ansj_seg 0.0.5-java

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 977533c05998577f3a417f3f074a31873b94dfec
+  data.tar.gz: 8bd5a644c16111c097d958ad5fc9349139b39379
+SHA512:
+  metadata.gz: caa06fda8c4eec4468444ee3708a51eb0752b3e986f7258153969943245ff7117f1bedd337a1ba4e413dd7e8e8494b4b80e5af1441bec405b79d3d93a8b8ed20
+  data.tar.gz: 2b79703de604e3e725bb925c2f7be6d1d5076181199847077e0ffb50efee116b01965fd22ff35f91a8c07f20dda83ad8ceb8229cd11af1bb2fcf0f48470adb41

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.DS_Store

data/.ruby-version

@@ -0,0 +1 @@
+jruby-9.1.6.0

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in ansj_seg-jruby.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Howl王
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,106 @@
+# Ansj中文分词 for JRuby
+
+## 引用原项目摘要
+> 这是一个基于 n-Gram + CRF + HMM 的中文分词的 Java 实现。
+
+> 分词速度达到每秒钟大约 200万字左右（原作者 MacbookAir 下测试），准确率能达到 96% 以上
+
+> 目前实现了 中文分词、中文姓名识别、用户自定义词典、关键字提取、自动摘要、关键字标记等功能。
+
+> 可以应用到自然语言处理等方面，适用于对分词效果要求高的各种项目。
+
+Read Ansj中文分词 docs for more details: http://nlpchina.github.io/ansj_seg
+
+## Installing
+
+Add to your `Gemfile`:
+
+```ruby
+gem 'ansj_seg'
+```
+
+Then `bundle install`.
+
+Or install it yourself as:
+
+    $ gem install ansj_seg
+
+## Usage
+
+```ruby
+require 'jrjackson' # 可选项， JRuby 下最快的 json 解析器， 需要提前：gem install jrjackson -V 
+require 'ansj_seg'
+
+# 设置用户（默认）词典
+AnsjSeg::Config::DIC['dic'] = '/Users/howl/Desktop/library/default.dic'
+# 设置用户自定义词典，key 的规则是以 dic_ 为前缀
+AnsjSeg::Config::DIC['dic_souhu'] = '/Users/howl/Desktop/library/souhu.dic'
+# 设置CRF模型，用户自定义CRF模型时，key 的规则是以 crf_ 为前缀
+AnsjSeg::Config::CRF['crf'] = '/Users/howl/Desktop/library/crf.model'
+# 设置歧义词典
+AnsjSeg::Config.ambiguityLibrary = '/Users/howl/Desktop/library/ambiguity.dic'
+
+# 设置过滤器(过滤：词性为空或标点，是和的)
+AnsjSeg.fitler.ignore(natures: ['null', 'w'], words: ['是', '的'])
+
+text = "Ruby China，对！没错！这里就是 Ruby 社区，目前这里已经是国内最权威的 Ruby 社区，拥有国内所有资深的 Ruby 工程师。"
+```
+
+```ruby
+# 分词
+# 第二个参数可选：:to, :nlp, :index 三种分词模式
+text.to_a(:terms) # text.to_a(:terms, :nlp)
+```
+> 
+```ruby
+[
+  {:name=>"ruby", :natureStr=>"en", :newWord=>false, :offe=>0, :realName=>"ruby"},
+  {:name=>"china", :natureStr=>"en", :newWord=>false, :offe=>5, :realName=>"china"},
+  {:name=>"对", :natureStr=>"p", :newWord=>false, :offe=>11, :realName=>"对"},
+  {:name=>"没错", :natureStr=>"v", :newWord=>false, :offe=>13, :realName=>"没错"},
+  {:name=>"这里", :natureStr=>"r", :newWord=>false, :offe=>16, :realName=>"这里"},
+  {:name=>"就", :natureStr=>"d", :newWord=>false, :offe=>18, :realName=>"就"},
+  {:name=>"ruby", :natureStr=>"en", :newWord=>false, :offe=>21, :realName=>"ruby"},
+  {:name=>"社区", :natureStr=>"n", :newWord=>false, :offe=>26, :realName=>"社区"},
+  {:name=>"目前", :natureStr=>"t", :newWord=>false, :offe=>29, :realName=>"目前"},
+  {:name=>"这", :natureStr=>"r", :newWord=>false, :offe=>31, :realName=>"这"},
+  {:name=>"里", :natureStr=>"f", :newWord=>false, :offe=>32, :realName=>"里"},
+  {:name=>"已经", :natureStr=>"d", :newWord=>false, :offe=>33, :realName=>"已经"},
+  {:name=>"国内", :natureStr=>"s", :newWord=>false, :offe=>36, :realName=>"国内"},
+  {:name=>"最", :natureStr=>"d", :newWord=>false, :offe=>38, :realName=>"最"},
+  {:name=>"权威", :natureStr=>"n", :newWord=>false, :offe=>39, :realName=>"权威"},
+  {:name=>"ruby", :natureStr=>"en", :newWord=>false, :offe=>43, :realName=>"ruby"},
+  {:name=>"社区", :natureStr=>"n", :newWord=>false, :offe=>48, :realName=>"社区"},
+  {:name=>"拥有", :natureStr=>"v", :newWord=>false, :offe=>51, :realName=>"拥有"},
+  {:name=>"国内", :natureStr=>"s", :newWord=>false, :offe=>53, :realName=>"国内"},
+  {:name=>"所有", :natureStr=>"b", :newWord=>false, :offe=>55, :realName=>"所有"},
+  {:name=>"资深", :natureStr=>"b", :newWord=>false, :offe=>57, :realName=>"资深"},
+  {:name=>"ruby", :natureStr=>"en", :newWord=>false, :offe=>61, :realName=>"ruby"},
+  {:name=>"工程师", :natureStr=>"n", :newWord=>false, :offe=>66, :realName=>"工程师"}
+]
+```
+
+```ruby
+# 提取关键词
+# 第二个参数定义分词个数，默认：20
+text.to_a(:words) # text.to_a(:words, 5)
+```
+> 
+```ruby
+[
+  {:freq=>2, :name=>"这里", :score=>16.315514814428745},
+  {:freq=>2, :name=>"社区", :score=>14.99970404519092},
+  {:freq=>2, :name=>"国内", :score=>13.684318222044968},
+  {:freq=>1, :name=>"目前", :score=>5.3946562994797125},
+  {:freq=>1, :name=>"已经", :score=>4.868333845606951},
+  {:freq=>1, :name=>"权威", :score=>4.078866889481741},
+  {:freq=>1, :name=>"所有", :score=>1.973668895869867},
+  {:freq=>1, :name=>"资深", :score=>1.7105130430872182},
+  {:freq=>1, :name=>"没错", :score=>1.4999705998354727},
+  {:freq=>1, :name=>"就是", :score=>1.3683942314288522},
+  {:freq=>1, :name=>"工程师", :score=>0.5263054050944183},
+  {:freq=>1, :name=>"拥有", :score=>0.4999901999451576}
+]
+```
+
+*PS.* Built and tested on JRuby 9.1.6

data/Rakefile

@@ -0,0 +1,20 @@
+#-*- mode: ruby -*-
+require 'ruby-maven'
+
+desc "Pack jar after compiling classes"
+task :compile do
+  RubyMaven.exec('prepare-package')
+end
+
+desc "Clean build"
+task :clean do
+  RubyMaven.exec('clean')
+end
+
+task :default => [ :compile ]
+
+require 'rubygems/package_task'
+Gem::PackageTask.new( eval File.read( 'ansj_seg.gemspec' ) ) do
+  desc 'Pack gem'
+  task :package => [:compile]
+end

data/ansj_seg.gemspec

@@ -0,0 +1,30 @@
+# -*- encoding: utf-8 -*-
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ansj_seg/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ansj_seg"
+  spec.version       = AnsjSeg::VERSION
+  spec.authors       = ["Howl王"]
+  spec.email         = ["mimosa@aliyun.com"]
+  spec.description   = %q{AnsjSeg for jRuby}
+  spec.summary       = %q{ansj_seg for jRuby}
+  spec.homepage      = "https://github.com/NLPchina/ansj_seg"
+  spec.license       = "MIT"
+  # important to get the jars installed
+  spec.platform = 'java'
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.requirements << 'jar org.nlpcn, nlp-lang, 1.7'
+  spec.requirements << 'jar org.ansj, ansj_seg, 5.0.1'
+
+  spec.add_runtime_dependency 'ruby-maven', '~> 3.3', '>= 3.3.12'
+  spec.add_runtime_dependency 'jar-dependencies', '~> 0.3.5'
+  spec.add_runtime_dependency 'multi_json', '~> 1.12', '>= 1.12.1'
+end

data/ansj_seg.rb

@@ -0,0 +1,3 @@
+# -*- encoding: utf-8 -*-
+
+require 'lib/ansj_seg'

data/lib/ansj_seg.rb

@@ -0,0 +1,93 @@
+# -*- encoding: utf-8 -*-
+unless RUBY_PLATFORM =~ /java/
+  puts 'This library is only compatible with a java-based ruby environment like JRuby.'
+  exit 255
+end
+
+require 'ansj_seg_jars'
+require 'multi_json'
+
+module AnsjSeg
+  def self.fitler
+    @fitler ||= Filter.new
+  end
+
+  class Filter < Java::OrgAnsjRecognitionImpl::FilterRecognition
+    def ignore(opts = { natures: ['null', 'w'], words: ['是', '的'] })
+      if opts[:natures].is_a?(Array) && !opts[:natures].empty?
+        self.insertStopNatures(*opts.delete(:natures))
+      end
+
+      if opts[:words].is_a?(Array) && !opts[:words].empty?
+        self.insertStopWords(opts.delete(:words))
+      end
+
+      if opts[:regex].is_a?(Array) && !opts[:regex].empty?
+        opts.delete(:regex).map { |r|  self.insertStopRegex(r) }
+      end
+    end
+
+    def ignore!(opts = {})
+      self.ignore(opts)
+      self
+    end
+  end
+
+  class Config < Java::OrgAnsjUtil::MyStaticValue
+  end
+
+  module JSON
+    extend MultiJson
+    
+    def self.trans(obj)
+      json = self.dump(obj).to_s
+      self.load(json, use_bigdecimal: false, symbolize_keys: true)
+    end
+  end
+
+  module String
+    include_package 'org.ansj.splitWord.analysis'
+
+    def to_a(pattern = nil, limit = 0)
+      case pattern.to_s
+      when /terms/
+        split_terms(limit)
+      when /words/
+        split_words(limit)
+      else
+        split(pattern, limit) 
+      end
+    end
+    alias_method :拆, :to_a
+
+    private
+
+      def split_terms(mode = nil)
+        klass = case mode.to_s
+        when /to/
+          ToAnalysis
+        when /nlp/
+          NlpAnalysis
+        when /index/
+          IndexAnalysis
+        else
+          BaseAnalysis
+        end
+
+        JSON.trans klass.parse(self).recognition(AnsjSeg.fitler.ignore!).getTerms
+      end
+
+      def split_words(limit = 0)
+        limit = if limit.to_i == 0
+          20
+        else
+          limit
+        end
+
+        JSON.trans Java::OrgAnsjAppKeyword.KeyWordComputer.new(limit).computeArticleTfidf(self)
+      end
+  end
+
+end # AnsjSeg
+
+String.send(:include, AnsjSeg::String)

data/lib/ansj_seg/version.rb

@@ -0,0 +1,5 @@
+# -*- encoding: utf-8 -*-
+
+module AnsjSeg
+  VERSION = '0.0.5'
+end

data/lib/src/main/java/org/ansj/SegApi.java

@@ -0,0 +1,39 @@
+package org.ansj;
+
+import org.ansj.splitWord.analysis.ToAnalysis;
+import org.ansj.splitWord.analysis.NlpAnalysis;
+import org.ansj.app.keyword.KeyWordComputer;
+
+public class SegApi {
+  
+  /**
+   * 分词服务，默认 ToAnalysis 分词
+   * @param content 需要分词的文本
+   * @return 分词后的结果集
+   */
+  @Execute
+  public Object toSeg(String content){
+    return ToAnalysis.parse(content).getTerms();
+  }
+  
+  /**
+   * 分词服务，默认 NlpAnalysis 分词
+   * @param content 需要分词的文本
+   * @return 分词后的结果集
+   */
+  @Execute
+  public Object nlpSeg(String content){
+    return NlpAnalysis.parse(content).getTerms();
+  }
+  
+  /**
+   * 关键词抽取
+   * @param content 需要抽取关键词的文本
+   * @return 关键词的结果集
+   */
+  @Execute
+  public Object keyWord(String content){
+    return new KeyWordComputer(20).computeArticleTfidf(content);
+  }
+  
+}

data/settings.xml

@@ -0,0 +1,17 @@
+<?xml version='1.0'?>
+<settings>
+  <profiles>
+    <profile>
+      <id>ansj_seg</id>
+      <repositories>
+        <repository>
+          <id>mvn-repo</id>
+          <url>http://maven.nlpcn.org/</url>
+        </repository>
+      </repositories>
+    </profile>
+  </profiles>
+  <activeProfiles>
+    <activeProfile>ansj_seg</activeProfile>
+  </activeProfiles>
+</settings>

metadata

@@ -0,0 +1,112 @@
+--- !ruby/object:Gem::Specification
+name: ansj_seg
+version: !ruby/object:Gem::Version
+  version: 0.0.5
+platform: java
+authors:
+- Howl王
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2016-11-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.12
+  name: ruby-maven
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.12
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.5
+  name: jar-dependencies
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.5
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.12.1
+  name: multi_json
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.12.1
+description: AnsjSeg for jRuby
+email:
+- mimosa@aliyun.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".ruby-version"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- ansj_seg.gemspec
+- ansj_seg.rb
+- lib/ansj_seg.rb
+- lib/ansj_seg/version.rb
+- lib/src/main/java/org/ansj/SegApi.java
+- settings.xml
+homepage: https://github.com/NLPchina/ansj_seg
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements:
+- jar org.nlpcn, nlp-lang, 1.7
+- jar org.ansj, ansj_seg, 5.0.1
+rubyforge_project:
+rubygems_version: 2.6.8
+signing_key:
+specification_version: 4
+summary: ansj_seg for jRuby
+test_files: []