'
6
+
7
+ system "./configure --prefix=#{Dir.pwd}" unless File.exists?('Makefile')
@@ -58,8 +58,7 @@ static const LanguageInfo kLanguageInfoTable[] = {
58
58
  { "IRISH", "ga", "gle", NULL},
59
59
  { "GALICIAN", "gl", "glg", NULL},
60
60
  // Impossible to tell Tagalog from Filipino at the moment.
61
- // Use ISO 639-2 code for Filipino here.
62
- { "TAGALOG", NULL, "fil", NULL},
61
+ { "TAGALOG", "tl", "tgl", NULL},
63
62
  { "TURKISH", "tr", "tur", NULL},
64
63
  { "UKRAINIAN", "uk", "ukr", NULL},
65
64
  { "HINDI", "hi", "hin", NULL},
data/ext/cld/thunk.cc CHANGED
@@ -12,8 +12,7 @@ typedef struct {
12
12
  } RESULT;
13
13
 
14
14
  extern "C" {
15
- RESULT detectLanguageThunkInt(const char * src) {
16
- bool is_plain_text = true;
15
+ RESULT detectLanguageThunkInt(const char * src, bool is_plain_text) {
17
16
  bool do_allow_extended_languages = true;
18
17
  bool do_pick_summary_language = false;
19
18
  bool do_remove_weak_matches = false;
data/lib/cld.rb CHANGED
@@ -4,8 +4,8 @@ require "ffi"
4
4
  module CLD
5
5
  extend FFI::Library
6
6
 
7
- def self.detect_language(text)
8
- result = detect_language_ext(text)
7
+ def self.detect_language(text, is_plain_text=true)
8
+ result = detect_language_ext(text.to_s, is_plain_text)
9
9
  Hash[ result.members.map {|member| [member.to_sym, result[member]]} ]
10
10
  end
11
11
 
@@ -16,6 +16,6 @@ module CLD
16
16
  end
17
17
 
18
18
  GEM_ROOT = File.expand_path("../../", __FILE__)
19
- ffi_lib "#{GEM_ROOT}/ext/cld/cld.so"
20
- attach_function "detect_language_ext","detectLanguageThunkInt", [:buffer_in], ReturnValue.by_value
19
+ ffi_lib "#{GEM_ROOT}/ext/cld/lib/cld.so"
20
+ attach_function "detect_language_ext","detectLanguageThunkInt", [:buffer_in, :bool], ReturnValue.by_value
21
21
  end
data/lib/cld/version.rb CHANGED
@@ -1,3 +1,3 @@
1
1
  module CLD
2
- VERSION = "0.5.0"
2
+ VERSION = "0.10.0"
3
3
  end
metadata CHANGED
@@ -1,57 +1,42 @@
1
- --- !ruby/object:Gem::Specification
1
+ --- !ruby/object:Gem::Specification
2
2
  name: cld
3
- version: !ruby/object:Gem::Version
4
- prerelease:
5
- version: 0.5.0
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.10.0
6
5
  platform: ruby
7
- authors:
6
+ authors:
8
7
  - Jason Toy
9
8
  autorequire:
10
9
  bindir: bin
11
10
  cert_chain: []
12
-
13
- date: 2012-02-11 00:00:00 Z
14
- dependencies:
15
- - !ruby/object:Gem::Dependency
11
+ date: 2021-07-20 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
16
14
  name: ffi
17
- prerelease: false
18
- requirement: &id001 !ruby/object:Gem::Requirement
19
- none: false
20
- requirements:
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
21
17
  - - ">="
22
- - !ruby/object:Gem::Version
23
- version: "0"
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
24
20
  type: :runtime
25
- version_requirements: *id001
26
- - !ruby/object:Gem::Dependency
27
- name: rspec
28
21
  prerelease: false
29
- requirement: &id002 !ruby/object:Gem::Requirement
30
- none: false
31
- requirements:
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
32
24
  - - ">="
33
- - !ruby/object:Gem::Version
34
- version: "0"
35
- type: :development
36
- version_requirements: *id002
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
37
27
  description: Compact Language Detection for Ruby
38
- email:
28
+ email:
39
29
  - jtoy@jtoy.net
40
30
  executables: []
41
-
42
- extensions:
31
+ extensions:
43
32
  - ext/cld/extconf.rb
44
33
  extra_rdoc_files: []
45
-
46
- files:
47
- - .gitignore
48
- - .rspec
49
- - Gemfile
34
+ files:
50
35
  - LICENSE
51
36
  - README.md
52
- - Rakefile
53
- - cld.gemspec
54
- - ext/cld/Makefile
37
+ - ext/cld/Makefile.am
38
+ - ext/cld/Makefile.in
39
+ - ext/cld/aclocal.m4
55
40
  - ext/cld/base/basictypes.h
56
41
  - ext/cld/base/build_config.h
57
42
  - ext/cld/base/casts.h
@@ -71,7 +56,15 @@ files:
71
56
  - ext/cld/base/template_util.h
72
57
  - ext/cld/base/type_traits.h
73
58
  - ext/cld/base/vlog_is_on.h
59
+ - ext/cld/build_aux/config.guess
60
+ - ext/cld/build_aux/config.sub
61
+ - ext/cld/build_aux/depcomp
62
+ - ext/cld/build_aux/install-sh
63
+ - ext/cld/build_aux/ltmain.sh
64
+ - ext/cld/build_aux/missing
74
65
  - ext/cld/cld_encodings.h
66
+ - ext/cld/configure
67
+ - ext/cld/configure.ac
75
68
  - ext/cld/encodings/compact_lang_det/#cldutil.cc#
76
69
  - ext/cld/encodings/compact_lang_det/#cldutil.h#
77
70
  - ext/cld/encodings/compact_lang_det/#compact_lang_det_impl.h#
@@ -151,35 +144,26 @@ files:
151
144
  - ext/cld/thunk.cc
152
145
  - lib/cld.rb
153
146
  - lib/cld/version.rb
154
- - spec/cld_spec.rb
155
- - spec/spec_helper.rb
156
- homepage: http://github.com/jtoy/cld
147
+ homepage: https://github.com/jtoy/cld
157
148
  licenses: []
158
-
149
+ metadata: {}
159
150
  post_install_message:
160
151
  rdoc_options: []
161
-
162
- require_paths:
152
+ require_paths:
163
153
  - lib
164
- required_ruby_version: !ruby/object:Gem::Requirement
165
- none: false
166
- requirements:
154
+ required_ruby_version: !ruby/object:Gem::Requirement
155
+ requirements:
167
156
  - - ">="
168
- - !ruby/object:Gem::Version
169
- version: "0"
170
- required_rubygems_version: !ruby/object:Gem::Requirement
171
- none: false
172
- requirements:
157
+ - !ruby/object:Gem::Version
158
+ version: '0'
159
+ required_rubygems_version: !ruby/object:Gem::Requirement
160
+ requirements:
173
161
  - - ">="
174
- - !ruby/object:Gem::Version
175
- version: "0"
162
+ - !ruby/object:Gem::Version
163
+ version: '0'
176
164
  requirements: []
177
-
178
- rubyforge_project:
179
- rubygems_version: 1.8.11
165
+ rubygems_version: 3.2.16
180
166
  signing_key:
181
- specification_version: 3
167
+ specification_version: 4
182
168
  summary: Compact Language Detection for Ruby
183
- test_files:
184
- - spec/cld_spec.rb
185
- - spec/spec_helper.rb
169
+ test_files: []
data/.gitignore DELETED
@@ -1,20 +0,0 @@
1
- *.gem
2
- *.rbc
3
- .bundle
4
- .config
5
- .yardoc
6
- Gemfile.lock
7
- InstalledFiles
8
- _yardoc
9
- coverage
10
- doc/
11
- lib/bundler/man
12
- pkg
13
- rdoc
14
- spec/reports
15
- test/tmp
16
- test/version_tmp
17
- tmp
18
- ext/cld/*.o
19
- ext/cld/*.a
20
- ext/cld/*.so
data/.rspec DELETED
@@ -1,2 +0,0 @@
1
- --color
2
- --format documentation
data/Gemfile DELETED
@@ -1,6 +0,0 @@
1
- source 'https://rubygems.org'
2
-
3
- # Specify your gem's dependencies in cld.gemspec
4
- gemspec
5
-
6
- gem "rake"
data/Rakefile DELETED
@@ -1,5 +0,0 @@
1
- #!/usr/bin/env rake
2
- require "bundler/gem_tasks"
3
-
4
- require "rspec/core/rake_task"
5
- RSpec::Core::RakeTask.new("spec")
data/cld.gemspec DELETED
@@ -1,22 +0,0 @@
1
- # -*- encoding: utf-8 -*-
2
- require File.expand_path('../lib/cld/version', __FILE__)
3
-
4
- Gem::Specification.new do |gem|
5
- gem.authors = ["Jason Toy"]
6
- gem.email = ["jtoy@jtoy.net"]
7
- gem.description = %q{Compact Language Detection for Ruby}
8
- gem.summary = %q{Compact Language Detection for Ruby}
9
- gem.homepage = "http://github.com/jtoy/cld"
10
-
11
- gem.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
12
- gem.files = `git ls-files`.split("\n")
13
- gem.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
14
- gem.extensions = ["ext/cld/extconf.rb"]
15
- gem.name = "cld"
16
- gem.require_paths = ["lib"]
17
- gem.version = CLD::VERSION
18
-
19
- gem.add_dependency "ffi"
20
-
21
- gem.add_development_dependency "rspec"
22
- end
data/ext/cld/Makefile DELETED
@@ -1,31 +0,0 @@
1
- CFLAGS=-fPIC -I. -O2 -DCLD_WINDOWS
2
- LDFLAGS=-L.
3
- CC=g++
4
- AR=ar
5
- SOURCES=encodings/compact_lang_det/cldutil.cc \
6
- encodings/compact_lang_det/cldutil_dbg_empty.cc \
7
- encodings/compact_lang_det/compact_lang_det.cc \
8
- encodings/compact_lang_det/compact_lang_det_impl.cc \
9
- encodings/compact_lang_det/ext_lang_enc.cc \
10
- encodings/compact_lang_det/getonescriptspan.cc \
11
- encodings/compact_lang_det/letterscript_enum.cc \
12
- encodings/compact_lang_det/tote.cc \
13
- encodings/compact_lang_det/generated/cld_generated_score_quadchrome_0406.cc \
14
- encodings/compact_lang_det/generated/compact_lang_det_generated_cjkbis_0.cc \
15
- encodings/compact_lang_det/generated/compact_lang_det_generated_ctjkvz.cc \
16
- encodings/compact_lang_det/generated/compact_lang_det_generated_deltaoctachrome.cc \
17
- encodings/compact_lang_det/generated/compact_lang_det_generated_quadschrome.cc \
18
- encodings/compact_lang_det/win/cld_htmlutils_windows.cc \
19
- encodings/compact_lang_det/win/cld_unilib_windows.cc \
20
- encodings/compact_lang_det/win/cld_utf8statetable.cc \
21
- encodings/compact_lang_det/win/cld_utf8utils_windows.cc \
22
- encodings/internal/encodings.cc \
23
- languages/internal/languages.cc \
24
- thunk.cc
25
-
26
- install:
27
- rm -f *.o
28
- rm -f libcld.a
29
- $(CC) -c $(CFLAGS) $(SOURCES)
30
- $(AR) rcs libcld.a *.o
31
- $(CC) -DCLD_WINDOWS -I. -L. -shared -o cld.so -lstdc++ *.o
data/spec/cld_spec.rb DELETED
@@ -1,44 +0,0 @@
1
- # encoding: UTF-8
2
- require "spec_helper"
3
-
4
- describe CLD do
5
-
6
- context "English text" do
7
- subject { CLD.detect_language("This is a test") }
8
-
9
- it { subject[:name].should eq("ENGLISH") }
10
- it { subject[:code].should eq("en") }
11
- it { subject[:reliable].should be_true }
12
- end
13
-
14
- context "French text" do
15
- subject { CLD.detect_language("plus ça change, plus c'est la même chose") }
16
-
17
- it { subject[:name].should eq("FRENCH") }
18
- it { subject[:code].should eq("fr") }
19
- it { subject[:reliable].should be_true }
20
- end
21
-
22
- context "Simplified Chinese text" do
23
- subject { CLD.detect_language("你好吗箭体") }
24
-
25
- it { subject[:name].should eq("Chinese") }
26
- it { subject[:code].should eq("zh") }
27
- end
28
-
29
- context "Traditional Chinese text" do
30
- subject { CLD.detect_language("你好嗎繁體") }
31
-
32
- it { subject[:name].should eq("ChineseT") }
33
- it { subject[:code].should eq("zh-TW") }
34
- end
35
-
36
- context "Unknown text" do
37
- subject { CLD.detect_language("") }
38
-
39
- it { subject[:name].should eq("Unknown") }
40
- it { subject[:code].should eq("un") }
41
- it { subject[:reliable].should be_true }
42
- end
43
-
44
- end
data/spec/spec_helper.rb DELETED
@@ -1,6 +0,0 @@
1
- require "rubygems"
2
- require "bundler/setup"
3
- Bundler.require(:default)
4
-
5
- RSpec.configure do |config|
6
- end