cseg 0.0.5 → 0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2e72d6d7a3b9559d28b26af6b3b8e65749e4b3a3
+  data.tar.gz: d4c8bec5d8e91cb20e39df81dd0e69eef7b690f7
+SHA512:
+  metadata.gz: bdf2ab1fea49f6773a5098983f6e11fe2b7afc416ab62df0bf01cdccce08e4e8fdcaf5688721dc66be5155ffae600f92866244ebc809418c6aa1838a73aac3fa
+  data.tar.gz: 3306478b36f552272388f4be4c64dbcea6f2a8d786faf47aadcbc99cc1b4ba181dce1557105fe015a6e9d2f9af4fdd5e3e11e8b7f0187bcafe84618b6eb6120f

data/.gitignore

@@ -15,3 +15,4 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+data/

data/README.md

@@ -1,9 +1,10 @@
-# Cseg
+# Kurumi
 
 Use MIRA to train a large amount of features.
 
-Segment chinese sentences into words in high speed and correctly.
+Segment chinese(both traditional and simplized) sentences into words in high speed and correctly.
 
+take care the name of the gem is different from the repo name!
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -18,9 +19,7 @@ Or install it yourself as:
 
     $ gem install cseg
 
-you need to install CRF++ first and set the environment variables.
-
-Here is the site of CRF++<http://crfpp.googlecode.com/svn/trunk/doc/index.html> and you should follow the manual
+you need to install [CRF++](http://crfpp.googlecode.com/svn/trunk/doc/index.html?source=navbar) first and set the environment variables.
 
 On github the dictionary file was deleted since it is quite large, though you can get all from rubygems.
 
@@ -34,17 +33,15 @@ Recall: 92.86%
 	
 ## Usage
 
+```
+The default is Simplified Chinese
     require "cseg"
-    a=Kurumi.segment("屌丝是一种自我讽刺")  
-    =>屌丝/是/一/种/自我/讽刺
-	
-	the result will be an array.
-	
+    a=Kurumi.segment("屌丝是一种自我讽刺。")
+=>["屌丝", "是", "一", "种", "自我", "讽刺", "。"]
+Use parameter "tr" to specify Traditional Chinese
+    a=Kurumi.segment("台妹真是正點。","tr")  
+=>["台妹", "真", "是", "正點", "。"]	
 
-## Contributing
+```	
 
-1. Fork it
-2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Commit your changes (`git commit -am 'Add some feature'`)
-4. Push to the branch (`git push origin my-new-feature`)
-5. Create new Pull Request
+## Contributing

data/cseg.gemspec

@@ -8,8 +8,8 @@ Gem::Specification.new do |gem|
   gem.version       = Cseg::VERSION
   gem.authors       = ["gyorou"]
   gem.email         = ["gyorou@tjjtds.com"]
-  gem.description   = %q{"a chinese segmentation tool using CRF++"}
-  gem.summary       = %q{"CRF++ should be installed and set in the environment variables"}
+  gem.description   = %q{"a chinese segmentation tool using CRF"}
+  gem.summary       = %q{""}
   gem.homepage      = ""
 
   gem.files         = [".gitignore",
@@ -17,6 +17,7 @@ Gem::Specification.new do |gem|
 						"README.md",
 						"Gemfile",
 						"data/pkumodle.data",
+						"data/as_training_less.data",
 						"lib/cseg/version.rb",
 						"lib/cseg.rb",
 						"cseg.gemspec",

data/lib/cseg.rb

@@ -1,23 +1,26 @@
 # encoding:utf-8
 require "cseg/version"
-require "tempfile"
 class Kurumi
 	# since crf++ can only read from file
-	@modle=File.expand_path("../../data/pkumodle.data", __FILE__)
-	def self.segment(str)
-		tmpstr=""
-		for i in 0..str.length-1
-			tmpstr+=str[i]+"\n"
+	@modle_sp=File.expand_path("../../data/as_training.data", __FILE__)
+	@modle_tr=File.expand_path("../../data/as_training_less.data", __FILE__)
+	def self.segment(str, mode="sp")
+	  @result=Array.new
+	  	case mode
+			when "sp"
+			       @modle=@modle_sp
+			when "tr"
+		 		@modle=@modle_tr
+			else
+			raise "no such parameter, please use sp or tr"		
 		end
-		@tmp=Tempfile::new("tmp")
-		@resultfile=Tempfile::new("result")
-		@tmp.write(tmpstr)
-		@tmp.rewind
-		@result=Array.new
-		system("crf_test -m #{@modle} #{@tmp.path}>#{@resultfile.path}")
-		@resultfile.rewind
+	  result_data = IO.popen "crf_test -m #{@modle}", 'r+' do |io|
+  		io.puts *str.chars
+  		io.close_write
+  		io.read
+	  end
 		word=""
-		@resultfile.read.each_line{|line|
+		result_data.each_line{|line|
 			token=line.chomp.split("	")
 			if token[1]=="B"or token[1]=="O"
 				if word!=""
@@ -27,6 +30,7 @@ class Kurumi
 			elsif token[1]=="I"
 				word+=token[0]
 			else
+				#nil
 				if word!=""
 					@result.push(word)
 					word=""
@@ -34,12 +38,8 @@ class Kurumi
 			end
 
 		}
-		
-		@resultfile.close(true)
-		@tmp.close(true)
 		return @result
 	end
 end
 
- # result=Kurumi.segment("屌丝是一种生活态度")
- # print result
+print Kurumi.segment("屌丝是一种自我讽刺。")

data/lib/cseg/version.rb

@@ -1,3 +1,3 @@
 module Cseg
-  VERSION = "0.0.5"
+  VERSION = "0.1"
 end

metadata

@@ -1,17 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: cseg
 version: !ruby/object:Gem::Version
-  version: 0.0.5
-  prerelease: 
+  version: '0.1'
 platform: ruby
 authors:
 - gyorou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-25 00:00:00.000000000 Z
+date: 2014-09-08 00:00:00.000000000 Z
 dependencies: []
-description: ! '"a chinese segmentation tool using CRF++"'
+description: '"a chinese segmentation tool using CRF"'
 email:
 - gyorou@tjjtds.com
 executables: []
@@ -19,37 +18,37 @@ extensions: []
 extra_rdoc_files: []
 files:
 - .gitignore
+- Gemfile
 - LICENSE.txt
 - README.md
-- Gemfile
+- Rakefile
+- cseg.gemspec
+- data/as_training_less.data
 - data/pkumodle.data
-- lib/cseg/version.rb
 - lib/cseg.rb
-- cseg.gemspec
-- Rakefile
+- lib/cseg/version.rb
 homepage: ''
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 - data
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.28
+rubygems_version: 2.4.1
 signing_key: 
-specification_version: 3
-summary: ! '"CRF++ should be installed and set in the environment variables"'
+specification_version: 4
+summary: '""'
 test_files: []