commit: d5cabfe5c65ac29d2f9c151b46c01a9fd885a9e0
parent: af6a84da147f4230807b37c64bc09760e6ab5055
Author: Akihiko Odaki <akihiko.odaki.4i@stu.hosei.ac.jp>
Date: Wed, 10 May 2017 02:58:03 +0900
Use CLD3 (#2949)
Compact Language Detector v3 (CLD3) is the successor of CLD2, which was
used in the previous implementation. CLD3 includes improvements since CLD2,
and supports newer compilers. On the other hand, it has additional
requirements and cld3-ruby, the FFI of CLD3 for Ruby, is still new and may
be still inmature.
Though CLD3 is named after CLD2, it is implemented with a neural network
model, different from the old implementation, which is based on a Naïve
Bayesian classifier.
CLD3 supports newer compilers, such as GCC 6. CLD2 is not compatible with
GCC 6 because it assigns negative values to varibales typed unsigned.
(see internal/cld_generated_cjk_uni_prop_80.cc) The support for GCC 6 and
newer compilers are essential today, when some server operating system
such as Ubuntu Server 16.10 has GCC 6 by default.
On the one hand, CLD3 requires C++11 support. Environments with old
compilers such as Ubuntu Server 14.04 needs to update the system or install
a newer compiler.
CLD3 needs protocol buffers as a new dependency. However,it is not
considered problematic because major server operating systems, CentOS and
Ubuntu Server provide them.
The FFI cld3-ruby was written by me (Akihiko Odaki) for use in Mastodon.
It is still new and may be inmature, but confirmed to pass existing tests.
Diffstat:
7 files changed, 23 insertions(+), 15 deletions(-)
diff --git a/.travis.yml b/.travis.yml
@@ -13,9 +13,9 @@ env:
- LOCAL_DOMAIN=cb6e6126.ngrok.io
- LOCAL_HTTPS=true
- RAILS_ENV=test
- - CXX=g++-4.8
- NOKOGIRI_USE_SYSTEM_LIBRARIES=true
- PARALLEL_TEST_PROCESSORS=2
+ - "PATH=$HOME:$PATH"
addons:
postgresql: 9.4
@@ -24,8 +24,10 @@ addons:
- ubuntu-toolchain-r-test
- trusty-media
packages:
- - g++-4.8
- ffmpeg
+ - g++-6
+ - libprotobuf-dev
+ - protobuf-compiler
rvm:
- 2.3.4
@@ -43,6 +45,7 @@ install:
before_script:
- bundle exec rake parallel:create parallel:load_schema parallel:prepare
- bundle exec rails assets:precompile
+ - ln -s /usr/bin/x86_64-linux-gnu-g++-6 "$HOME/g++"
script:
- bundle exec parallel_test spec/ --group-by filesize --type rspec
diff --git a/Dockerfile b/Dockerfile
@@ -16,7 +16,8 @@ RUN echo "@edge https://nl.alpinelinux.org/alpine/edge/main" >> /etc/apk/reposit
libxml2-dev \
libxslt-dev \
python \
- build-base" \
+ build-base \
+ protobuf-dev" \
&& apk -U upgrade && apk add \
$BUILD_DEPS \
nodejs@edge \
@@ -29,6 +30,7 @@ RUN echo "@edge https://nl.alpinelinux.org/alpine/edge/main" >> /etc/apk/reposit
file \
imagemagick@edge \
ca-certificates \
+ protobuf \
&& npm install -g npm@3 && npm install -g yarn \
&& update-ca-certificates \
&& rm -rf /tmp/* /var/cache/apk/*
diff --git a/Gemfile b/Gemfile
@@ -19,7 +19,7 @@ gem 'paperclip', '~> 5.1'
gem 'paperclip-av-transcoder'
gem 'addressable'
-gem 'cld2', require: 'cld'
+gem 'cld3', '~> 3.1.0'
gem 'devise'
gem 'devise-two-factor'
gem 'doorkeeper'
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -99,8 +99,8 @@ GEM
rack-test (>= 0.5.4)
xpath (~> 2.0)
chunky_png (1.3.8)
- cld2 (1.0.3)
- ffi (~> 1.9.3)
+ cld3 (3.1.0)
+ ffi (>= 1.1.0, < 1.10.0)
climate_control (0.1.0)
cocaine (0.5.8)
climate_control (>= 0.0.3, < 1.0)
@@ -480,7 +480,7 @@ DEPENDENCIES
capistrano-rbenv
capistrano-yarn
capybara
- cld2
+ cld3 (~> 3.1.0)
devise
devise-two-factor
doorkeeper
diff --git a/Vagrantfile b/Vagrantfile
@@ -33,7 +33,9 @@ sudo apt-get install \
redis-tools \
postgresql \
postgresql-contrib \
+ protobuf-compiler \
yarn \
+ libprotobuf-dev \
libreadline-dev \
-y
diff --git a/app/lib/language_detector.rb b/app/lib/language_detector.rb
@@ -6,6 +6,7 @@ class LanguageDetector
def initialize(text, account = nil)
@text = text
@account = account
+ @identifier = CLD3::NNetLanguageIdentifier.new(1, 2048)
end
def to_iso_s
@@ -15,15 +16,15 @@ class LanguageDetector
private
def detected_language_code
- detected_language[:code].to_sym if detected_language_reliable?
+ result.language.to_sym if detected_language_reliable?
end
- def detected_language
- @_detected_language ||= CLD.detect_language(text_without_urls)
+ def result
+ @result ||= @identifier.find_language(text_without_urls)
end
def detected_language_reliable?
- detected_language[:reliable]
+ result.reliable?
end
def text_without_urls
diff --git a/spec/lib/language_detector_spec.rb b/spec/lib/language_detector_spec.rb
@@ -24,15 +24,15 @@ describe LanguageDetector do
end
describe 'when language can\'t be detected' do
- it 'confirm language engine cant detect' do
- result = CLD.detect_language('')
- expect(result[:reliable]).to be false
+ it 'uses default locale when sent an empty document' do
+ result = described_class.new('').to_iso_s
+ expect(result).to eq :en
end
describe 'because of a URL' do
it 'uses default locale when sent just a URL' do
string = 'http://example.com/media/2kFTgOJLXhQf0g2nKB4'
- cld_result = CLD.detect_language(string)[:code]
+ cld_result = CLD3::NNetLanguageIdentifier.new(0, 2048).find_language(string)
expect(cld_result).not_to eq :en
result = described_class.new(string).to_iso_s
