cseg 0.0.2 → 0.0.3

data/README.md

@@ -20,26 +20,17 @@ Or install it yourself as:
 
 you need to install CRF++ first and set the environment environment variables.
 
-Here is the site of CRF++ and you should follow the manual
+Here is the site of CRF++<http://crfpp.googlecode.com/svn/trunk/doc/index.html> and you should follow the manual
+
+On github the dictionary file was deleted since it is quite large, though you can get all from rubygems.
 	
 ## Usage
 
-	require "cseg"
-	
-	a=Kurumi.segment("屌丝是一种自我讽刺")
-	
-	=>屌丝
+    require "cseg"
+    a=Kurumi.segment("屌丝是一种自我讽刺")
+    
+    =>屌丝/是/一/种/自我/讽刺
 	
-	  是
-	  
-	  一
-	  
-	  种
-	  
-	  自我
-	  
-	  讽刺
-	  
 	the result will be an array.
 	
 

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{""}
+  gem.description   = %q{"a chinese segmentation tool using CRF++"}
+  gem.summary       = %q{"CRF++ should be installed and set in the environment variables"}
   gem.homepage      = ""
 
   gem.files         = [".gitignore",

data/lib/cseg/version.rb

@@ -1,3 +1,3 @@
 module Cseg
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/cseg.rb

@@ -3,25 +3,19 @@ require "cseg/version"
 require "tempfile"
 class Kurumi
 	# since crf++ can only read from file
-	#@tmpfile.read{|file| file=nil}
 	@modle=File.expand_path("../../data/pkumodle.data", __FILE__)
-	@result=Array.new
 	def self.segment(str)
 		tmpstr=""
 		for i in 0..str.length-1
 			tmpstr+=str[i]+"\n"
 		end
-		#@tmpfile=nil
-	@tmp=Tempfile::new("tmp")
-	@resultfile=Tempfile::new("result")
+		@tmp=Tempfile::new("tmp")
+		@resultfile=Tempfile::new("result")
 		@tmp.write(tmpstr)
 		@tmp.rewind
-		#@tmpfile.close
+		@result=Array.new
 		system("crf_test -m #{@modle} #{@tmp.path}>#{@resultfile.path}")
 		@resultfile.rewind
-	#	puts @resultfile.read
-	#	puts @tmp.read
-		
 		word=""
 		@resultfile.read.each_line{|line|
 			token=line.chomp.split("	")
@@ -33,21 +27,17 @@ class Kurumi
 			elsif token[1]=="I"
 				word+=token[0]
 			else
-				#nil
 				if word!=""
 					@result.push(word)
 				end
 			end
-			# @result.push(line.chomp.split("	")[0])
 
 		}
 		
 		@resultfile.close(true)
 		@tmp.close(true)
-		return @result
-		# puts $?
 	end
 end
 
-# result=Cseg.segment("���?�z??�܁C���ꊼ�k??�I??��")
+# result=Cseg.segment("屌丝是一种生活态度")
 # print result

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cseg
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,9 +9,9 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-13 00:00:00.000000000 Z
+date: 2014-02-17 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: []
@@ -48,8 +48,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 1.8.28
 signing_key: 
 specification_version: 3
-summary: ! '""'
+summary: ! '"CRF++ should be installed and set in the environment variables"'
 test_files: []