chinese_sugar 0.0.1 → 0.0.2

data/lib/sugar.rb

@@ -1,4 +1,5 @@
 require "sugar/version"
+require "sugar/trie"
 
 module Sugar
   

data/lib/sugar/pinyin.rb

@@ -0,0 +1,18 @@
+require "sugar/version"
+module Sugar
+  class Pinyin
+    def initialize(options = {})
+      options = {with_tone: false}.merge(options)
+      dict = File.expand_path("../../data/pinyin.txt", __FILE__)
+      @hash = {}
+      File.read(dict).split("\n").map do |line|
+        key, *values = line.split(" ")
+        @hash[key] = options[:with_tone] ? values : values.map{|v| v[/[a-z]+/]}
+      end
+    end
+
+    def get(word)
+      @hash[word]
+    end
+  end
+end

data/lib/sugar/trie.rb

@@ -6,7 +6,7 @@ module Sugar
     attr_accessor :trie, :frequnces, :count
 
     def initialize
-      dict = File.expand_path("../../dict.txt", __FILE__)
+      dict = File.expand_path("../../data/phrase.txt", __FILE__)
       self.trie, self.frequnces, self.count = Sugar::Trie.build(dict)
     end
 

data/lib/sugar/version.rb

@@ -1,3 +1,3 @@
 module Sugar
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/spec/sugar_spec.rb

@@ -0,0 +1,15 @@
+require 'sugar'
+
+describe Sugar::Trie, "module" do
+  trie = Sugar::Trie.new
+  it "can segment word" do
+    trie.word?('江西').should be_true
+  end
+
+  it "can segment sentence" do
+    sentence = "江西是个好地方"
+    segmentation = trie.best_segmentation(sentence)
+    puts "\n" + sentence
+    puts segmentation.to_s
+  end
+end

data/sugar.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.authors       = ["binz"]
   spec.email         = ["xinkiang@gmail.com"]
   spec.summary       = %q{Chinese text data mining.}
-  spec.description   = %q{1.Chinese words segmentation using Trie and Viterbi}
+  spec.description   = %q{1.Chinese words segmentation using Trie and Viterbi;}
   spec.homepage      = "https://github.com/slacken/sugar"
   spec.license       = "MIT"
 
@@ -20,4 +20,5 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.5"
   spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: chinese_sugar
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - binz
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-16 00:00:00.000000000 Z
+date: 2014-06-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -38,7 +38,21 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: 1.Chinese words segmentation using Trie and Viterbi
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 1.Chinese words segmentation using Trie and Viterbi;
 email:
 - xinkiang@gmail.com
 executables: []
@@ -50,10 +64,13 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
-- lib/dict.txt
+- lib/data/phrase.txt
+- lib/data/pinyin.txt
 - lib/sugar.rb
+- lib/sugar/pinyin.rb
 - lib/sugar/trie.rb
 - lib/sugar/version.rb
+- spec/sugar_spec.rb
 - sugar.gemspec
 - sugar.rb
 homepage: https://github.com/slacken/sugar
@@ -80,4 +97,5 @@ rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Chinese text data mining.
-test_files: []
+test_files:
+- spec/sugar_spec.rb